CN110618420A

CN110618420A - Ultrasonic data processing method and system, vehicle and storage medium

Info

Publication number: CN110618420A
Application number: CN201910976614.6A
Authority: CN
Inventors: 邓志权; 张博; 蒋少峰; 欧阳湛
Original assignee: Guangzhou Xiaopeng Motors Technology Co Ltd
Current assignee: Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority date: 2019-10-15
Filing date: 2019-10-15
Publication date: 2019-12-27

Abstract

A method, a system, a vehicle and a storage medium for processing ultrasonic data are provided, the method comprises: acquiring a reflection point position when ultrasonic waves emitted by an ultrasonic sensor are reflected by an obstacle as a data point collected by the ultrasonic sensor; segmenting the data points according to the distance between the vehicle and the obstacle corresponding to the data points to obtain a plurality of data point sets; the variation of the distance between the vehicle and the obstacle corresponding to the data points in the same data point set does not exceed a preset first threshold; determining an obstacle corresponding to the set of data points from the data points within the set of data points. By implementing the embodiment of the invention, data points belonging to different obstacles can be segmented from the acquired ultrasonic data.

Description

Ultrasonic data processing method and system, vehicle and storage medium

Technical Field

The invention relates to the technical field of ultrasonic data processing, in particular to a method and a system for processing ultrasonic data, a vehicle and a storage medium.

Background

Ultrasonic sensors are one of the sensors commonly used for autopilot. Based on the ultrasonic data acquired by the ultrasonic sensor, the vehicle can detect the distance between the surrounding obstacle and the vehicle.

However, when a plurality of obstacles exist around the vehicle, it is difficult for the vehicle to distinguish different obstacles from the ultrasonic data. That is, it is difficult to distinguish which ultrasonic data are reflected by the same obstacle and which ultrasonic data are reflected by different obstacles. This is not favorable for the vehicle to recognize different obstacles from the ultrasonic data, and is also unfavorable for the vehicle to perform different obstacle avoidance operations for different obstacles.

Disclosure of Invention

The embodiment of the invention discloses a method and a system for processing ultrasonic data, a vehicle and a storage medium, which can be used for separating data points belonging to different obstacles from the acquired ultrasonic data.

The first aspect of the embodiments of the present invention discloses a method for processing ultrasonic data, where the method includes:

acquiring a reflection point position when ultrasonic waves emitted by an ultrasonic sensor are reflected by an obstacle as a data point collected by the ultrasonic sensor;

dividing a plurality of data points according to the distance between the vehicle and the obstacle corresponding to the data points to obtain a plurality of data point sets; the variation of the distance between the vehicle and the obstacle corresponding to the data points in the same data point set does not exceed a preset first threshold;

determining an obstacle corresponding to the set of data points from the data points within the set of data points.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, the segmenting the data points according to the distances between the vehicle and the obstacle corresponding to the data points to obtain data point sets includes:

identifying the variation of the distance between the vehicle and the obstacle corresponding to two adjacent data points;

and if the variation exceeds a preset first threshold, dividing the two adjacent data points to divide the two adjacent data points into different data point sets.

As an optional implementation manner, in the first aspect of this embodiment of the present invention, the method further includes:

fitting a line corresponding to the data point set by using the data points in the data point set to obtain a plurality of lines;

identifying a hopping edge from the plurality of lines and identifying a non-hopping edge of the plurality of lines other than the hopping edge; the jumping edge is formed by data points of which the variation between the corresponding distances is in an ascending trend or in a descending trend;

calculating a projection distance of the jump edge in a direction perpendicular to a driving direction of the vehicle;

judging whether the projection distance is larger than a preset second threshold value or not;

and if the data point is smaller than or equal to the second threshold value, fusing the data point forming the hopping edge and the data point forming the non-hopping edge connected with the hopping edge into the same data point set.

if the projection distance is greater than the second threshold, the data points that form the transition edge and the data points that form the non-transition edge that is connected to the transition edge are divided into different sets of data points.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, before the fitting a line corresponding to the data point set by using the data points in the data point set to obtain a plurality of lines, the method further includes:

identifying noise points of the corresponding distance jumps in the data point set;

filtering the noise points from the data point set to obtain the data point set subjected to noise removal;

and fitting a line corresponding to the data point set by using the data points in the data point set to obtain a plurality of lines, including:

and fitting a line corresponding to the data point set by using the data points in the denoised data point set to obtain a plurality of lines.

As an alternative implementation, in the first aspect of the embodiment of the present invention, the first threshold is set with reference to a length or a width of the vehicle.

As an optional implementation manner, in the first aspect of the embodiment of the present invention, before the dividing a number of the data points according to the distance between the vehicle and the obstacle corresponding to the data points to obtain a number of data point sets, the method further includes:

acquiring the current location of the vehicle;

and inquiring a segmentation threshold bound with the current position of the vehicle as the first threshold.

A second aspect of the embodiments of the present invention discloses a system for processing ultrasonic data, including:

the acquisition unit is used for acquiring the position of a reflecting point when the ultrasonic wave emitted by the ultrasonic sensor is reflected by an obstacle as a data point acquired by the ultrasonic sensor;

the segmentation unit is used for segmenting the data points according to the distance between the vehicle and the obstacle corresponding to the data points to obtain a plurality of data point sets; the variation of the distance between the vehicle and the obstacle corresponding to the data points in the same data point set does not exceed a preset first threshold;

a determination unit for determining an obstacle corresponding to the set of data points from the data points within the set of data points.

As an optional implementation manner, in a second aspect of the embodiment of the present invention, the dividing unit includes:

the identification subunit is used for identifying the variation of the distance between the vehicle and the obstacle corresponding to the two adjacent data points;

and the first segmentation subunit is configured to segment the two adjacent data points to divide the two adjacent data points into different data point sets when the identification subunit identifies that the variation exceeds a preset first threshold.

As an optional implementation manner, in a second aspect of the embodiment of the present invention, the dividing unit further includes:

the fitting subunit is configured to fit lines corresponding to the data point sets by using the data points in the data point sets to obtain a plurality of lines;

the identification subunit is further configured to identify a hopping edge from the plurality of lines and identify a non-hopping edge of the plurality of lines other than the hopping edge; the jumping edge is formed by data points with the upward trend or the downward trend of the variation between the corresponding distances;

the calculating subunit is used for calculating the projection distance of the jump edge in the direction perpendicular to the driving direction of the vehicle;

the judging subunit is used for judging whether the projection distance is greater than a preset second threshold value;

and a fusion subunit, configured to fuse, when the judgment subunit judges that the projection distance is smaller than or equal to the second threshold, the data point forming the transition edge and the data point forming the non-transition edge connected to the transition edge into the same data point set.

and a second dividing subunit, configured to divide the data points forming the transition edge and the non-transition edge connected to the transition edge into different data point sets when the judging subunit judges that the projection distance is greater than the second threshold.

a denoising subunit, configured to identify a noise point of the distance jump corresponding to the data point set before the fitting subunit fits a line corresponding to the data point set by using the data points in the data point set to obtain a plurality of lines; filtering the noise point from the data point set to obtain the data point set subjected to noise removal;

and the fitting subunit is specifically configured to fit a line corresponding to the data point set by using the data points in the denoised data point set to obtain a plurality of lines.

A third aspect of embodiments of the present invention discloses a vehicle comprising any of the systems disclosed in the second aspect of embodiments of the present invention.

A fourth aspect of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute any one of the methods disclosed in the first aspect of the embodiments of the present invention.

A fifth aspect of the embodiments of the present invention discloses a computer program product, which, when running on a computer, causes the computer to execute any one of the methods disclosed in the first aspect of the embodiments of the present invention.

Compared with the prior art, the embodiment of the invention has the following beneficial effects:

based on the distance between the vehicle and the obstacle measured by the ultrasonic sensor, the position of the reflection point when the ultrasonic sensor is reflected by the obstacle can be acquired as the data point acquired by the ultrasonic sensor. In practice, it has been found that the edges of the same obstacle have a certain regularity and generally do not have excessive undulations. Therefore, if the distances between the vehicle and the obstacle corresponding to the plurality of data points are close (i.e., the distances do not change by more than the first threshold), the probability that the data points belong to the same obstacle is relatively high. Therefore, the data points can be segmented by utilizing the distance between the vehicle and the obstacle corresponding to the data points acquired by the ultrasonic sensor, and the data points belonging to the same obstacle are divided into the same point set, so that the data points belonging to different obstacles can be segmented.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed 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 that other drawings can be obtained according to these drawings without creative efforts.

FIG. 1 is a schematic flow chart of a method for processing ultrasonic data according to an embodiment of the present invention;

FIG. 2 is an exemplary diagram of data points collected by an ultrasonic sensor of a vehicle according to an embodiment of the present disclosure;

FIG. 3 is a schematic flow chart illustrating another method for processing ultrasound data according to an embodiment of the present disclosure;

FIG. 4-1 is an exemplary diagram of a data point segmentation disclosed in an embodiment of the present invention;

FIG. 4-2 is another exemplary graph of data point segmentation disclosed in embodiments of the present invention;

FIG. 5-1 is an exemplary graph of a line fitted based on the segmentation results of FIG. 4-1 in a vehicle coordinate system, according to embodiments of the present disclosure;

FIG. 5-2 is an exemplary graph of a line fitted based on the segmentation results of FIG. 4-2 in a vehicle coordinate system, according to an embodiment of the present disclosure;

FIG. 6-1 is a diagram illustrating an example of a modification of the segmentation result of FIG. 4-1 according to an embodiment of the present disclosure;

FIG. 6-2 is an exemplary diagram of a modified segmentation result of FIG. 4-2 according to an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of an ultrasound data processing system according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of another ultrasonic data processing system disclosed in the embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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.

It is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

The embodiment of the invention discloses a segmentation processing method and system for ultrasonic data, a vehicle and a storage medium, which can segment data points belonging to different obstacles from the acquired ultrasonic data. The following are detailed below.

Example one

Referring to fig. 1, fig. 1 is a schematic flow chart of a method for processing ultrasonic data according to an embodiment of the present invention. The data processing system applicable to the ultrasonic data processing method described in fig. 1 may be operated in a vehicle-mounted Electronic device or apparatus such as an Electronic Control Unit (ECU) and a vehicle-mounted computer of a vehicle, and is also applicable to a cloud server in communication connection with the vehicle, which is not limited in the embodiment of the present invention. As shown in fig. 1, the method for processing ultrasonic data may include the following steps:

101. the data processing system acquires the position of a reflecting point when the ultrasonic wave emitted by the ultrasonic sensor is reflected by the obstacle as a data point collected by the ultrasonic sensor.

In the embodiment of the present invention, the ultrasonic sensor may emit ultrasonic waves at a certain period and receive echoes of the ultrasonic waves reflected by the obstacle. Based on the time difference between the echoes of the transmitted ultrasonic wave and the received ultrasonic wave in one cycle and the propagation speed of the ultrasonic wave, the distance between the reflection point reflecting the ultrasonic wave and the ultrasonic sensor can be calculated.

The ultrasonic sensor may be mounted on the vehicle, and the distance between the reflection point and the ultrasonic sensor may be approximately regarded as the distance between the reflection point and the vehicle. The position of the vehicle can be measured by a odometer of the vehicle at the moment when the ultrasonic sensor transmits the ultrasonic wave, and the position of the reflection point of the reflected ultrasonic wave can be calculated by combining the distance between the reflection point and the ultrasonic sensor. Further, if the installation position of the ultrasonic sensor on the vehicle is known, the distance between the reflection point and the ultrasonic sensor can be converted into the distance between the reflection point and the vehicle, so that the more accurate position of the reflection point can be calculated.

As the vehicle moves, multiple ultrasonic waves emitted by the ultrasonic sensor may be reflected at different positions on the same obstacle or emitted at different obstacles, so that the ultrasonic sensor may measure the positions of multiple reflection points, i.e., acquire multiple data points.

102. And the data processing system divides the data points according to the distances between the vehicle and the obstacle corresponding to the data points to obtain a plurality of data point sets.

In the embodiment of the present invention, the distance between the vehicle and the obstacle corresponding to the data point acquired by the ultrasonic sensor is a distance between a position where the vehicle is located and a position of a reflection point at which the ultrasonic wave is reflected at the time when the data point is acquired.

For convenience of description, data points acquired by the ultrasonic sensor during the driving process of the vehicle can be unified to a vehicle coordinate system for representation. The x-axis of the vehicle coordinate system is parallel to the ground and points to the driving direction of the vehicle, the y-axis is parallel to the ground and perpendicular to the x-axis, and the z-axis is perpendicular to the plane formed by the x-axis and the y-axis. If the collected data points are unified to a vehicle coordinate system for representation, when the data processing system segments a plurality of data points according to the distance between the vehicle and the obstacle corresponding to the data points, the data processing system can segment the plurality of data points according to the projection of the distance between the vehicle and the obstacle corresponding to the data points (hereinafter referred to as the distance corresponding to the data points) on the x-axis.

Referring to fig. 2, fig. 2 is a diagram illustrating an example of data points collected by an ultrasonic sensor of a vehicle according to an embodiment of the disclosure. As shown in fig. 2, the host vehicle 10 travels in the direction indicated by the arrow in fig. 2, and the host vehicle 10 is provided with an ultrasonic sensor 11. The data points 30 collected by the ultrasonic sensor 11 during the travel of the host vehicle 10 are the reflection points located on the wall 40 and the reflection points located on the vehicle 20, respectively.

As can be seen from fig. 2, the distance between the data point 30 belonging to the wall 40 and the host vehicle 10 does not vary much, while the distance between the data point 30 belonging to the wall 40 and the host vehicle 10 varies much more than the distance between the data point 30 belonging to the vehicle 20 and the host vehicle 10. Thus, a data point 30 belonging to the wall 40, which is located below in fig. 2, can be separated from a data point 30 belonging to the vehicle 20 by a dividing line 31, and a data point 30 belonging to the wall 40, which is located above in fig. 2, can be separated from a data point 30 belonging to the vehicle 20 by a dividing line 32.

That is, the plurality of data points 30 shown in fig. 2 may be divided into three data point sets, the data points 30 located below fig. 2 and belonging to the wall 40 are divided into a first data point set, the data points 30 belonging to the vehicle 20 are divided into a second data point set, and the data points 30 located above fig. 2 and belonging to the wall 40 are divided into a third data point set.

Specifically, the specific implementation of the data processing system executing step 102 may be: the data processing system clusters a plurality of collected data points, and each group obtained after clustering is regarded as a data point set; the criterion of clustering end may be that the variation of the distances corresponding to the data points in each group does not exceed a first threshold.

Alternatively, the specific implementation of the data processing system executing step 102 may also be:

the data processing system judges whether the two data points adjacent to the position need to be divided according to the variation of the distance between the vehicle and the obstacle corresponding to the two data points adjacent to the position respectively. If the variation of the distance corresponding to two adjacent data points exceeds a first threshold, the two adjacent data points are segmented; otherwise, no segmentation is performed.

In the embodiment of the present invention, the first threshold may be set with reference to a width or a length of a vehicle body. For example, it may be set with reference to the width or length of the vehicle body. In the automatic parking scene, it is necessary to identify a parking available area into which the vehicle can park. Taking fig. 2 as an example, for a certain parking available area, it is assumed that the side parallel to the vehicle driving direction in fig. 2 is the width of the parking available area, and the side perpendicular to the vehicle driving direction in fig. 2 is the length of the parking available area. In a parallel parking scene, the length of the parking available area is not less than the width of the vehicle body; in the vertical parking scenario, the length of the parking available area should be no less than the length of the vehicle body. It can be understood that, while the ultrasonic data points are divided into different data point sets, the area scanned by the ultrasonic sensor is also divided into different sub-areas, that is, one data point set may correspond to one sub-area, and the data points in the data point set may form the outline of the sub-area. It can be seen that setting the first threshold value with reference to the width or length of the vehicle body can distinguish data points belonging to different obstacles, and meanwhile, there may be stoppable areas in the divided sub-areas. And further judging the width of the sub-region on the basis of dividing the sub-region to determine the stoppable region.

Alternatively, the current location of the vehicle may be acquired. Specifically, the current positioning position of the vehicle can be obtained, and the current location of the vehicle is determined according to the positioning position; alternatively, the current location of the Vehicle is also obtained based on Vehicle-to-Vehicle communication (V2V). In the embodiment of the present invention, different locations may be bound to corresponding segmentation thresholds in advance, and after the location where the vehicle is currently located is determined, the segmentation threshold bound to the location where the vehicle is currently located may be queried as the first threshold, and the first threshold is used as a standard for data point segmentation. That is, the first threshold may also be set with reference to a division threshold bound to a place where the vehicle is currently located.

For example, if the current location of the vehicle is a parking lot, the partition threshold value bound with the parking lot can be set by referring to the length of the parking space partitioned in the parking lot, so that ultrasonic data points can be partitioned for the parking space, the parking space and a non-parking space can be identified according to the data points, and for obstacles in the non-parking space, further partitioning is not needed, namely, the data points corresponding to the obstacles belonging to the non-parking space can be partitioned into the same data point set, and the data volume to be processed when the parking space is identified can be reduced;

if the current location of the vehicle is an expressway, the segmentation threshold value bound with the expressway can be set by referring to the lane width. It can be understood that if the variation of the distance between two adjacent data points exceeds the lane width, the obstacle corresponding to one data point may be located on the adjacent lane, and the obstacle corresponding to the other data point may not be located on the adjacent lane, and the two adjacent data points should belong to two different obstacles, so that the two data points can be accurately distinguished.

Further optionally, the binding relationship between different locations and the corresponding segmentation threshold may be pre-stored in the vehicle local, or may be stored in the cloud server or the field server of the current location of the vehicle, which is not limited in the embodiment of the present invention.

It should be noted that the segmentation using clustering and the segmentation directly using a threshold may result in different segmentation results. For example, if the data points 30 shown in fig. 2 are segmented by clustering, the data points 30 belonging to the wall 40 may be all divided into a data point set; if the threshold value is directly used for the segmentation, among the data points 30 belonging to the wall 40, the data points 30 above the segmentation line 32 may be segmented into one data point set, and the data points 30 below the segmentation line 31 may be segmented into another data point set. Both segmentation methods can segment data points 30 belonging to the wall 40 from data points 30 belonging to the vehicle 20, so that data points belonging to different obstacles can be segmented.

103. The data processing system determines an obstruction corresponding to the set of data points from the data points within the set of data points.

In the embodiment of the invention, after the data points belonging to different obstacles are divided into different data point sets, the data points in the data point sets can be identified in a characteristic matching mode or by a pre-trained classifier, so that the specific type of the obstacle corresponding to the data point set can be identified.

In summary, in the method described in fig. 1, based on the distance between the vehicle and the obstacle measured by the ultrasonic sensor, the position of the reflection point when the ultrasonic sensor is reflected by the obstacle can be obtained as the data point acquired by the ultrasonic sensor, so that the data point can be segmented by using the distance between the vehicle and the obstacle corresponding to the data point acquired by the ultrasonic sensor, the data points belonging to the same obstacle are divided into the same data point set, and the data points belonging to different obstacles can be segmented. Further, the first threshold value can be set by referring to the width or the length of the vehicle body, so that ultrasonic data points belonging to different obstacles can be effectively distinguished, and a stoppable area can be conveniently identified.

Example two

Referring to fig. 3, fig. 3 is a schematic flow chart of another ultrasonic data processing method according to an embodiment of the present invention. As shown in fig. 3, the method for processing ultrasonic data may include the steps of:

301. the data processing system acquires the position of a reflecting point when the ultrasonic wave emitted by the ultrasonic sensor is reflected by the obstacle as a data point collected by the ultrasonic sensor.

302. The data processing system identifies the variation of the distance between the vehicle and the obstacle corresponding to the two data points adjacent to each other in position, and judges whether the variation of the distance corresponding to the two adjacent data points exceeds a first threshold value or not; if yes, go to step 303; if not, step 304 is performed.

303. The data processing system segments two adjacent data points to divide the two adjacent data points into different sets of data points.

304. The data processing system divides two adjacent data points into the same data point set.

In the embodiment of the present invention, steps 302 to 304 may be regarded as a process of roughly dividing the data point, and the data point is primarily divided into a plurality of data point sets with the first threshold as a reference. It can be seen that the result of the coarse segmentation depends on the value of the first threshold, which is set to a different value, which may result in a different coarse segmentation result.

Referring also to fig. 4, in addition to the wall 40 and the vehicle 20, fig. 4 shows another barrier 50. Fig. 4-1 is an exemplary diagram of segmenting data points according to an embodiment of the present invention. If the first threshold is set to a smaller value, the segmentation result may be as shown in FIG. 4-1. As can be seen from fig. 4-1, when the first threshold is small, the data points 30 belonging to the wall 40, the vehicle 20 and the obstacle 50 can be well segmented.

However, due to the certain beam angle of the ultrasound waves, redundant data points may be detected that are partially beyond the boundary of the object itself. For example, the data points 30 belonging to the vehicle 20, the data points 30 distributed on both sides of the head of the vehicle 20 may be considered as redundant data points. The distance to which these redundant data points correspond may not coincide with the distance to which other data points belonging to the vehicle 20 correspond, and if the first threshold is small, it is possible to segment these redundant data points into another set of data points. As shown in fig. 4-1, the division lines 34 and 33 may further divide the data points 30 belonging to the vehicle 20 into three data point sets.

Referring to fig. 4-2, fig. 4-2 is a diagram illustrating another example of dividing data points according to an embodiment of the present invention. If the first threshold is set to a larger value, the segmentation result may be as shown in fig. 4-2. As can be seen from fig. 4-2, but the first threshold is larger, the data points 30 belonging to the vehicle 20 are all divided into the same set of data points, but it is also possible to divide the division points 30 belonging to the obstacle 50 and to the wall 40 into the same set of data points.

Therefore, steps 306 to 309 described below can be performed to further improve the accuracy of the segmentation. Wherein, if there is noise in the data point set, step 305 may be performed before step 306 is performed.

305. And the data processing system identifies the noise points with the corresponding distance jump in the data point set and filters the noise points from the data point set to obtain the denoised data point set.

In the embodiment of the present invention, the distance corresponding to the noise point is significantly different from the distance corresponding to other data points in the data point set. For example, assuming that the first threshold is set to 1m, the distance between the vehicle and the obstacle corresponding to most data points in the data point set is in the range of 5.5m to 5.6m, and the distance between the vehicle and the obstacle corresponding to a certain data point is 6 m. Since the variation between the distance corresponding to the data point and the distances corresponding to other data points in the data point set is less than 1m, when the data point is divided based on the first threshold, it is reasonable to divide the data point corresponding to the distance of 6m into the data point set. However, after a certain number of data points are accumulated in the data point set, the data point distribution in the data point set also presents a certain degree of aggregation, at this time, the data point with the corresponding distance of 6m is obviously different from other data points with the corresponding distance in the range of 5.5m to 5.6m, and a distance jump phenomenon exists, so that the data point with the corresponding distance of 6m can be identified as a noise point, the noise point is filtered out from the data point set, the distance corresponding to the data point in the data point set is more concentrated, and the accuracy of the next fitting is improved.

306. And the data processing system fits a line corresponding to the data point set by using the data points in the denoised data point set to obtain a plurality of lines.

It is understood that the denoising operation shown in step 305 may be performed first in order to improve the accuracy of the fitting. In other possible embodiments, after performing steps 302-304 to roughly divide the data points into several data point sets, step 305 may be directly performed to fit the data points in the data point sets.

Wherein the data points may be fitted to a line using a least squares method. The data points in one data point set may be synthesized inversely into one line or inversely into multiple lines, which is not limited in the embodiment of the present invention.

307. The data processing system identifies a transition edge from the plurality of lines and identifies a non-transition edge other than the transition edge from the plurality of lines.

In the embodiment of the present invention, the transition edge is formed by data points in which the variation between the corresponding distances is in an upward trend or in a downward trend. Optionally, the fitted lines may be converted into a vehicle coordinate system for representation, and if the gradient of a certain line is greater than a preset gradient threshold, the line is identified as a jump edge; otherwise, this line is identified as a non-hopping edge.

In the embodiment of the present invention, please refer to fig. 5. Fig. 5-1 is an exemplary diagram of a line fitted based on the segmentation result of fig. 4-1 in a vehicle coordinate system according to an embodiment of the present invention. Fig. 5-2 is an exemplary diagram of a line fitted based on the segmentation result of fig. 4-2 in a vehicle coordinate system according to an embodiment of the present invention. The dashed lines in fig. 5 represent the dividing lines, which are used to divide the different sets of data points.

308. The data processing system calculates a projected distance of the jump edge in a direction perpendicular to a driving direction of the vehicle.

In the embodiment of the invention, if the fitted lines are represented in the vehicle coordinate system, the projection distance of the jump edge in the direction perpendicular to the driving direction of the vehicle is the projection distance of the jump edge on the y axis.

With continued reference to FIG. 5, in FIG. 5-1, the transition edges are L1 and L2, and the remaining lines are non-transition edges. The projection distance of L1 on the y-axis is d1, and the projection distance of L2 on the y-axis is d 2. In fig. 5-2, the jumping edges are L1, L2, L3, and L4, the projection distances on the y-axis are d1, d2, d3, and d4 in this order, and the remaining lines in fig. 5-2 are non-jumping edges.

309. The data processing system judges whether the projection distance of the jumping edge is larger than a preset second threshold value or not; if yes, go to step 310; if not, step 311 is performed.

310. The data processing system partitions the data points that comprise the hopping edge and the data points that comprise the non-hopping edge that is connected to the hopping edge into different sets of data points and continues to step 312.

311. The data processing system merges the data points that make up the hopping edge and the data points that make up the non-hopping edge that is connected to the hopping edge into the same set of data points and continues to step 312.

In the embodiment of the present invention, the second threshold may be an empirical value, and is set with reference to the first threshold. If the value of the first threshold is smaller, the second threshold can be set to be larger than the first threshold; if the first threshold value is larger, the second threshold value may be set smaller than the first threshold value.

With continued reference to fig. 5-1, L1 and L2 are fit from redundant data points, and thus generally have smaller values for d1 and d 2. If d1, d2 are less than the second threshold, then step 311 is performed to fuse L1, L2 and the non-hopping edges connecting L1 and L2 into the same set of data points. After steps 309-311 are performed, the result of segmenting the data points in FIG. 5-1 can be as shown in FIG. 6-1.

In fig. 5-2, L3, L4 are actually the dividing lines between two different objects, and L3 and L4 are fitted because the data points 30 belonging to the obstacle 50 and to the wall 40 are divided into the same data point set in the rough division. Generally, the projection distance of the boundary between different objects on the y-axis is larger, so that d3 and d4 may be larger than the second threshold, step 310 is performed to segment L3 and the non-transition edge connected to L3, and segment L4 and the non-transition edge connected to L4. d1 and d2 may be less than the second threshold, and step 310 is performed to fuse L1, L2, and the non-hopping edges connecting L1 and L2. In fact, L1, L2 and the non-hopping edge connecting L1 and L2 are already divided into the same data point set during rough division, so step 310 may not be performed. After steps 309-311 are performed, the result of segmenting the data points in fig. 5-2 can be as shown in fig. 6-2.

312. The data processing system determines an obstruction corresponding to the set of data points from the data points within the set of data points.

It can be seen that in the method described in fig. 3, a plurality of data points can be roughly divided based on the distance between the vehicle and the obstacle corresponding to the data points, so that the data points belonging to different obstacles can be divided. Furthermore, by judging the projection distance of the jumping edge on the y axis, the segmentation result of the rough segmentation can be corrected, so that the segmentation accuracy is improved. Furthermore, before the jumping edge is identified and the projection distance on the y axis is calculated, the data points in the data point set need to be fitted into a line, and in order to improve the fitting accuracy, noise in the data point set can be filtered out first.

EXAMPLE III

Referring to fig. 7, fig. 7 is a schematic structural diagram of an ultrasound data processing system according to an embodiment of the present invention. As shown in fig. 7, the processing system of ultrasonic data may include:

an acquiring unit 701, configured to acquire a position of a reflection point when an ultrasonic wave emitted by an ultrasonic sensor is reflected by an obstacle as a data point acquired by the ultrasonic sensor;

in the embodiment of the present invention, the obtaining unit 701 may obtain the position of the vehicle measured by the odometer of the vehicle, and may calculate the position of the reflection point reflecting the ultrasonic wave by combining the distance between the reflection point and the ultrasonic sensor. Further, if the installation position of the ultrasonic sensor on the vehicle is known, the distance between the reflection point and the ultrasonic sensor can be converted into the distance between the reflection point and the vehicle, so that the more accurate position of the reflection point can be calculated.

A dividing unit 702, configured to divide a plurality of data points according to distances between the vehicle and the obstacle corresponding to the data points, so as to obtain a plurality of data point sets; the variation of the distance between the vehicle and the obstacle corresponding to the data points in the same data point set does not exceed a preset first threshold.

In this embodiment of the present invention, the dividing unit 702 is configured to divide the data points according to the distances between the vehicle and the obstacle corresponding to the data points, so as to obtain the data point sets, specifically, the manner of dividing the data point sets may be:

a segmentation unit 702, configured to cluster the collected multiple data points, and regard each group obtained after the clustering as a data point set; the criterion of clustering end may be that the variation of the distance corresponding to the data points in the data in each group does not exceed a first threshold;

or, the data processing device is configured to determine whether to segment the two data points adjacent to the position according to the variation of the distance between the vehicle and the obstacle corresponding to the two data points adjacent to the position. If the variation of the distance corresponding to two adjacent data points exceeds a first threshold, the two adjacent data points are segmented; otherwise, no segmentation is performed.

The first threshold value may be set with reference to the width or length of the vehicle body.

Alternatively, the segmentation threshold setting bound to the current location of the vehicle may also be referred to; that is, as an alternative embodiment, before the segmentation unit 702 segments the data points according to the distances between the vehicle and the obstacle corresponding to the data points to obtain the data point sets, it may also be used to obtain the current location of the vehicle; and inquiring the segmentation threshold bound with the current position of the vehicle as the first threshold.

A determining unit 703, configured to determine an obstacle corresponding to the data point set according to the data points in the data point set segmented by the segmenting unit 702.

It can be seen that, with the ultrasonic data processing system shown in fig. 7, the data points can be segmented by using the distance between the vehicle and the obstacle corresponding to the data points acquired by the ultrasonic sensor, the data points belonging to the same obstacle can be divided into the same data point set, and then the data points belonging to different obstacles can be segmented. Further, the first threshold value can be set by referring to the width or the length of the vehicle body, so that ultrasonic data points belonging to different obstacles can be effectively distinguished, and a stoppable area can be conveniently identified.

Example four

Referring to fig. 8, fig. 8 is a schematic structural diagram of another ultrasonic data processing system according to an embodiment of the disclosure. The processing system of the ultrasonic data shown in fig. 8 is optimized by the processing system of the ultrasonic data shown in fig. 7. In the processing system of ultrasonic data shown in fig. 8:

the above-mentioned dividing unit 702 may include:

the identifying subunit 7021 is configured to identify a variation amount of a distance between the vehicle and the obstacle, where the distance corresponds to two data points adjacent to each other in the position;

a first dividing subunit 7022, configured to, when the identifying subunit 7021 identifies that the variation exceeds a preset first threshold, divide two adjacent data points to divide the two adjacent data points into different data point sets.

That is, first dividing subunit 7022 may roughly divide a plurality of data points based on the first threshold value.

Further optionally, the dividing unit 702 may further include:

a fitting subunit 7023, configured to fit lines corresponding to the data point sets by using the data points in the data point sets to obtain a plurality of lines;

the identifier 7021 is further configured to identify a transition edge from the plurality of lines and identify a non-transition edge other than the transition edge from the plurality of lines; the jumping edge is formed by data points of which the variation between corresponding distances is in an ascending trend or a descending trend;

a computing subunit 7024, configured to compute a projection distance of the jump edge in a direction perpendicular to a driving direction of the vehicle;

a determining subunit 7025, configured to determine whether the projection distance is greater than a preset second threshold;

and a fusing subunit 7026, configured to fuse, when the determining subunit 7025 determines that the projection distance is smaller than or equal to the second threshold, the data points that form the hopping edge and the data points that form the non-hopping edge that are connected to the hopping edge into the same data point set.

Optionally, the method may further include:

and a second dividing subunit 7027, configured to, when the determining subunit 7025 determines that the projection distance is greater than the second threshold, divide the data points that form the hopping edge and the data points that form the non-hopping edge connected to the hopping edge into different data point sets.

As can be seen, the blending subunit 7026 and the second dividing subunit 7027 may further correct the division result of the rough division according to the projection distance of the transition edge on the y-axis, so as to improve the accuracy of the division.

Further, the dividing unit 702 may further include:

a denoising subunit 7028, configured to identify a noise point of distance jump corresponding to the data point set before the fitting subunit 7023 fits a line corresponding to the data point set by using the data points in the data point set to obtain a plurality of lines; filtering out noise points from the data point set to obtain a denoised data point set;

and the fitting subunit 7023 is specifically configured to fit lines corresponding to the data point set by using the data points in the denoised data point set to obtain a plurality of lines.

It can be seen that, by implementing the ultrasonic data processing system shown in fig. 8, a plurality of data points can be roughly divided based on the distance between the vehicle and the obstacle corresponding to the data points, so that the data points belonging to different obstacles can be divided. Furthermore, by judging the projection distance of the jump edge on the y axis, the segmentation result of the rough segmentation can be corrected so as to improve the accuracy of the segmentation. Furthermore, before the jump edge is identified and the projection distance on the y axis is calculated, the data points in the data point set need to be fitted into a line, and in order to improve the fitting accuracy, noise in the data point set can be filtered out first.

In addition, the embodiment of the invention discloses a vehicle which comprises any one of the ultrasonic data processing systems shown in 7 or 8.

The embodiment of the invention discloses a computer-readable storage medium which stores a computer program, wherein the computer program enables a computer to execute any one of the ultrasonic data processing methods shown in fig. 1 or fig. 3.

An embodiment of the invention discloses a computer program product comprising a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute any one of the ultrasonic data processing methods shown in fig. 1 or fig. 3.

It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Those skilled in the art should also appreciate that the embodiments described in this specification are exemplary and alternative embodiments, and that the acts and modules illustrated are not required in order to practice the invention.

In various embodiments of the present invention, it should be understood that the sequence numbers of the above-mentioned processes do not imply an inevitable order of execution, and the order of execution of the processes should be determined by their functions and inherent logic, and should not limit the implementation processes of the embodiments of the present invention.

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 hardware form, and can also be realized in a software functional unit form.

The integrated units, if implemented as software functional units and sold or used as a stand-alone product, may be stored in a computer accessible memory. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a memory, and includes several requests to enable a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute some or all of the steps of the above methods according to the embodiments of the present invention.

It will be understood by those skilled in the art that all or part of the steps in the methods of the above embodiments may be implemented by hardware instructions associated with a program, and the program may be stored in a computer readable storage medium, where the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM), or other Memory Disk storage, tape storage, or any other medium readable by a computer that can be used to carry or store data.

The ultrasonic data processing method, system, vehicle and storage system disclosed in the embodiments of the present invention are described in detail, and the principles and embodiments of the present invention are explained herein using specific examples, which are only used to help understand the method and core concept of the present invention. Meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific implementation manners and application ranges, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A method of processing ultrasound data, the method comprising:

segmenting the data points according to the distance between the vehicle and the obstacle corresponding to the data points to obtain a plurality of data point sets; the variation of the distance between the vehicle and the obstacle corresponding to the data points in the same data point set does not exceed a preset first threshold;

2. The method of claim 1, wherein said segmenting a number of said data points according to distances between a vehicle and said obstacle to which said data points correspond to obtain a number of data point sets comprises:

and if the variation exceeds a preset first threshold, segmenting the two adjacent data points so as to divide the two adjacent data points into different data point sets.

3. The method of claim 2, further comprising:

identifying a transition edge from the plurality of lines and identifying a non-transition edge of the plurality of lines other than the transition edge; the jumping edge is formed by data points of which the variation between the corresponding distances is in an ascending trend or in a descending trend;

4. The method of claim 3, further comprising:

if the projected distance is greater than the second threshold, the data points that constitute the transition edge and the data points that constitute the non-transition edge connected to the transition edge are divided into different sets of data points.

5. The method of claim 3 or 4, wherein before said fitting a line to which the set of data points corresponds using the data points in the set of data points to obtain a plurality of lines, the method further comprises:

6. A method according to any of claims 1-4, characterized in that the first threshold value is set with reference to the length or width of the vehicle.

7. The method according to any one of claims 1 to 4, wherein before the segmenting the plurality of data points according to the distance between the vehicle and the obstacle corresponding to the data points to obtain a plurality of data point sets, the method further comprises:

acquiring the current location of the vehicle;

8. A system for processing ultrasonic data, comprising:

9. A vehicle characterized in that it comprises a processing system of ultrasonic data according to claim 8.

10. A computer-readable storage medium characterized by storing a computer program, wherein the computer program causes a computer to execute the method of processing ultrasonic data according to any one of claims 1 to 7.