CN111406224A

CN111406224A - Target reliability determination method, target identification system, vehicle and storage medium

Info

Publication number: CN111406224A
Application number: CN201980005757.0A
Authority: CN
Inventors: 陆新飞; 李怡强; 陈雷
Original assignee: SZ DJI Technology Co Ltd
Current assignee: Shenzhen Zhuoyu Technology Co ltd
Priority date: 2019-01-30
Filing date: 2019-01-30
Publication date: 2020-07-10
Anticipated expiration: 2039-01-30
Also published as: WO2020154962A1; CN111406224B

Abstract

A target reliability determination method, a target identification method, a system, a movable platform and a storage medium are provided. The target reliability determination method comprises the following steps: acquiring detection information of a detection target and information of a Doppler cell around the detection target (S201); determining the reliability of the type of the detection target according to the detection information of the detection target and the information of Doppler units around the detection target (S202). The target identification method comprises the following steps: detecting the same detection target for multiple times; determining the current reliability of the detection target according to the current detection result of the detection target and the last reliability of the detection target; and determining the detection target as a specific target type according to the current credibility. The method adopts the radar to determine the credibility of the detection target and determine whether the detection target is a specific target type, thereby improving the accuracy of identifying the target type.

Description

Target reliability determination method, target identification system, vehicle and storage medium

The disclosure of this patent document contains material which is subject to copyright protection. The copyright is owned by the copyright owner. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the patent and trademark office official records and records.

Technical Field

The embodiment of the application relates to the technical field of unmanned driving, in particular to a target reliability determination method, a target identification system, a radar, a movable platform and a storage medium.

Background

With the development of the unmanned driving industry, assisted driving and automatic driving become current research hotspots, and in the fields of assisted driving and automatic driving, the identification of targets is important for realizing unmanned driving. For example, different types of targets such as pedestrians, vehicles, guideboards and the like are effectively identified, and then functions such as deceleration avoidance, emergency stop, obstacle detouring, lane changing, automatic stop according to specific situations are performed.

In the conventional technology, an image of a target is mainly acquired by a vision sensor to identify the target. However, the vision sensor does not have the characteristics of all-time and all-weather identification when identifying the target. For example, in the case of weak light, rain, snow and haze, the effect of the visual sensor on collecting the image is not good, and the effect of the visual sensor on target identification is obviously reduced. At this time, if the vision sensor is solely relied on, a large number of scenes with automatic driving failures are possible. Compared with a visual sensor, the millimeter wave radar has the advantages of all-time and all-weather operation and the like, but the related technology cannot realize effective identification of the target through the millimeter wave radar.

Disclosure of Invention

The embodiment of the application provides a target reliability determination method, a target identification system, a radar, a movable platform and a storage medium.

In a first aspect, an embodiment of the present application provides a method for determining a target reliability, where the method includes:

acquiring detection information of a detection target and information of Doppler units around the detection target;

and determining the credibility of the type of the detection target according to the detection information of the detection target and the information of Doppler units around the detection target.

In a second aspect, an embodiment of the present application provides a target identification method, where the method includes:

detecting the same detection target for multiple times;

determining the current reliability of the detection target according to the current detection result of the detection target and the last reliability of the detection target;

and determining the detection target as a specific target type according to the current credibility.

In a third aspect, embodiments of the present application provide a target credibility determination system, which includes one or more processors, working collectively or individually, the processors being configured to perform the following operations:

In a fourth aspect, embodiments of the present application provide an object recognition system, which includes one or more processors, working collectively or individually, the processors being configured to:

detecting the same detection target for multiple times;

In a fifth aspect, an embodiment of the present application provides a radar, including:

the antenna is used for acquiring echo signals;

a processor, communicatively coupled to the antenna, configured to perform the method according to any one of the first and/or second aspects of the present application.

In a sixth aspect, an embodiment of the present application provides a movable platform, including:

a body;

the power system is arranged on the machine body and used for providing power;

and a radar according to any one of the fifth aspect of the present application.

In a seventh aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored thereon, and the computer program is executed by a processor to implement the steps of the target reliability determination method provided in the technical solution of the first aspect of the present application and/or the target identification method provided in the technical solution of the second aspect of the present application.

In the embodiment of the application, the target is detected, the detection information of the target and the information of the doppler cells around the target are obtained, and the target is identified according to the obtained information. The target can be effectively identified all day long and all weather, and the stability and safety of automatic driving/assistant driving are improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or technical solutions in the prior art, the drawings required to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a schematic diagram illustrating an application scenario provided in an embodiment of the present application;

fig. 2 is a schematic flowchart illustrating a target reliability determination method according to an embodiment of the present application;

fig. 3 is a schematic flowchart illustrating a target reliability determination method according to an embodiment of the present application;

fig. 4 is a flowchart illustrating a target reliability determination method according to an embodiment of the present application;

FIG. 5 is a flow chart illustrating a method for object recognition according to an embodiment of the present application;

FIG. 6 is a flow chart illustrating a method for object recognition according to another embodiment of the present application;

FIG. 7 is a flow chart illustrating a method for object recognition according to another embodiment of the present application;

FIG. 8A illustrates a Doppler-range plane image provided in accordance with an embodiment of the present application, and FIG. 8B illustrates an algorithm implementation in accordance with an embodiment of the present application;

fig. 9 is a schematic structural diagram of a target reliability determination system according to an embodiment of the present application;

FIG. 10 is a schematic diagram illustrating an exemplary embodiment of a target recognition system;

FIG. 11 is a schematic diagram of a radar according to an embodiment of the present application;

FIG. 12 is a schematic diagram illustrating a structure of a movable platform according to an embodiment of the present application;

fig. 13 shows a schematic structural diagram of a movable platform according to an embodiment of the present application.

Detailed Description

In order to improve the safety of an automatic driving/assistant driving system, the embodiment of the application provides a target reliability determination method, a target identification method, a system, a mobile platform and a storage medium. At least one sensor carried on the movable platform: vision systems, laser radar, millimeter wave radar, ultrasonic radar, identifying the target by using at least one of the sensors required for autopilot/assisted driving. The target is identified, for example, by at least one of the above-mentioned sensors carried on the movable platform. The target may be a person, animal, tree, vehicle, guideboard, fence, drone, or the like. The target identification method can be used for determining the type of the target, determining the flight path of the target, planning the flight path of the movable platform, working of the movable platform and other scenes.

The reliability is an evaluation index for measuring the reliability of the type of the detection target. And acquiring information of the detection target returned in the echo signal by detecting the detection target, and generating the type credibility of the detection target according to the acquired information of the detection target. The higher the credibility is, the higher the credibility for determining the type of the detection target is proved to be; the lower the confidence level, the lower the confidence level of the certification for determining the type of the detection target. And finally determining the type of the detection target by judging the credibility determined by the multiple times of detection for multiple times.

In some embodiments, the detection target is determined to be a specific target type, such as a pedestrian target, an unmanned aerial vehicle target, and the like, by detecting the same detection target multiple times and according to the current detection result of the detection target and the last detection result of the detection target.

In some embodiments, after the target is identified by the target identification method, the track of the target can be recorded and predicted, so that the target can be tracked.

In some embodiments, after the target is identified by the target identification method, the motion trajectory of the movable platform can be planned according to the current flight path of the target. For example, deceleration avoidance, emergency stop, obstacle detour, lane change, automatic stop, and the like are performed.

The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Fig. 1 provides an example of an application scenario provided in the embodiment of the present application. Referring to fig. 1, the movable platform is an unmanned vehicle 10, and includes a vehicle body 101 and a radar 102. The radar 102 is mounted on the vehicle body 101.

The radar may be mounted on a movable platform, e.g., a robot, an unmanned aerial vehicle, an unmanned vehicle, a general vehicle, VR glasses, AR glasses, etc. For example, the radar may be integrated at one or more positions of the vehicle, or may be a device mounted on the vehicle, such as an on-board device, without limitation. The radar may be a millimeter-wave radar or other types of radar sensors, which is not limited to this. The radar comprises at least an antenna for receiving the echo signals.

In the present embodiment, the radar 102 moves along with the movement of the unmanned vehicle 10, performs detection on a target to be detected to acquire data for target reliability determination and target identification, acquires detection information of the detected target and information of a doppler cell around the detected target, and determines reliability of the type of the detected target according to the detection information of the detected target and the information of the doppler cell around the detected target; determining the current reliability of the detection target according to the current detection result of the detection target and the last reliability of the detection target; and determining the detection target as a specific target type according to the current credibility.

The radar 102 used for target reliability determination and target identification in the present embodiment may be a millimeter microwave radar.

Fig. 2 is a schematic flowchart of a target reliability determination method according to an embodiment of the present application. As shown in fig. 2, the method may include:

s201, acquiring detection information of a detection target and information of Doppler units around the detection target.

The execution body may be a radar or a mobile platform mounted processor. The following describes the target reliability determination method in detail by taking an execution subject as a radar as an example.

In some embodiments, the detection information of the detection target includes at least one of: distance, scattering intensity, velocity information, angle information, observation energy. Wherein the distance information comprises a radial distance of the detection target relative to the radar; the scattering intensity information comprises the echo intensity of a scattering echo generated by a detection target under the irradiation of radar waves; the velocity information comprises radial velocity data of the detected object relative to the radar determined by the Doppler shift; the angle information is the angle of the target object relative to the radar; the observation energy is the energy of the echo signal.

Specifically, the radar acquires detection information of a detection target by transmitting an electromagnetic wave and receiving a feedback echo signal. Optionally, the echo signal is a Frequency Modulated Continuous Wave (FMCW), such as a fast scan waveform, a triangular wave, or a sawtooth wave.

In some embodiments, detecting information of doppler cells around the target includes at least one of: the Doppler unit around the detected target on the Doppler-distance plane image acquired when the radar detects the detected target, the Doppler energy of each Doppler unit around the detected target, and the number of Doppler units with the Doppler energy larger than a preset Doppler energy threshold value. Thereby determining the number of Doppler units with Doppler energy larger than the preset Doppler energy threshold value.

Specifically, the information of the doppler unit around the detection target may include, but is not limited to: acquiring a Doppler-range plane image by a radar, the Doppler-range plane image including a plurality of Doppler cells around a target; and comparing the energy value of the Doppler unit with a preset Doppler energy threshold value, and recording the number of the Doppler units with Doppler energy larger than the preset Doppler energy threshold value. Optionally, adding the doppler unit with the doppler energy greater than a preset doppler energy threshold to the doppler unit set; otherwise, the Doppler unit is discarded.

The preset doppler energy threshold may be a preset fixed value or an energy value of a reference doppler unit. The doppler energy threshold may be determined by the noise signal strength of the radar and the doppler energies corresponding to different classes of targets. And the average energy of the noise is counted, and the average energy of the noise is selected to be added with a constant Pn to be used as a Doppler energy threshold value. The constant Pn is energy information of the radar acquisition target. Pn is obtained by collecting and training targets of different classes for multiple times.

In this embodiment, the detection information of the detection target includes at least one of: distance, scattering intensity, velocity information; and detecting information of the Doppler cells around the target includes at least one of: the doppler power of each doppler cell around the target and the number of doppler cells having doppler power greater than the preset doppler power threshold are detected as an example for explanation.

The acquiring of the detection information of the detection target and the information of the doppler units around the detection target specifically includes:

and acquiring information of Doppler units around the detection target at the same time of acquiring detection information of the detection target. That is, detection information of the detection target and information of the doppler cells around the detection target are acquired at the same time or after the detection of the detection target.

Or, first obtaining detection information of the detection target, and if the detection information of the detection target meets a first preset condition, obtaining information of doppler units around the detection target; and/or if the detection information of the detection target does not meet the first preset condition, no longer acquiring the information of the Doppler units around the detection target. The detection information is judged once, and the information of the Doppler units around the detection target is obtained only when the first preset condition is met. Therefore, the frequency of acquiring the information of the Doppler units around the detection target is reduced, the calculation amount is reduced, and the calculation speed of the system is improved.

Specifically, the determining whether the detection information satisfies the first preset condition specifically includes, but is not limited to, the following methods: and judging whether the specific parameters contained in the detection information are in the corresponding threshold value range. For example, it is determined whether the scattering intensity is within a preset scattering intensity threshold range, whether the velocity information is within a preset velocity threshold range, and the like. The following three scenarios are exemplified:

for example, the detection information includes scattering intensity information, and if the scattering intensity is within a preset scattering intensity threshold range, the detection information of the detection target satisfies a first preset condition, and information of doppler units around the detection target is acquired. In some embodiments, if the scattering intensity is not within a preset scattering intensity threshold range, the detection information of the detection target does not satisfy the first preset condition, and information of doppler cells around the detection target is not acquired.

For another example, the detection information includes velocity information, and if the velocity information is within a preset velocity threshold range, the detection information of the detection target satisfies a first preset condition, and information of a doppler unit around the detection target is acquired. In some embodiments, if the speed information is not within a preset speed threshold range, the detection information of the detection target does not satisfy the first preset condition, and information of a doppler unit around the detection target is not acquired.

For another example, the detection information includes scattering intensity information and velocity information, and if the scattering intensity is within a preset scattering intensity threshold range and the velocity information is within a preset velocity threshold range, the detection information of the detection target satisfies a first preset condition, and information of doppler units around the detection target is obtained. That is, only when both are satisfied, the detection information of the detection target satisfies the first preset condition, and the information of the doppler cell around the detection target is acquired. In some embodiments, if the scattering intensity is not within a preset scattering intensity threshold range, the velocity information is not within a preset velocity threshold range, the detection information of the detection target does not satisfy the first preset condition, and information of a doppler unit around the detection target is not acquired.

On the basis of the above embodiment, the scattering intensity threshold range is determined, which specifically includes, but is not limited to, the following methods:

(1) and acquiring the scattering intensity of the external target at different distances.

The targets of the same category are different in distance from the radar, and detection information contained in echo signals acquired by the radar is different. For example, in the case of different distances from the radar, the radar performs multiple detections on the same target to obtain the scattering intensity of targets located at different distances. In some embodiments, the acquired scattering intensities of targets located at different distances are averaged in advance to improve the accuracy of the process of determining the confidence level of the targets. In some embodiments, the radar performs multiple detections on targets in multiple different classes of targets to obtain the scattering intensity of targets located at different distances.

In this embodiment, the scattering intensity of the pedestrian target at different distances is obtained as an example. In an external field test, the radar detects the pedestrian target to acquire the scattering intensity of the pedestrian target at different distances. And then, recording the distance information and the scattering intensity information corresponding to the distance information at the same time. And averaging the acquired scattering intensities of the pedestrian targets at different distances to form a scattering intensity average value and a distance information change curve or a scattering intensity average value and distance information lookup table of the pedestrian targets.

(2) And determining the scattering intensity threshold range according to the scattering intensities of the external targets at the different distances.

In some embodiments, the scattering intensity threshold is determined from the scattering intensity average and the distance information variation curve. Alternatively, respective threshold ranges of scattering intensity are determined for different types of targets, taking into account that different types of targets have different scattering intensities. In some embodiments, the scatter intensity threshold is also determined by the noise signal strength of the radar, taking into account that the radar has noise. And by counting the average intensity of the noise, the average intensity of the noise is selected to be added with the acquired scattering intensities of the target at different distances to be used as a scattering intensity threshold value.

In this embodiment, in the moving or stationary process of the movable platform, the radar installed on the movable platform detects an external target, and performs multiple detections on the same target to obtain detection information of targets located at different distances, and processes the detection information to determine the scattering intensity threshold range, so as to improve the accuracy of the process of determining the reliability of the target.

S202, determining the credibility of the type of the detection target according to the detection information of the detection target and the information of Doppler units around the detection target.

On the one hand, different classes of targets, have different motion velocities and/or scattering intensities. For example, the speed of the pedestrian target does not exceed a certain predetermined value, and the scattering intensity of the pedestrian target is weak relative to the vehicle. In some embodiments, the confidence level of the type of the detection target is determined according to the acquired detection information of the detection target. For example, by acquiring information such as the velocity, scattering intensity, distance, etc. of the detection target, the confidence level of the type of the detection target is determined.

Specifically, the pedestrian target will be described as an example. For example, the obtained speed information of the detection target may be used to determine the confidence level of the type of the detection target in combination with the speed ranges corresponding to different types of targets. And when the acquired speed information of the detection target meets the speed range corresponding to the pedestrian target, adding the credibility that the detection target is the pedestrian, for example, adding a first preset value. And/or when the acquired speed information of the detection target does not meet the speed range corresponding to the pedestrian target, subtracting the credibility of the detection target being the pedestrian, for example, subtracting a second preset value.

For another example, the acquired scattering intensity of the detection target may be compared with a previously generated look-up table for forming a scattering intensity average value and a distance information variation curve, or a scattering intensity average value and a distance information of a pedestrian target. And when the acquired scattering intensity of the detection target meets a preset scattering intensity range corresponding to the pedestrian target, adding the credibility that the detection target is the pedestrian, for example, adding a first preset value. And/or when the acquired scattering intensity of the detection target does not meet the preset scattering intensity range corresponding to the pedestrian target, subtracting the credibility of the detection target as the pedestrian, for example, subtracting a second preset value.

For another example, when the acquired speed information of the detection target meets a speed range corresponding to the pedestrian target and the acquired scattering intensity of the detection target meets a preset scattering intensity range corresponding to the pedestrian target, the credibility that the detection target is the pedestrian is added; otherwise, the credibility that the detection target is the pedestrian is subtracted.

On the other hand, the motion of the target is complex, and not only has overall motion, but also has micro motion of acceleration, vibration, rotation, rolling and the like. The micro-motion of the target has corresponding micro-Doppler characteristics, wherein the contained landmark information of the target types such as motion, behavior and the like reflects the fine characteristics of the target. The micro-motions of different classes of targets have different micro-doppler characteristics, thereby making the identification of the targets unique. For example, when a human body moves, the human body has obvious micro-doppler characteristics due to the swinging of limbs, and the micro-doppler characteristics contain landmark information such as the movement and the behavior of the human body. Landmark information, such as doppler energy, is extracted from the micro-doppler features to effectively identify pedestrian objects.

In some embodiments, information of doppler cells around a detection target is obtained and analyzed to obtain corresponding micro-doppler features, and landmark information, such as doppler energy, is extracted from the micro-doppler features to obtain the doppler cells with doppler energy greater than a preset doppler energy threshold, so as to determine the confidence level according to the number of the doppler cells with doppler energy greater than the preset doppler energy threshold. By acquiring and analyzing the information of the Doppler units around the detected target, the method has higher accuracy for determining the type of the target.

Specifically, the explanation will be given taking the example of determining the reliability that the type of the detection target is a pedestrian. When the number of the Doppler units with Doppler energy larger than a preset Doppler energy threshold value is larger than or equal to a Doppler unit number threshold value, adding the credibility that the detected target is a pedestrian; and/or when the number of the Doppler units with Doppler energy larger than a preset Doppler energy threshold value is smaller than a Doppler unit number threshold value, the credibility that the detection target is the pedestrian is subtracted.

In this embodiment, the method for determining the confidence level of the type of the detection target according to the detection information of the detection target and the information of the doppler cells around the detection target specifically includes:

the detection information includes scattering intensity information. When the scattering intensity is within a preset scattering intensity threshold range and the information of the Doppler units around the detection target meets a preset Doppler unit condition, increasing a first preset value by the reliability; otherwise, subtracting a second preset value from the reliability.

Alternatively, the detection information includes speed information. When the speed information is within a preset speed threshold range and the information of the Doppler units around the detection target meets a preset Doppler unit condition, increasing a first preset value by the reliability; otherwise, subtracting a second preset value from the reliability.

Alternatively, the detection information includes scattering intensity information and velocity information. When the speed information is within a preset speed threshold range, the scattering intensity is within the preset scattering intensity threshold range, and the information of the Doppler units around the detection target meets the preset Doppler unit condition, the reliability is increased by a first preset value; otherwise, subtracting a second preset value from the reliability.

In some embodiments, determining the type of the target according to the determined credibility of the type of the detection target is further included. Optionally, at least one confidence range for different types of targets is preset. And when the determined credibility of the type of the detection target is within a certain credibility range, determining that the target is the target type corresponding to the credibility range.

According to the target reliability determining method provided by the embodiment of the application, the reliability of the type of the detection target is determined by acquiring the detection information of the detection target and the information of the Doppler units around the detection target and according to the detection information of the detection target and the information of the Doppler units around the detection target. Thereby determining the trustworthiness of the target type based on the information acquired by the radar. The speed of system operation is improved, accuracy of determining the type of the detection target is facilitated, and safety and stability in the automatic driving/auxiliary driving process are facilitated to be improved.

On the basis of fig. 2, fig. 3 is a schematic flowchart of a target reliability determination method provided in an embodiment of the present application. Please refer to fig. 3, which specifically includes:

step S301, acquiring the number of the Doppler units with the scattering intensity within a preset scattering intensity threshold range.

In this embodiment, the method specifically includes:

(1) and acquiring the Doppler energy of each Doppler unit around the detection target.

Energy values, distance values, velocity values, and the like of a large number of scattering points (doppler cells) of a detection target can be acquired by radar. Alternatively, the relationship between the energy value and the range value of each doppler cell may form a doppler-range plane, which includes a plurality of doppler cells.

In some embodiments, before acquiring the doppler energy of each doppler cell around the detection target of the detection target, the method further includes preprocessing the echo signal acquired by the radar to acquire the doppler energy of each doppler cell around the detection target. For example, the radar performs coherent accumulation on echo signals acquired by the radar by using a Fast Fourier Transform (FFT) technique to acquire doppler energy of each doppler cell around a detection target. Of course, in practical application, other techniques may also be used for obtaining, which is not limited to this.

(2) And determining the number of the Doppler units with the scattering intensity within a preset scattering intensity threshold range according to the Doppler energy of each Doppler unit.

Energy screening is performed for each doppler cell around the detection target, for example, by filtering through RCS (Radar cross section) or CFAR (Constant False Alarm Rate) algorithm. The preset Doppler energy threshold value can be obtained through a correlation method, and after the Doppler energy of each Doppler unit around the detected target is obtained through the radar, the Doppler units around the detected target can be filtered by the preset Doppler energy threshold value, so that invalid Doppler units are filtered, the influence of the invalid Doppler units on subsequent judgment is avoided, and the calculation amount is reduced. In some embodiments, the filtered doppler cells may be further filtered twice, for example, by using a one-ring rule to output a doppler cell with higher quality, so as to determine to further reduce the amount of computation and improve the processing efficiency.

Specific methods for determining the preset doppler energy threshold can be seen in, but not limited to, the following methods:

firstly, for different types of targets, the radar can acquire energy information and distance information of the targets at different moments in advance. For example, a radar mounted on a movable platform may continuously acquire doppler power information and range information of a target during movement of the movable platform. And then, acquiring a variation curve of the energy and the distance of the radar according to the Doppler energy information and the distance information. And finally, determining a preset Doppler energy threshold value curve according to the change curve.

In some embodiments, the preset doppler energy threshold may also be modified based on noise data of the radar, in some embodiments, taking into account that the radar has noise. For example, the background noise of the radar may be added to the preset doppler energy threshold to obtain the corrected preset doppler energy threshold. Of course, in practical applications, the preset doppler energy threshold may be modified in other manners, which is not limited in this respect.

Step S302, determining whether the number of the Doppler units is within a preset Doppler unit number range or not according to the number of the Doppler units, and determining the reliability.

In the present embodiment, a pedestrian target is taken as an example for explanation. The method specifically comprises the following steps: if the number of the acquired Doppler units with the Doppler energy of the detected target being larger than the preset Doppler energy threshold value is within the range of the number of the preset Doppler units corresponding to the pedestrian target, increasing a third preset value to the credibility; and/or if the number of the Doppler units is not within the range of the preset number of Doppler units corresponding to the pedestrian target, subtracting a fourth preset value from the reliability.

Specific methods for determining the range of the preset doppler unit number can be seen in the following methods:

the number of the doppler cells with doppler energy greater than the preset doppler energy threshold value at different distances of the pedestrian target is taken as an example for explanation. The radar acquires the number of Doppler units of which the Doppler energy of the pedestrian target at different distances is greater than a preset Doppler energy threshold value by detecting the pedestrian target. And then, recording the distance information and the number of the Doppler units with the Doppler energy of the pedestrian target corresponding to the distance information larger than a preset Doppler energy threshold value at the same time. Averaging the acquired number of the Doppler units with the Doppler energy of the pedestrian targets at different distances larger than a preset Doppler energy threshold value to form a Doppler unit number threshold value average value and a distance information change curve or a Doppler unit number threshold value average value and a distance information lookup table of the pedestrian targets.

According to the target reliability determining method provided by the embodiment of the application, the number of the detecting units with the Doppler energy larger than the preset Doppler energy threshold value in the Doppler units around the detected target is obtained, and the reliability of the type of the target is determined, so that the accuracy of determining the type of the detected target is facilitated, and the safety and the stability in the automatic driving/auxiliary driving process are improved.

On the basis of the embodiment shown in fig. 2, fig. 4 is a schematic flowchart of a target reliability determination method provided in an embodiment of the present application, and specifically includes:

step S401, obtaining the distance information;

specifically, the radial distance of the detection target with respect to the radar or a movable platform on which the radar is mounted is acquired.

Step S402, judging whether the distance information is smaller than a preset distance or not according to the distance information;

specifically, the description will be given taking an example in which the radar is mounted on an automobile. And judging whether the distance information is smaller than a preset distance according to the acquired radial distance of the detection target relative to the radar or the automobile provided with the radar. Optionally, in a plurality of external field tests, the preset distance is determined in advance. For example, a fixed value of the preset distance is determined in advance, or the preset distance at different vehicle speeds is determined according to the vehicle speed of the vehicle on which the radar is mounted. It will be appreciated that the determination of the preset distance is also related to at least one of the following factors: weather conditions, illumination intensity, driver's eyesight, braking equipment, road surface conditions. The method for determining the preset distance according to any of the above factors is not limited herein.

The preset distance is greater than or equal to the safe vehicle distance, namely the preset distance is greater than or equal to the necessary spacing distance kept between the radar-mounted vehicle and the detection target during driving. So that enough braking space (including braking time, braking distance and the like) is reserved in emergency, and the safe driving of the automobile is facilitated.

And S403, if the distance information is smaller than a preset distance, controlling the movable platform to execute obstacle avoidance operation, or controlling an alarm device to perform alarm processing.

In some embodiments, the alarm device is controlled to perform alarm processing, and the alarm device comprises a movable platform provided with the radar, a digital display alarm or a voice broadcast alarm or a vibration alarm, wherein the movable platform displays an alarm through an L ED lamp according to the distance information, or the alarm device can be the movable platform or other control platforms, and also can be APP of corresponding equipment, so that the safety in the automatic driving/auxiliary driving process is ensured.

According to the target reliability determining method provided by the embodiment of the application, the distance information of the detected target is obtained, whether the distance information is smaller than the preset distance or not is judged, and once the distance information is smaller than the preset distance, the movable platform is controlled to execute obstacle avoidance operation, or an alarm device is controlled to perform alarm processing. Therefore, passengers or drivers can know abnormal conditions in the driving process in time, and the safety in the automatic driving/auxiliary driving process is ensured.

Fig. 5 is a schematic flowchart of a target identification method according to another embodiment of the present application, including:

and step S501, detecting the same detection target for multiple times.

When a detection target is detected, interference may be caused in the detection process, so that the detection results are too different when the detection is carried out successively. Therefore, the reliability differences respectively determined according to the detection results determined at the successive detection times are too large, and further, the result that the target is determined to be the determined target type is caused to have a problem. For example, when a detection target is detected by a radar, the detection result may be affected by multipath interference. The following description will be given taking an example of detection of a detection target by radar.

In some embodiments, the radar performs detection once per pair of the same detection target, and obtains the detection result of the same detection target once. Optionally, the radar may detect a plurality of detection targets simultaneously or asynchronously, and obtain a detection result of each detection target respectively. Optionally, the detection result includes, but is not limited to, detection information of a detection target and information of a doppler cell around the detection target.

In some embodiments, the radar acquires a current detection result of the detection target according to the echo signal. Optionally, the current detection result of the detection target is obtained through a chirp continuous wave radar echo signal.

Step S502, determining the current reliability of the detection target according to the current detection result of the detection target and the last reliability of the detection target.

The radar detects the same detection target every time, and can determine the primary reliability according to the detection information acquired every time. When the radar detects the same detection target at the current time, the determination of the current reliability depends on the detection information acquired at the current time and the last reliability. Therefore, as the detection times of the radar for detecting the same detection target are increased, the current credibility of the detection target is continuously updated.

In some embodiments, the current confidence level of the detected object is determined by the following method for the current detection result: if the current detection result meets a second preset condition, the current credibility is the last credibility increased by a first preset value; otherwise, the current reliability is the last reliability minus a second preset value.

Wherein, the current detection result includes but is not limited to: the detection information of the detection target at the current moment and the information of the Doppler units around the detection target. Optionally, the second preset condition is: the detection information of the detection target at the current moment meets a preset detection information condition and the information of the Doppler units around the detection target meets a preset Doppler condition.

Specifically, if the detection information of the detection target at the current moment meets a preset detection information condition and the information of the doppler units around the detection target meets a preset doppler condition, the current reliability is the last reliability increased by a first preset value; otherwise, the current reliability is the last reliability minus a second preset value.

It should be noted that the object reliability determination method referred to in the embodiments of the present application may also be used in the embodiments of the object identification method described above. Optionally, the "preset detection information condition" described in the above embodiment corresponds to the "first preset condition" related to the embodiment of the present application shown in fig. 2. Optionally, the "preset doppler condition" described in the above embodiment corresponds to the "preset doppler cell number range" and the "preset doppler power threshold" related to the embodiment of the present application shown in fig. 2.

In some embodiments, a plurality of detection targets may be detected respectively, and detection results may be obtained respectively. The acquired multiple detection results of multiple detection targets can be processed simultaneously or asynchronously. Therefore, the target types of a plurality of detection targets are determined, and the safety and the reliability of the operation of the automatic driving/auxiliary driving system are improved.

And S503, determining the detection target to be a specific target type according to the current credibility.

The current trustworthiness of the detection target characterizes the trustworthiness of the detection target for the particular target type at the current time. Along with the increase of the detection times of the radar for detecting the same detection target, the current credibility of the detection target is continuously updated. Therefore, under the condition of detecting the same target for multiple times to determine and update the current reliability of the detection target, whether the detection target is a specific target type or not can be accurately determined through the current reliability of the detection target.

Optionally, the type of the detection target is determined according to the number of times of detecting the same detection target and the current reliability. Specifically, the description will be given taking an example of determining whether the detection target is a pedestrian target. Detecting a detection target for the first time by a radar, acquiring a first detection result, and determining the first credibility of the detection target as a pedestrian target according to the detection result; and then, detecting the detection target for the second time by the radar, acquiring a second detection result, and according to the detection result, performing addition or subtraction on the basis of the first credibility to determine the second credibility of the detection target which is the pedestrian target. And so on to the nth time. And finally, determining whether the detected target is a pedestrian target according to the Nth credibility.

According to the target identification method provided by the embodiment of the application, the current reliability of the detection target is determined according to the current detection result of the detection target and the last reliability of the detection target by detecting the same detection target for multiple times; and determining the detection target as a specific target type according to the current credibility. Thereby determining whether the target is of a particular target type based on information acquired by the radar. The problem of the determination of the target type caused by abnormal detection results is effectively solved, the accuracy of target identification is improved, and the safety and the stability in the automatic driving/auxiliary driving process are further improved.

On the basis of the embodiment shown in fig. 5, fig. 6 is a schematic flowchart illustrating a target identification method according to another embodiment of the present application, including:

step S601, when the number of times of detecting the same detection target is smaller than a first preset number of times of detection, comparing the current reliability of the detection target determined by detecting the same detection target each time with a first preset reliability.

Specifically, the description will be given taking an example in which the detection target is determined to be a pedestrian target. And presetting a detection time threshold value for detecting the same detection target as a stop condition for detecting the same detection target for multiple times. For example, a first preset number of detections is set as the threshold number of detections. And setting a reliability threshold as a judgment condition for determining whether the detected target is a pedestrian target. For example, a first predetermined confidence level is set as a confidence level threshold. Along with the increase of the detection times of the radar for detecting the detection target, the current credibility of the detection target is updated on the basis of the previous credibility. When the detection times of the radar for detecting the detection target are less than a first preset detection time, comparing the current reliability of the detection target determined by detecting the same detection target each time with a first preset reliability. Once the detection times for detecting the detection target are greater than or equal to the first preset detection times, the detection target is not detected any more, and therefore the current reliability of the detection target determined by detecting the same detection target does not need to be compared with the first preset reliability. Thereby, the operation speed is increased, and the efficiency of determining that the detection target is a specific target type is improved.

Step S602, if the current reliability of the detection target determined by probing the same detection target each time is less than the first preset reliability, determining that the detection target is not the specific target type; and/or determining that the detection target is the specific target type once the current credibility is greater than the first preset credibility.

Specifically, the description will be given taking an example in which the detection target is determined to be a pedestrian target. Optionally, a first preset detection time is used as a detection time threshold for detecting the same detection target, that is, as a stop condition for detecting the same detection target for multiple times. And stopping detecting the same detection target when the detection times of detecting the same detection target for multiple times reach a first preset detection time. Thereby completing the determination of whether the detection target is the specific target type within a limited number of times.

For example, if the reliability of each of the detection targets determined by detecting the same detection target is less than the first preset reliability until the number of times of detection of the same detection target reaches the first preset number of times of detection, it is determined that the detection target is not a pedestrian target. Therefore, the calculation amount of the system is reduced, and the efficiency of identifying the detection target is improved.

For another example, when the number of times of probing the same detection target does not reach a first preset number of times of probing, after each time of probing the detection target, the current reliability of the detection target is compared with the first preset reliability, and if the current reliability of the detection target is greater than the first preset reliability, the detection target is determined to be a pedestrian target. And the same detection target is no longer detected, and it is no longer determined whether the detection target is a pedestrian target. Therefore, the calculation amount of the system is reduced, and the rapid identification of the detection target is realized.

According to the target identification method provided by the embodiment of the application, when the frequency of detecting the same detection target does not reach a first preset detection frequency, the type of the detection target is determined according to the current credibility of the detection target. When the target is determined to be in a specific category, determining the value; and if the target is not determined to be in the specific category in the first preset times, judging that the target is not in the specific target type. By the method, the efficiency of target identification is effectively improved, and meanwhile, the safety in the automatic driving/auxiliary driving process is also improved.

On the basis of the embodiment shown in fig. 5, fig. 7 is a schematic flowchart of a target identification method according to another embodiment of the present application, including:

step S701, when the number of times of probing the same detection target is smaller than the first preset probing number of times and the current reliability is greater than the first preset reliability, decreasing the first preset reliability by a fifth preset value.

When the radar detects a target, due to the existence of a multipath interference phenomenon, signals returned from the target reach the radar antenna through different paths, so that the radar works unstably, and the detection result of the radar has errors. By detecting the same detection target for multiple times, detection errors can be effectively eliminated, and the method is favorable for improving the identification capability of the radar on target categories.

Specifically, the description will be given taking an example in which it is determined that the detection target is a pedestrian target.

In some embodiments, the target is determined to be a pedestrian target according to the detection result obtained at the previous detection moment; and determining that the target is not a pedestrian target according to detection results obtained at the current and later detection time. If the number of times of detecting the same detection target is smaller than the first preset number of times of detection, after the detection result obtained at the previous detection time is determined that the target is the pedestrian target, the detection target is not detected any more, and under the condition that the detection result obtained at the previous detection time is wrong, misjudgment on whether the detection target is the pedestrian target or not may occur.

To avoid this, in some embodiments, a target detection exit hysteresis determination is set. For example, when the number of times of probing the same target is smaller than the first preset number of times of probing, after each time of probing the same target, the current reliability is compared with a first preset reliability, and if the current reliability is greater than the first preset reliability, the first preset reliability is updated, for example, a fifth preset value is decreased. Therefore, after the same detection target is detected next time, the next reliability needs to be compared with the updated first preset reliability.

In some embodiments, it is determined that the detected object is not a pedestrian object if the reliability of each of the detected objects determined by detecting the same detected object is less than a first preset reliability until the number of times of detecting the same detected object reaches a first preset number of times of detection. Optionally, at this time, the determination of whether the detected target is the pedestrian target is exited, and the first preset reliability does not need to be updated.

Step S702, when the number of times of detecting the same detection target is smaller than the first preset detection number of times and the current reliability is larger than the first preset reliability, continuing to detect the detection target, wherein the target type of the detection target is determined before continuing to detect the second preset detection number of times.

Specifically, under the condition that the number of times of detecting the same detection target is smaller than the first preset detection number of times, after detecting the same detection target each time, comparing the current reliability with a first preset reliability, and if the current reliability is larger than the first preset reliability, continuing to detect the detection target. Therefore, the method is helpful for avoiding misjudgment of the type of the detection target determined at the current moment due to the fact that the detection result obtained at the previous detection moment is wrong. Optionally, before continuing to probe the detection target, a second number of probing times is set as a termination condition for determining the target type of the detection target. In the process of continuously detecting the detection target, before the number of continuous detection times reaches a second detection time, the target type of the detection target needs to be determined. Therefore, the type of the detected target is accurately determined in the limited detection process, the processing time is reduced, and the safety of automatic driving/auxiliary driving is improved.

Step S703, if the current reliability of the detection target determined by detecting the same detection target each time is greater than or equal to a first preset reliability, determining that the detection target is the specific target type; and/or determining that the detection target is not the specific target type if the current credibility of the detection target for detecting and determining the same detection target is less than a first preset credibility.

Specifically, when the number of times of detecting the same detection target is smaller than the first preset number of times of detection, a threshold value is preset before the detection target is continuously detected, and the threshold value is used for judging whether the detection target is determined to be a specific target type.

For example, when the detection target is continuously detected, if the number of continuous detection times reaches the threshold value, the detection target is determined to be a specific target type. Optionally, the detection of the detection target may be continued thereafter. Optionally, the threshold may also be used as a stop condition for continuing to detect the same detection target, and once the number of times of continuing to detect reaches the threshold, the continuing to detect the same detection target is stopped. Therefore, the problems of large system operation amount and low operation speed caused by continuously acquiring and analyzing the streaming data information are avoided.

In this embodiment, the threshold is set by setting a second preset number of detections. And the frequency of continuously detecting the detection target is less than a second preset detection frequency. In the process, if the current reliability of the detection target determined by detecting the same detection target each time is greater than or equal to a first preset reliability, the detection target is determined to be a specific target type. And/or determining that the detection target is not a specific target type if the current reliability of the detection target determined by detecting the same detection target each time is less than a first preset reliability. By the method, misjudgment of the target type caused by jitter of the detection result is effectively avoided.

In some embodiments, when the detection target is determined to be a specific target type, the alarm device is controlled to perform alarm processing. In particular, the alarm device may be the movable platform, or other control platform, etc. Thereby ensuring safety during automatic driving/driver assistance.

In some embodiments, after determining that the detected target is a specific target type, outputting the target type of the detected target through L ED lamp display, voice broadcast and vibration modes, specifically, controlling an alarm device to display an alarm through a L ED lamp or display an alarm through a number or broadcast an alarm through voice or alarm through vibration according to the fact that the detected target is the specific target type.

In some embodiments, the radar is a millimeter wave radar.

The target identification method provided by the embodiment of the application sets the target detection to quit the delayed judgment, effectively solves the abnormal result generated by the interference on detection, effectively improves the accuracy of target identification, and is further favorable for improving the safety and stability in the automatic driving/auxiliary driving process.

In one embodiment, the description will be given taking an example in which the detection target is determined to be a pedestrian target.

Fig. 8A illustrates a doppler-range plane information provided by an embodiment of the present application, see fig. 8A. Wherein, every time one frame of data is obtained, one frame of Doppler-distance unit plane image is correspondingly obtained, and the deeper the color is, the higher the Doppler energy representing the Doppler unit is; the lighter the color, the lower the doppler energy characterizing the doppler cell. The pedestrian target has an expansion characteristic in doppler due to the swinging motion of the arms and legs when walking, and therefore a plurality of doppler cells are present around the target. Whereas the doppler power of a plurality of doppler cells present around a pedestrian target is low. The determination as to whether the detection target is a pedestrian target may be made according to the above-described features.

FIG. 8B shows an algorithm implementation of a specific embodiment of the present application. As shown in fig. 8B, the specific algorithm implementation steps are as follows:

(1) and training the scattering intensity threshold range of the pedestrian target.

And acquiring the scattering intensity of the pedestrian target at different distances by utilizing a plurality of external field tests, averaging the scattering intensity, and further acquiring a scattering intensity threshold lookup table. And from a plurality of measurements an energy fluctuation range is obtained, e.g. + -. Pa, where Pa is constant. And selecting a scattering intensity threshold according to the distance of the detection target, and if the scattering intensity of the detection target is within the range of +/-P _ a of a set threshold, meeting the scattering intensity condition of the pedestrian target.

(2) A speed threshold range is set for the pedestrian target.

The speed of the pedestrian target is set to be not more than 10m/s, and the speed range is adjustable. If the speed of the detected object exceeds the speed range, the object is not considered to be a pedestrian object.

(3) Doppler energy threshold range training for pedestrian targets

And selecting the most appropriate Doppler energy threshold value through multiple times of training, and determining the Doppler energy threshold value range according to the noise signal intensity of the radar system. Specifically, the average doppler energy of the non-target is counted, for example, the result is P _ n, and a doppler energy threshold + P _ n is selected as a range of the doppler energy threshold, where P _ n is a constant.

(4) And carrying out Doppler unit number threshold training on the pedestrian target.

And (3) when the corresponding strength of the Doppler units around the detected target meets the Doppler energy threshold range set in the step (3), adding 1 to the count, and when the count exceeds the Doppler unit number threshold, meeting the Doppler characteristic of the pedestrian target, namely meeting the Doppler judgment condition. The Doppler unit number threshold is obtained by taking the average value of a plurality of pedestrian targets.

(5) And carrying out pedestrian probability calculation on the detection target.

The radar detects the detection target once, acquires detection data once, and determines the probability that the primary target is a pedestrian. That is, one frame of detection data is acquired every detection, and the reliability that the object is a pedestrian is determined once.

If the detected target simultaneously meets the threshold range of the scattering intensity of the pedestrian, the threshold range of the speed of the pedestrian and the Doppler judgment condition for the single frame data, the probability Prob _ i of the detected target is increased by the probability Probl; if the target does not meet the strength judgment, subtracting the probability Prob2 from the pedestrian probability Prob _ i; and if the target does not meet the speed judgment, subtracting the probability Prob3 from the pedestrian probability Prob _ i, wherein Prob1, Prob2 and Prob3 are constants and are obtained according to a plurality of pedestrian target training.

(6) Setting pedestrian detection probability threshold

a) Whether the detected target is a pedestrian target or not is determined through single-frame data, and a large amount of misjudgments can occur due to the fact that interference can be caused in the detection process. Therefore, the current reliability of the detection target is determined through multi-frame accumulation joint judgment, namely, through detecting the same detection target for multiple times and according to the current detection result of the detection target and the last reliability of the detection target; and determining whether the detection target is a pedestrian target or not according to the current credibility. And within the set frame number range, when the current credibility of the detected target is greater than a first preset credibility threshold, judging the target as a pedestrian target. And if the frame number reaches the set frame number, judging the target as a non-pedestrian target when the current credibility of the detected target still does not reach the first preset credibility threshold.

b) In order to avoid the shaking phenomenon of the pedestrian detection result, the current frame is used for judging that the detection target is the pedestrian target, the next frame is used for judging that the detection target is the non-pedestrian target, and then the detection target is detected as the pedestrian target. The invention sets the pedestrian detection exit delay judgment, updates the first preset credibility to a smaller value after the current frame judges that the detection target is the pedestrian target, and continues to judge the next frame. In the subsequent processes of detecting the detection target, acquiring detection data and determining the current reliability, once the current reliability of the detection target is determined to be smaller than the updated first preset reliability within the limited detection times, such as within the second preset detection times, the detection target is determined to be a non-pedestrian target; and if the credibility of the detection target is determined to be greater than or equal to the updated first preset credibility each time within the second preset detection times, determining the detection target as the pedestrian target.

And when the current credibility of the detection target determined in the next frame is lower than the set credibility threshold, the pedestrian detection state is changed into the non-pedestrian detection state. The threshold setting value is smaller than the threshold in a), i.e. the first predetermined confidence level is updated to a smaller value.

This specific embodiment shows that it is determined whether or not the detection target is a pedestrian target. It should be understood that, for the detected target with micro-doppler characteristic, the method is applicable to the determination of the target type of the detected target by the technical solution described in this embodiment. For example, it can be determined whether the detected target is a drone according to the micro doppler characteristic when the propeller of the drone moves.

On the basis of the embodiments shown in fig. 2 to fig. 5, an embodiment of the present application provides a target reliability determination system, and fig. 9 is a schematic structural diagram of the target reliability determination system provided in the embodiment of the present application. As shown in fig. 9, target confidence determination system 90 includes: a processor 901. Optionally, the processor 901 is one or more, and works together or separately, and the processor 901 is configured to execute the technical solution of the embodiment of the target reliability determination method.

Optionally, the target reliability determination system 90 further includes: memory 902, radar 903. The memory is used for storing program codes;

the processor 901, which invokes the program code, when executed, is configured to:

Optionally, the radar 903 is provided separately from the processor 901. Optionally, the radar 903 comprises a processor 901.

The target reliability determining system provided in this embodiment can execute the technical solution of the above-mentioned embodiment of the target reliability determining method, and the execution manner and the beneficial effect are similar, and are not described herein again.

On the basis of the embodiments shown in fig. 6 to 7, an embodiment of the present application provides a target recognition system, fig. 10 is a schematic structural diagram of the target recognition system provided in the embodiment of the present application, and as shown in fig. 10, the target recognition system 100 includes: the object recognition system 100 includes: a processor 1001. Optionally, the processor 1001 is one or more, and works together or separately, and the processor is configured to execute the technical solution of the embodiment of the object recognition method.

Optionally, the target recognition system 100 further includes: memory 1002 and radar 1003. The memory 1002 is used for storing program codes;

the processor 1001, which invokes the program code, when the program code is executed, is configured to perform the following operations:

detecting the same detection target for multiple times;

Optionally, the radar 1003 is provided separately from the processor 1001. Optionally, the radar 1003 comprises a processor 1001.

The object recognition system provided in this embodiment can execute the technical solution of the embodiment of the object recognition system method, and the execution manner and the beneficial effect are similar, and are not described herein again.

On the basis of the above embodiments, the present application provides a radar. Fig. 11 is a schematic structural diagram of a radar according to an embodiment of the present application, and as shown in fig. 11, a radar 110 includes: an antenna 1101, and a processor 1102.

An antenna 1101 for acquiring an echo signal;

a processor 1102, communicatively connected to the antenna, is configured to execute the technical solution of the above-mentioned embodiment of the target reliability determining method, and/or is configured to execute the technical solution of the embodiment of the target identifying method.

On the basis of the embodiment shown in fig. 9, an embodiment of the present application provides a movable platform, and fig. 12 is a movable platform 120 provided in an embodiment of the present application, as shown in fig. 12, the movable platform 120 includes: the machine body 1201, the power system 1202 and the technical scheme target reliability determination system 90.

Wherein, the movable platform 120 may be any one of the following: the robot, unmanned vehicles, ordinary vehicles, VR glasses, AR glasses.

The movable platform of the embodiment shown in fig. 12 may be used to implement the technical solution of the above-mentioned target reliability determination method embodiment, and the implementation principle and technical effect are similar, which are not described herein again.

On the basis of the embodiment shown in fig. 10, an embodiment of the present application provides a movable platform, and fig. 13 is a movable platform 130 provided in an embodiment of the present application, as shown in fig. 13, the movable platform 130 includes: fuselage 1301, driving system 1302 and technical scheme object recognition system 100 above.

The movable platform 130 may be any of: the robot, unmanned vehicles, ordinary vehicles, VR glasses, AR glasses.

The movable platform of the embodiment shown in fig. 13 may be used to implement the technical solution of the above-mentioned target identification method embodiment, and the implementation principle and technical effect are similar, which are not described herein again.

In addition, the present embodiment also provides a computer-readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the object reliability determination method and/or the object identification method described in the above embodiments.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, system, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

It is obvious to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining the reliability of a target is applied to radar, and is characterized by comprising the following steps:

2. The method of claim 1, wherein the detection information of the detection target comprises at least one of: distance, scattering intensity, velocity information.

3. The method according to claim 1, wherein the confidence level is increased by a first preset value when the detection information of the detection target satisfies a preset condition and the information of doppler cells around the detection target satisfies a preset doppler cell condition; otherwise, subtracting a second preset value from the reliability.

4. The method of claim 3, wherein the detection information of the detection target includes scattering intensity and velocity information,

and when the speed information is within a preset speed threshold range and the scattering intensity is within a preset scattering intensity threshold range, determining that the detection information of the detection target meets a preset condition.

5. The method of claim 3, wherein the detection information of the detection target includes a scattering intensity,

and when the scattering intensity is within a preset scattering intensity threshold value range, determining that the detection information of the detection target meets a preset condition.

6. The method according to claim 3, wherein the detection information of the detection target includes speed information,

and when the speed information is within a preset speed threshold value range, determining that the detection information of the detection target meets a preset condition.

7. The method according to claim 4 or 5, wherein before the obtaining the detection information of the detection target, the method further comprises:

acquiring the scattering intensity of an external target at different distances;

determining the scattering intensity threshold range according to the scattering intensities of the external targets at the different distances.

8. The method of claim 1,

and when the detection information of the detection target meets a first preset condition, acquiring the information of Doppler units around the detection target.

9. The method according to claim 8, comprising in particular:

the detection information comprises distance and scattering intensity, and if the scattering intensity is within a preset scattering intensity threshold range, and/or the detection information comprises speed information, and if the speed information is within a preset speed threshold range, the detection information of the detection target meets a first preset condition; otherwise, the detection information of the detection target does not meet the first preset condition.

10. The method of claim 1,

and acquiring information of Doppler units around the detection target at the same time of acquiring detection information of the detection target.

11. The method of claim 1, comprising:

the information of the Doppler units around the detected target comprises the Doppler energy of each Doppler unit around the detected target and the number of the Doppler units with the scattering intensity within a preset scattering intensity threshold range;

and determining the reliability according to the number of the Doppler units with the scattering intensity within a preset scattering intensity threshold range.

12. The method of claim 11, comprising:

acquiring the number of the Doppler units with the scattering intensity within a preset scattering intensity threshold range;

and determining whether the number of the Doppler units is within a preset Doppler unit number range or not according to the number of the Doppler units, and determining the reliability.

13. The method of claim 12, comprising:

acquiring Doppler energy of each Doppler unit around the detection target;

and determining the number of the Doppler units with the scattering intensity within a preset scattering intensity threshold range according to the Doppler energy of each Doppler unit.

14. The method of claim 11, comprising:

if the number of the Doppler units is within a preset Doppler unit number range, increasing a third preset value to the reliability; and/or the presence of a gas in the gas,

and if the number of the Doppler units is not within the range of the preset Doppler unit number, subtracting a fourth preset value from the reliability.

15. The method of claim 1, further comprising:

acquiring the distance information;

judging whether the distance information is smaller than a preset distance or not according to the distance information;

and if the distance information is smaller than the preset distance, controlling the movable platform to execute obstacle avoidance operation, and/or controlling an alarm device to perform alarm processing.

16. The method of claim 1, wherein the step of removing the metal oxide layer comprises removing the metal oxide layer from the metal oxide layer

And acquiring the detection information of the detection target through a radar.

17. The method of claim 16, wherein the radar is a millimeter wave radar.

18. The method according to claim 1, wherein detection information of the detection target is acquired by acquiring an echo signal.

19. A method of object recognition, comprising:

detecting the same detection target for multiple times;

20. The method of claim 19, wherein each pair of the same detection targets is detected once, and the detection result of the same detection target is obtained once.

21. The method of claim 19,

if the current detection result meets a second preset condition, the current credibility is the last credibility increased by a first preset value; otherwise, the current reliability is the last reliability minus a second preset value.

22. The method according to claim 21, wherein the detection result of the detected object includes detection information of the detected object and information of doppler cells around the detected object;

the second preset condition includes: and the detection information of the detection target at the current moment meets a preset detection information condition and the information of Doppler units around the detection target meets a preset Doppler condition.

23. The method of claim 19, comprising:

and determining the type of the detection target according to the frequency of detecting the same detection target and the current reliability.

24. The method according to claim 23, wherein when the number of times of probing the same target is less than a first predetermined number of times of probing, the current reliability of the target determined by probing the same target each time is compared with a first predetermined reliability;

if the current reliability of the detection target determined by detecting the same detection target each time is less than the first preset reliability, determining that the detection target is not the specific target type; and/or the presence of a gas in the gas,

determining that the detection target is the specific target type once the current credibility is greater than or equal to the first preset credibility.

25. The method according to claim 23, wherein when the number of probing the same target is less than the first predetermined number of probing, and the current confidence level is greater than the first predetermined confidence level, the first predetermined confidence level is updated to a fifth predetermined value.

26. The method according to claim 25, wherein when the number of probing the same target is less than the first predetermined number of probing times and the current reliability is greater than the first predetermined reliability, continuing probing the target, wherein the target type of the target is determined before continuing probing for a second predetermined number of probing times;

if the current reliability of the detection target determined by detecting the same detection target each time is greater than or equal to a first preset reliability, determining that the detection target is the specific target type; and/or the presence of a gas in the gas,

and determining that the detection target is not the specific target type if the current credibility of the detection target for detecting the same detection target is less than a first preset credibility.

27. The method of claim 19, wherein when it is determined that the detected object is a specific object type, an alarm device is controlled to perform an alarm process

28. The method of claim 19, further comprising:

and after the detection target is determined to be a specific target type, outputting the target type of the detection target through L ED lamp display, voice broadcast and vibration modes.

29. The method of claim 19, wherein the same target is detected multiple times by radar.

30. The method of claim 19, wherein the radar is a millimeter wave radar.

31. The method of claim 19, wherein the current detection result of the target is obtained according to an echo signal.

32. An object credibility determination system, comprising: one or more processors, working collectively or individually, the processors being configured to perform the method of any of claims 1-15.

33. The system according to claim 32, wherein the detection information of the detection target is acquired by radar.

34. The system of claim 32, wherein the radar is a millimeter wave radar.

35. The system according to claim 32, wherein detection information of the detection target is acquired by acquiring the echo signal.

36. An object recognition system, comprising: one or more processors, working collectively or individually, the processors being configured to perform the method of any one of claims 19 to 27.

37. The system of claim 36, wherein the same target is detected multiple times by radar.

38. The system of claim 36, wherein the radar is a millimeter wave radar.

39. The system according to claim 36, wherein detection information of the detection target is acquired by acquiring the echo signal.

40. A radar, comprising:

the antenna is used for acquiring echo signals;

a processor, communicatively connected to the antenna, for performing the method of any of claims 1 to 15 and/or for performing the method of any of claims 19 to 28.

41. The radar of claim 40, wherein the radar is a millimeter wave radar.

42. The radar according to claim 40, wherein detection information of the detection target is acquired by acquiring the echo signal.

43. A movable platform, comprising:

a body;

the power system is arranged on the vehicle body and used for providing power;

and a radar as claimed in any one of claims 40 to 42.

44. The movable platform of claim 43, comprising at least one of: automobiles, unmanned aerial vehicles.

45. A computer-readable storage medium, having stored thereon a computer program for execution by a processor to perform the method of any one of claims 1-18.

46. A computer-readable storage medium, having stored thereon a computer program for execution by a processor to perform the method of any one of claims 19-31.