CN113486795A - Visual identification performance test method, device, system and equipment - Google Patents
Visual identification performance test method, device, system and equipment Download PDFInfo
- Publication number
- CN113486795A CN113486795A CN202110763555.1A CN202110763555A CN113486795A CN 113486795 A CN113486795 A CN 113486795A CN 202110763555 A CN202110763555 A CN 202110763555A CN 113486795 A CN113486795 A CN 113486795A
- Authority
- CN
- China
- Prior art keywords
- data
- identification
- parking space
- obtaining
- visual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to a method, a device, a system and equipment for testing the visual identification performance of a vehicle monitoring image system. The method comprises the following steps: acquiring visual detection data and radar detection data of a target parking space; acquiring visual identification deviation data corresponding to a target parking space; according to the vision identification deviation data, obtaining vision identification performance evaluation data of the vehicle monitoring image system; the obtaining of the visual identification deviation data corresponding to the target parking space includes: enabling the vehicle monitoring image system to output first identification data of a preset target in the target parking space, which is obtained according to the visual detection data; obtaining second identification data of the preset target according to the radar detection data; deviation data of the first identification data is obtained according to the first identification data and the second identification data. According to the embodiment of the application, the test cost can be reduced, and the test efficiency can be improved.
Description
Technical Field
The present disclosure relates to the field of visual recognition performance testing technologies, and in particular, to a method, an apparatus, a system, and a device for testing visual recognition performance of a vehicle monitoring system.
Background
In the related art, when a vehicle is cruising at a low speed, the vehicle can sense the surrounding environment through an Automatic Parking Assist (APA) function, so that a driver is helped to find a proper parking space. After the driver sends a parking instruction, the vehicle can be automatically parked in the parking space through the APA. The automatic parking auxiliary function of the vehicle is realized based on a vehicle monitoring image system, and the vehicle monitoring image system identifies the parking space limiter so as to determine the position of the vehicle which is parked at last in the automatic parking process. Only under the condition that the evaluation data of the visual identification performance of the vehicle monitoring image system reaches the preset expected conditions, the reliability of the identification result of the parking space limiter can be ensured, and therefore the vehicle can be finally parked at a proper position in the parking space. Therefore, it is very important to test the visual recognition performance of the vehicle monitoring image system of the vehicle.
Disclosure of Invention
In order to solve or partially solve the problems in the related art, the application provides a method, a device, a system and equipment for testing the visual identification performance of a vehicle monitoring image system, which can reduce the testing cost and improve the testing efficiency.
The application provides in a first aspect a method for testing visual identification performance of a vehicle surveillance imaging system, comprising:
acquiring visual detection data and radar detection data of a target parking space; the visual detection data is collected by a monitoring image system installed on a vehicle, and the radar detection data is collected by radar equipment installed on the vehicle;
obtaining visual identification deviation data corresponding to the target parking space;
obtaining visual identification performance evaluation data of the vehicle monitoring image system according to the visual identification deviation data;
wherein the obtaining of the visual identification deviation data corresponding to the target parking space comprises:
enabling the vehicle monitoring image system to output first identification data of a preset target in the target parking space, which is obtained according to the visual detection data;
obtaining second identification data of the preset target according to the radar detection data;
and obtaining deviation data of the first identification data according to the first identification data and the second identification data.
In one embodiment, the obtaining visual detection data and radar detection data of the target parking space includes: respectively obtaining visual detection data and radar detection data of a plurality of different types of target parking spaces;
the obtaining of the visual identification deviation data corresponding to the target parking space includes: obtaining a plurality of visual identification deviation data corresponding to the target parking spaces of different types;
the obtaining of the identification performance evaluation data of the vehicle monitoring image system according to the visual identification deviation data includes: and obtaining the identification performance evaluation data of the vehicle monitoring image system according to the plurality of visual identification deviation data.
In one embodiment, the causing the vehicle monitoring vision system to output first identification data of a predetermined target in the target parking space obtained from the visual detection data includes: enabling the vehicle monitoring image system to output first identification position data of a preset target in the target parking space in a vehicle coordinate system, wherein the first identification position data is obtained according to the visual detection data;
the obtaining second identification data of the predetermined target from the radar detection data includes: obtaining second identification position data of the preset target in the vehicle coordinate system according to the radar detection data;
the obtaining deviation data of the first identification data according to the first identification data and the second identification data comprises: and obtaining deviation data of the first identification position data according to the first identification position data and the second identification position data.
In one embodiment, the obtaining visual detection data and radar detection data of the target parking space includes:
enabling the vehicle monitoring image system and the radar equipment to acquire visual detection data and radar detection data of a target parking space and obtain system time from a CAN bus of the vehicle;
and obtaining temporally aligned visual detection data and radar detection data according to the system time.
In one embodiment, the causing the vehicle monitoring vision system to output first identification data of a predetermined target in the target parking space obtained from the visual detection data includes: enabling the vehicle monitoring image system to output position coordinates of end points of two ends of the parking space limiting object in the target parking space along the length direction under a vehicle coordinate system, wherein the position coordinates are obtained according to the visual detection data;
the obtaining second identification data of the predetermined target from the radar detection data includes: obtaining position related data of the parking space limiter along the length direction under the vehicle coordinate system according to the radar detection data;
the obtaining deviation data of the first identification data according to the first identification data and the second identification data comprises: and respectively obtaining deviation data of the end points at the two ends according to the position coordinates of the end points at the two ends and the position related data.
In one embodiment, the obtaining deviation data of the two end points according to the position coordinates of the two end points and the position-related data respectively includes:
and respectively obtaining distance values between the end points of the two ends and the straight lines in the length direction determined by the position related data according to the position coordinates of the end points of the two ends and the position related data.
In one embodiment, the parking space limiter comprises one or more combinations of a parking space limiting rod, a parking space limiter and a parking space ground lock;
the vehicle monitoring image system comprises an AVM system;
the radar equipment comprises a laser radar which is installed along the direction of the parking space limiter.
This application second aspect provides a vehicle monitoring image system's visual identification capability test device, includes:
the acquisition module is used for acquiring visual detection data and radar detection data of the target parking space; the visual detection data is collected by a monitoring image system installed on a vehicle, and the radar detection data is collected by radar equipment installed on the vehicle;
the test module is used for obtaining visual identification deviation data corresponding to the target parking space;
the evaluation module is used for obtaining the vision identification performance evaluation data of the vehicle monitoring image system according to the vision identification deviation data;
wherein the obtaining, by the testing module, the visual identification deviation data corresponding to the target parking space includes: enabling the vehicle monitoring image system to output first identification data of a preset target in the target parking space, which is obtained according to the visual detection data; obtaining second identification data of the preset target according to the radar detection data; and obtaining deviation data of the first identification data according to the first identification data and the second identification data.
In one embodiment, the causing the vehicle monitoring image system to output the first identification data of the predetermined target in the target parking space obtained according to the visual detection data by the testing module includes: enabling the vehicle monitoring image system to output first identification position data of a preset target in the target parking space in a vehicle coordinate system, wherein the first identification position data is obtained according to the visual detection data;
the obtaining, by the test module, second identification data of the predetermined target according to the radar detection data includes: obtaining second identification position data of the preset target in the vehicle coordinate system according to the radar detection data;
the step of obtaining deviation data of the first identification data by the test module according to the first identification data and the second identification data comprises: and obtaining deviation data of the first identification position data according to the first identification position data and the second identification position data.
In one embodiment, the causing the vehicle monitoring image system to output the first identification data of the predetermined target in the target parking space obtained according to the visual detection data by the testing module includes: enabling the vehicle monitoring image system to output position coordinates of end points of two ends of the parking space limiting object in the target parking space along the length direction under a vehicle coordinate system, wherein the position coordinates are obtained according to the visual detection data;
the obtaining, by the test module, second identification data of the predetermined target according to the radar detection data includes: obtaining position related data of the parking space limiter along the length direction under the vehicle coordinate system according to the radar detection data;
the step of obtaining deviation data of the first identification data by the test module according to the first identification data and the second identification data comprises: and respectively obtaining deviation data of the end points at the two ends according to the position coordinates of the end points at the two ends and the position related data.
A third aspect of the application provides a test apparatus comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implementing a method as described above.
The present application fourth aspect provides a visual identification performance test system of vehicle monitoring image system, includes: vehicle monitoring image system, radar equipment and test equipment as described above.
The technical scheme provided by the application can comprise the following beneficial effects:
according to the method provided by the embodiment of the application, the visual identification deviation data of the vehicle monitoring image system is obtained according to the radar equipment, and then the visual identification performance evaluation data of the vehicle monitoring image system can be obtained according to the visual identification deviation data, so that the visual identification performance test work of the vehicle monitoring image system can be realized without the assistance of special mapping and positioning equipment, the visual identification performance evaluation data of the vehicle monitoring image system can be obtained, the test cost is low, and the test efficiency is high.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application, as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
Fig. 1 is a schematic flowchart illustrating a method for testing visual recognition performance of a vehicle monitoring image system according to an embodiment of the present disclosure;
fig. 2A is a schematic flowchart of a method for testing visual identification performance of a vehicle monitoring system according to another embodiment of the present application;
fig. 2B is an exemplary diagram illustrating data acquisition of a rear stop lever in a target parking space by the vehicle monitoring image system and the radar device according to the embodiment of the present application;
fig. 3 is another schematic flow chart illustrating a method for testing the visual recognition performance of a vehicle monitoring system according to another embodiment of the present application;
fig. 4 is a schematic structural diagram of a visual recognition performance testing apparatus of a vehicle monitoring image system according to an embodiment of the present application;
FIG. 5 is a schematic structural diagram of a test apparatus according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a vision recognition performance testing system of a vehicle monitoring image system according to an embodiment of the present application.
Detailed Description
Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While embodiments of the present application are illustrated in the accompanying drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
In the related art, a visual recognition performance test of a vehicle monitoring image system is performed by using a special mapping and positioning device. The special mapping and positioning equipment is expensive and has low testing efficiency. In addition, special mapping and positioning equipment has great limitation on scenes during testing.
In view of the above problems, an embodiment of the present application provides a visual identification performance testing scheme for a vehicle monitoring image system, which can perform a visual identification performance testing operation of the vehicle monitoring image system without the assistance of a special mapping and positioning device, so as to obtain visual identification performance evaluation data of the vehicle monitoring image system, and the method has the advantages of low testing cost, high testing efficiency, flexible implementation, and wide application range.
The technical solutions of the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a method for testing visual recognition performance of a vehicle surveillance imaging system according to an embodiment of the present disclosure. Referring to fig. 1, the method includes:
and S101, obtaining visual detection data and radar detection data of the target parking space. The visual detection data is collected by a monitoring image system installed on the vehicle, and the radar detection data is collected by radar equipment installed on the vehicle.
The monitoring image system may be an AVM (Around View Monitor) system, which may also be referred to as a Around-the-eye vision inspection system, and includes a plurality of cameras and a software system, where the software system includes a vision recognition module for performing vision recognition processing on an image captured by the cameras. The Radar device may include a Laser Radar (Laser Radar), among others.
In this step, the visual detection data (i.e., the image data captured by the camera) of the target parking space may be obtained by the monitoring image system installed in the vehicle, and the radar detection data of the target parking space may be obtained by the radar device installed in the vehicle.
And S102, obtaining visual identification deviation data corresponding to the target parking space.
In this step, obtaining the visual identification deviation data corresponding to the target parking space may include: enabling the vehicle monitoring image system to output first identification data of a preset target in the target parking space, which is obtained according to the visual detection data; obtaining second identification data of the preset target according to the radar detection data; deviation data of the first identification data is obtained according to the first identification data and the second identification data.
The predetermined target can be a parking space limiter, and the parking space limiter can comprise one or more of a parking space limiting rod, a parking space limiter and a parking space ground lock. The parking space limiting rod may be also called a parking space rear gear rod or a parking space positioning rod, and is generally a rod-shaped object. The parking space limiter can be called as a parking space limiting block and is generally installed on a parking space in pairs.
After the camera of the AVM system shoots and obtains the image of the target parking space, the visual recognition module recognizes the preset target of the image, and first recognition data of the preset target are obtained.
After the point cloud data of the target parking space is obtained through scanning by the radar equipment, region-of-interest segmentation and edge extraction, filtering and the like of the preset target are carried out according to the preset target, and second identification data of the preset target are obtained.
In this step, the first identification data may be verified using the second identification data as a true value, so as to obtain deviation data of the first identification data. The deviation data of the first identification data may include deviation data of the first identification data from the second identification data.
And step S103, obtaining the vision identification performance evaluation data of the vehicle monitoring image system according to the vision identification deviation data.
The visual identification Performance evaluation data of the vehicle monitoring image system may include preset Performance KPI (Key Performance Indicator) data. It can be understood that when the vision identification deviation data is large, the performance KPI data obtained according to the vision identification deviation data indicates that the vision identification performance of the vehicle monitoring image system is poor, and further optimization is needed; when the vision identification deviation data is smaller, the performance KPI data obtained according to the vision identification deviation data shows that the vision identification performance of the vehicle monitoring image system is better.
Further, in one specific implementation, if the visual recognition deviation data or the visual recognition performance evaluation data meets a preset condition, a user prompt indicating that the visual recognition performance of the vehicle monitoring image system is qualified may be output.
Furthermore, if the vision identification deviation data or the vision identification performance evaluation data do not accord with the preset conditions, the vision identification deviation data can be used as correction data to optimize a vision identification module of the vehicle monitoring image system so as to improve the identification rate of the vehicle monitoring image system, so that the vehicle automatic parking software module can obtain more accurate data, and the accuracy of the vehicle automatic parking is improved.
It can be seen from this embodiment that, in the method provided in the embodiment of the present application, the visual detection data of the target parking space acquired by the monitoring image system and the radar detection data of the target parking space acquired by the radar device are acquired, so as to obtain the visual identification deviation data corresponding to the target parking space, where the visual identification deviation data may include the deviation data of the first identification data. The deviation data of the first identification data can be obtained according to first identification data of a preset target in the target parking space obtained by using the visual detection data and second identification data of the preset target obtained by using the radar detection data. The visual identification deviation data of the vehicle monitoring image system is obtained according to the radar equipment, and then the visual identification performance evaluation data of the vehicle monitoring image system can be obtained according to the visual identification deviation data, so that the visual identification performance test work of the vehicle monitoring image system can be realized without the assistance of special mapping and positioning equipment, the visual identification performance evaluation data of the vehicle monitoring image system is obtained, and the visual identification performance evaluation data of the vehicle monitoring image system is low in test cost, high in test efficiency, flexible and high in implementation and wide in application range.
Fig. 2A is a schematic flowchart of a method for testing visual identification performance of a vehicle monitoring system according to another embodiment of the present application. Referring to fig. 2A, the method includes:
and step S201, obtaining visual detection data and radar detection data of the target parking space. The visual detection data is collected by a monitoring image system installed on the vehicle, and the radar detection data is collected by radar equipment installed on the vehicle.
The monitoring image system may include an AVM (Around View Monitor, panoramic monitoring image) system, which may also be referred to as a Around-the-eye vision detection system, and includes a plurality of cameras and a software system arranged Around the vehicle body, and the software system has a vision recognition module for performing vision recognition processing on the images shot by the cameras. The Radar device may include a Laser Radar (Laser Radar), among others.
In some embodiments, the obtaining of the visual detection data and the radar detection data of the target parking space in step S201 may include:
enabling a vehicle monitoring image system and radar equipment to acquire visual detection data and radar detection data of a target parking space and acquiring system time from a Controller Area Network (CAN) bus of a vehicle; temporally aligned visual inspection data and radar detection data are obtained from the system time.
Through the step, the obtained visual detection data and the radar detection data can be aligned in system time, so that the effectiveness of the subsequent step is guaranteed, and the correctness of the visual identification deviation data obtained subsequently is guaranteed.
Further, in this embodiment, before the visual identification deviation data is obtained, the radar device may be calibrated to obtain the internal reference and the external reference of the radar device. After obtaining radar detection data that is time aligned with the vision inspection data, the radar detection data may be corrected using the internal reference. And then the corrected radar detection data is processed, so that the accuracy of the radar detection data serving as a recognition basis can be improved. The corrected radar detection data is point cloud data of a target parking space, and the processing of the corrected radar detection data may include: and for the point cloud data, performing region-of-interest segmentation and edge extraction, filtering and other processing of a preset target, and obtaining the position coordinates of the preset target in a vehicle coordinate system by using external parameters of radar equipment.
Step S202, enabling the vehicle monitoring image system to output first identification data of a preset target in the target parking space, wherein the first identification data are obtained according to the visual detection data.
The vehicle monitoring image system may include an AVM system.
In one implementation, the vehicle monitoring image system may be enabled to output first identification position data of a predetermined target in a target parking space in a vehicle coordinate system, which is obtained according to the visual detection data. That is, the first identification data may include first identification position data of the predetermined target in the vehicle coordinate system. Wherein the predetermined target may be a parking space limiter. The obtained first identification position data is based on data in a vehicle coordinate system, so that effective data comparison in subsequent steps is facilitated.
More specifically, the vehicle monitoring image system can output the position coordinates of the end points of the parking space limiter in the target parking space along the length direction under the vehicle coordinate system, which are obtained according to the visual detection data. Wherein, the parking space limiter can be a rear stop lever. It is understood that the first identification position data in the vehicle coordinate system may include position coordinates of end points of the parking space stopper in the length direction in the vehicle coordinate system. Referring to fig. 2B, that is, the first identification data may be position coordinates of two end points PT1 and PT2 of the parking space stopper in the vehicle coordinate system. For example, the first identification data may be coordinate information of end points of both ends of the rear bar in the length direction. For another example, the first identification data may be information of coordinates of end points of two spaced-apart ends of the paired parking space limiters.
Step S203, second identification data of the preset target is obtained according to the radar detection data.
Wherein, radar equipment can include laser radar, and laser radar can be followed and installed towards the spacing object direction of parking stall to in discernment parking stall spacing object. For example, in one embodiment, the parking space limiter is a rear bumper, and the single line lidar is mounted on a suitable location of the rear bumper of the vehicle and is oriented in the same direction as a camera of the rear bumper detected by the vehicle surveillance imaging system to align with a scanning area of the camera.
In this step, second recognized position data of the predetermined target in the vehicle coordinate system may be obtained from the radar detection data. That is, the obtained second recognized position data is based on the data in the vehicle coordinate system, thereby facilitating effective data comparison with the first recognized position data in the subsequent step.
Further, in this step, the second identification position data may be position related data of the parking space limiter in the vehicle coordinate system along the length direction according to the radar detection data, and the position related data may include, for example, position coordinates of end points of the rear bar in the length direction or other points of the outer surface of the rear bar in the vehicle coordinate system.
It is understood that, in the present application, the sequence of step S202 and step S203 is not limited, and step S203 may be executed before step S202, or executed synchronously with step S202.
And step S204, obtaining deviation data of the first identification data according to the first identification data and the second identification data.
In this embodiment, the second identification position data obtained according to the radar detection data is used as a true value, and the first identification position data obtained according to the visual detection data of the vehicle monitoring image system is verified to obtain deviation data of the first identification position data, that is, the visual identification deviation data of the vehicle monitoring image system.
When the preset target is the rear stop lever, deviation data of the position coordinates of the two end points is obtained according to the position coordinates of the two end points of the rear stop lever output by the vehicle monitoring image system and the position related data of the rear stop lever obtained according to radar detection data. In one specific implementation, the distance values between the position coordinates of the two end points PT1 and PT2 and the straight line in the length direction (indicated by L in fig. 2B) determined by the position data may be obtained, respectively. That is, the visual recognition deviation data of the vehicle monitoring image system may be a distance value between the end point coordinates of both ends of the rear bar recognized by the vehicle monitoring image system and a straight line along the length direction of the rear bar recognized according to the radar detection data.
And S205, acquiring identification performance evaluation data of the vehicle monitoring image system according to the deviation data of the first identification data.
And S206, if the identification performance evaluation data meet the preset conditions, outputting a user prompt with qualified visual identification performance.
Furthermore, if the identification performance evaluation data does not meet the preset conditions, the deviation data of the first identification data can be used as correction data to optimize the visual identification module of the vehicle monitoring image system, so that the identification rate of the vehicle monitoring image system is improved, the vehicle automatic parking software module can obtain more accurate data, and the accuracy of automatic parking of the vehicle is improved.
Fig. 3 is a flowchart illustrating a method for testing the visual recognition performance of a vehicle surveillance imaging system according to another embodiment of the present application. Referring to fig. 3, the method of the present embodiment includes:
s301, respectively obtaining visual detection data and radar detection data of a plurality of target parking spaces of different types; the visual detection data is collected by a monitoring image system installed on the vehicle, and the radar detection data is collected by radar equipment installed on the vehicle.
Wherein, a plurality of different types of target parking spaces may include a plurality of different types of parking spaces and/or different types of parking space restraints in different types of parking spaces. Different types of parking spaces may include conventional vertical spaces, non-vertical spaces, tile spaces (e.g., ecological brick spaces, textured brick spaces, etc.), other special spaces (e.g., ponding spaces, shaded spaces with poor light, etc.), and so forth. Different types of parking space limiters may include parking space limiters of different specifications and sizes (e.g., different heights), parking space limiters of different colors, etc.
According to this embodiment, can be located the target parking stall of different grade type with the vehicle, make respectively in each target parking stall and install the monitoring image system collection visual detection data of installing in the vehicle, make the radar equipment collection radar detection data of installing in the vehicle to obtain the respective visual detection data and the radar detection data in a plurality of different grade type target parking stalls.
Step S302, a plurality of visual identification deviation data corresponding to a plurality of target parking spaces of different types are obtained.
After the respective visual detection data and radar detection data of a plurality of different types of target parking spaces are respectively obtained, for each target parking space, the vehicle monitoring image system outputs first identification data of a preset target obtained according to the visual detection data of the parking space, second identification data of the preset target is obtained according to the radar detection data of the parking space, and deviation data of the first identification data corresponding to the parking space is obtained according to the first identification data and the second identification data. It is understood that the above embodiments can be implemented by referring to the description of the foregoing embodiments, and the detailed description is omitted here. Thus, a plurality of visual recognition deviation data corresponding to a plurality of target parking spaces can be obtained.
Step S303, obtaining identification performance evaluation data of the vehicle monitoring image system according to the plurality of visual identification deviation data.
In one implementation, a weighted average of a plurality of visual identification deviation data may be obtained, and identification performance evaluation data of the vehicle monitoring image system may be obtained according to the weighted average data.
In another specific implementation, the identification performance classification evaluation data corresponding to each visual identification deviation data may be obtained, and then the identification performance evaluation data of the vehicle monitoring image system may be obtained according to the obtained plurality of identification performance classification evaluation data.
Further, if the obtained identification performance evaluation data meets the preset conditions, a user prompt indicating that the visual identification performance of the vehicle monitoring image system is qualified can be output.
Furthermore, if the obtained identification performance evaluation data does not meet the preset conditions, the weighted average value of the plurality of visual identification deviation data can be used as correction data, and a visual identification module of the vehicle monitoring image system is optimized to improve the identification rate of the vehicle monitoring image system, so that the vehicle automatic parking software module can obtain more accurate data, and the accuracy of the vehicle automatic parking is improved.
In the embodiment, the collected sample range is enlarged by obtaining the visual detection data and the radar detection data of a plurality of different types of target parking spaces, and the reliability of the visual identification performance evaluation data of the vehicle monitoring image system under the different types of parking spaces is further improved.
Corresponding to the embodiment of the application function implementation method, the application also provides a device for testing the visual identification performance of the vehicle monitoring image system and a corresponding embodiment.
Fig. 4 is a schematic structural diagram of a visual recognition performance testing apparatus of a vehicle monitoring image system according to an embodiment of the present application.
Referring to fig. 4, the device for testing the visual recognition performance of the vehicle monitoring image system of the present embodiment includes: an acquisition module 401, a test module 402 and an evaluation module 403.
An obtaining module 401, configured to obtain visual detection data and radar detection data of a target parking space; the visual detection data is collected by a monitoring image system installed on the vehicle, and the radar detection data is collected by radar equipment installed on the vehicle.
The testing module 402 is configured to obtain visual identification deviation data corresponding to a target parking space.
And an evaluation module 403, configured to obtain, according to the vision recognition deviation data, vision recognition performance evaluation data of the vehicle monitoring image system.
The obtaining, by the test module 402, the visual identification deviation data corresponding to the target parking space includes: enabling the vehicle monitoring image system to output first identification data of a preset target in the target parking space, which is obtained according to the visual detection data; obtaining second identification data of the preset target according to the radar detection data; deviation data of the first identification data is obtained according to the first identification data and the second identification data.
Optionally, the manner of obtaining the visual identification deviation data corresponding to the target parking space by the test module 402 includes:
enabling the vehicle monitoring image system to output first identification position data of a preset target in the target parking space in a vehicle coordinate system, wherein the first identification position data is obtained according to the visual detection data;
obtaining second identification position data of the preset target in a vehicle coordinate system according to the radar detection data;
deviation data of the first recognized position data is obtained according to the first recognized position data and the second recognized position data.
Optionally, the manner of obtaining the visual identification deviation data corresponding to the target parking space by the testing module 402 may further include:
enabling the vehicle monitoring image system to output position coordinates of end points of two ends of the parking space limiting object in the target parking space along the length direction under a vehicle coordinate system, wherein the position coordinates are obtained according to the visual detection data;
obtaining position related data of the parking space limiter along the length direction under a vehicle coordinate system according to the radar detection data;
and respectively obtaining deviation data of the end points at the two ends according to the position coordinates and the position related data of the end points at the two ends.
In the embodiment, the visual identification deviation data of the vehicle monitoring image system is obtained according to the radar equipment, and then the visual identification performance evaluation data of the vehicle monitoring image system can be obtained according to the visual identification deviation data, so that the visual identification performance test work of the vehicle monitoring image system can be realized without the assistance of special mapping and positioning equipment, the visual identification performance evaluation data of the vehicle monitoring image system is obtained, and the visual identification performance evaluation data of the vehicle monitoring image system is low in test cost, high in test efficiency, flexible and high in implementation and wide in application range.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 5 is a schematic structural diagram of a test apparatus according to an embodiment of the present application. Referring to fig. 5, the test apparatus 500 of the present embodiment includes a processor 520 and a memory 510.
The Processor 520 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 510 may include various types of storage units, such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions for the processor 520 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory 510 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, may also be employed. In some embodiments, memory 510 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a digital versatile disc read only (e.g., DVD-ROM, dual layer DVD-ROM), a Blu-ray disc read only, an ultra-dense disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disk, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 510 has stored thereon executable code that, when processed by the processor 520, may cause the processor 520 to perform some or all of the methods described above.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of a test device (or test device, server, etc.), causes the processor to perform some or all of the various steps of the above-described methods in accordance with the present application.
Fig. 6 is a schematic structural diagram of a vision recognition performance testing system of a vehicle monitoring image system according to an embodiment of the present application.
Referring to fig. 6, the system for testing the visual recognition performance of the vehicle monitoring image system of the present embodiment includes: a vehicle monitoring vision system 601, a radar device 602, and a testing device 500 as described above.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A visual identification performance test method of a vehicle monitoring image system is characterized by comprising the following steps:
acquiring visual detection data and radar detection data of a target parking space; the visual detection data is collected by a monitoring image system installed on a vehicle, and the radar detection data is collected by radar equipment installed on the vehicle;
obtaining visual identification deviation data corresponding to the target parking space;
obtaining visual identification performance evaluation data of the vehicle monitoring image system according to the visual identification deviation data;
wherein the obtaining of the visual identification deviation data corresponding to the target parking space comprises:
enabling the vehicle monitoring image system to output first identification data of a preset target in the target parking space, which is obtained according to the visual detection data;
obtaining second identification data of the preset target according to the radar detection data;
and obtaining deviation data of the first identification data according to the first identification data and the second identification data.
2. The method of claim 1, wherein:
the obtaining of the visual detection data and the radar detection data of the target parking space comprises: respectively obtaining visual detection data and radar detection data of a plurality of different types of target parking spaces;
the obtaining of the visual identification deviation data corresponding to the target parking space includes: obtaining a plurality of visual identification deviation data corresponding to the target parking spaces of different types;
the obtaining of the identification performance evaluation data of the vehicle monitoring image system according to the visual identification deviation data includes: and obtaining the identification performance evaluation data of the vehicle monitoring image system according to the plurality of visual identification deviation data.
3. The method of claim 1, wherein obtaining visual inspection data and radar detection data for a target parking space comprises:
enabling the vehicle monitoring image system and the radar equipment to acquire visual detection data and radar detection data of a target parking space and obtain system time from a CAN bus of the vehicle;
and obtaining temporally aligned visual detection data and radar detection data according to the system time.
4. The method according to any one of claims 1 to 3, wherein:
the causing the vehicle monitoring image system to output first identification data of a predetermined target in the target parking space obtained according to the visual detection data includes: enabling the vehicle monitoring image system to output position coordinates of end points of two ends of the parking space limiting object in the target parking space along the length direction under a vehicle coordinate system, wherein the position coordinates are obtained according to the visual detection data;
the obtaining second identification data of the predetermined target from the radar detection data includes: obtaining position related data of the parking space limiter along the length direction under the vehicle coordinate system according to the radar detection data;
the obtaining deviation data of the first identification data according to the first identification data and the second identification data comprises: and respectively obtaining deviation data of the end points at the two ends according to the position coordinates of the end points at the two ends and the position related data.
5. The method of claim 4, wherein:
the parking space limiter comprises one or more combinations of a parking space limiting rod, a parking space limiter and a parking space ground lock;
the vehicle monitoring image system comprises an AVM system;
the radar equipment comprises a laser radar which is installed along the direction of the parking space limiter.
6. The utility model provides a vehicle monitoring image system's visual identification capability test device which characterized in that includes:
the acquisition module is used for acquiring visual detection data and radar detection data of the target parking space; the visual detection data is collected by a monitoring image system installed on a vehicle, and the radar detection data is collected by radar equipment installed on the vehicle;
the test module is used for obtaining visual identification deviation data corresponding to the target parking space;
the evaluation module is used for obtaining the vision identification performance evaluation data of the vehicle monitoring image system according to the vision identification deviation data;
wherein the obtaining, by the testing module, the visual identification deviation data corresponding to the target parking space includes: enabling the vehicle monitoring image system to output first identification data of a preset target in the target parking space, which is obtained according to the visual detection data; obtaining second identification data of the preset target according to the radar detection data; and obtaining deviation data of the first identification data according to the first identification data and the second identification data.
7. The apparatus of claim 6, wherein:
the test module enables the vehicle monitoring image system to output first identification data of a preset target in the target parking space, which is obtained according to the visual detection data, and comprises the following steps: enabling the vehicle monitoring image system to output first identification position data of a preset target in the target parking space in a vehicle coordinate system, wherein the first identification position data is obtained according to the visual detection data;
the obtaining, by the test module, second identification data of the predetermined target according to the radar detection data includes: obtaining second identification position data of the preset target in the vehicle coordinate system according to the radar detection data;
the step of obtaining deviation data of the first identification data by the test module according to the first identification data and the second identification data comprises: and obtaining deviation data of the first identification position data according to the first identification position data and the second identification position data.
8. The apparatus of claim 6, wherein:
the test module enables the vehicle monitoring image system to output first identification data of a preset target in the target parking space, which is obtained according to the visual detection data, and comprises the following steps: enabling the vehicle monitoring image system to output position coordinates of end points of two ends of the parking space limiting object in the target parking space along the length direction under a vehicle coordinate system, wherein the position coordinates are obtained according to the visual detection data;
the obtaining, by the test module, second identification data of the predetermined target according to the radar detection data includes: obtaining position related data of the parking space limiter along the length direction under the vehicle coordinate system according to the radar detection data;
the step of obtaining deviation data of the first identification data by the test module according to the first identification data and the second identification data comprises: and respectively obtaining deviation data of the end points at the two ends according to the position coordinates of the end points at the two ends and the position related data.
9. A test apparatus comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the method of any one of claims 1 to 5.
10. The utility model provides a visual identification capability test system of vehicle monitoring image system which characterized in that includes: a vehicle surveillance vision system, a radar apparatus and a test apparatus according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110763555.1A CN113486795A (en) | 2021-07-06 | 2021-07-06 | Visual identification performance test method, device, system and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110763555.1A CN113486795A (en) | 2021-07-06 | 2021-07-06 | Visual identification performance test method, device, system and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113486795A true CN113486795A (en) | 2021-10-08 |
Family
ID=77940599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110763555.1A Pending CN113486795A (en) | 2021-07-06 | 2021-07-06 | Visual identification performance test method, device, system and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113486795A (en) |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010249613A (en) * | 2009-04-14 | 2010-11-04 | Toyota Motor Corp | Obstacle recognition device and vehicle control unit |
| KR20140133131A (en) * | 2013-05-09 | 2014-11-19 | 현대오트론 주식회사 | Apparatus and method for correcting error of sensor of vehicle |
| KR20170080480A (en) * | 2015-12-30 | 2017-07-10 | 건아정보기술 주식회사 | The vehicle detecting system by converging radar and image |
| CN108694731A (en) * | 2018-05-11 | 2018-10-23 | 武汉环宇智行科技有限公司 | Fusion and positioning method and equipment based on low line beam laser radar and binocular camera |
| CN109782247A (en) * | 2019-01-28 | 2019-05-21 | 中船重工鹏力（南京）大气海洋信息***有限公司 | A method of utilizing track Information revision radar return |
| CN109919893A (en) * | 2019-03-20 | 2019-06-21 | 湖北亿咖通科技有限公司 | Point cloud modification method, device and readable storage medium storing program for executing |
| CN110310339A (en) * | 2019-07-04 | 2019-10-08 | 厦门金龙联合汽车工业有限公司 | A kind of caliberating device and a kind of radar and camera combined calibrating method and system |
| CN110604574A (en) * | 2019-09-16 | 2019-12-24 | 河北微幼趣教育科技有限公司 | Human body height measuring method based on video imaging principle |
| CN110799918A (en) * | 2017-08-04 | 2020-02-14 | 宝马股份公司 | Method, apparatus and computer program for a vehicle |
| CN111582256A (en) * | 2020-04-26 | 2020-08-25 | 智慧互通科技有限公司 | Parking management method and device based on radar and visual information |
| CN111624610A (en) * | 2020-04-29 | 2020-09-04 | 东风汽车集团有限公司 | Parking space angle-based self-adaptive parking ultrasonic radar adjusting method |
| CN111830519A (en) * | 2020-06-03 | 2020-10-27 | 江西江铃集团新能源汽车有限公司 | Multi-sensor fusion distance measurement method |
| CN111881955A (en) * | 2020-07-15 | 2020-11-03 | 北京经纬恒润科技有限公司 | Multi-source sensor information fusion method and device |
| CN112330754A (en) * | 2020-11-25 | 2021-02-05 | 上海欧菲智能车联科技有限公司 | Binocular vision correction method and device, electronic equipment and storage medium |
| CN112550278A (en) * | 2020-12-03 | 2021-03-26 | 上汽大众汽车有限公司 | Automatic parking method and system based on look-around camera and ultrasonic radar detection |
| CN112633152A (en) * | 2020-12-22 | 2021-04-09 | 深圳佑驾创新科技有限公司 | Parking space detection method and device, computer equipment and storage medium |
| CN112712129A (en) * | 2021-01-11 | 2021-04-27 | 深圳力维智联技术有限公司 | Multi-sensor fusion method, device, equipment and storage medium |
| CN112735174A (en) * | 2020-12-25 | 2021-04-30 | 广州小鹏自动驾驶科技有限公司 | Parking method and device |
| CN112835019A (en) * | 2020-12-30 | 2021-05-25 | 广州小鹏自动驾驶科技有限公司 | Vehicle sensor calibration method and device, vehicle and storage medium |
| CN112907676A (en) * | 2019-11-19 | 2021-06-04 | 浙江商汤科技开发有限公司 | Calibration method, device and system of sensor, vehicle, equipment and storage medium |
-
2021
- 2021-07-06 CN CN202110763555.1A patent/CN113486795A/en active Pending
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010249613A (en) * | 2009-04-14 | 2010-11-04 | Toyota Motor Corp | Obstacle recognition device and vehicle control unit |
| KR20140133131A (en) * | 2013-05-09 | 2014-11-19 | 현대오트론 주식회사 | Apparatus and method for correcting error of sensor of vehicle |
| KR20170080480A (en) * | 2015-12-30 | 2017-07-10 | 건아정보기술 주식회사 | The vehicle detecting system by converging radar and image |
| CN110799918A (en) * | 2017-08-04 | 2020-02-14 | 宝马股份公司 | Method, apparatus and computer program for a vehicle |
| CN108694731A (en) * | 2018-05-11 | 2018-10-23 | 武汉环宇智行科技有限公司 | Fusion and positioning method and equipment based on low line beam laser radar and binocular camera |
| CN109782247A (en) * | 2019-01-28 | 2019-05-21 | 中船重工鹏力（南京）大气海洋信息***有限公司 | A method of utilizing track Information revision radar return |
| CN109919893A (en) * | 2019-03-20 | 2019-06-21 | 湖北亿咖通科技有限公司 | Point cloud modification method, device and readable storage medium storing program for executing |
| CN110310339A (en) * | 2019-07-04 | 2019-10-08 | 厦门金龙联合汽车工业有限公司 | A kind of caliberating device and a kind of radar and camera combined calibrating method and system |
| CN110604574A (en) * | 2019-09-16 | 2019-12-24 | 河北微幼趣教育科技有限公司 | Human body height measuring method based on video imaging principle |
| CN112907676A (en) * | 2019-11-19 | 2021-06-04 | 浙江商汤科技开发有限公司 | Calibration method, device and system of sensor, vehicle, equipment and storage medium |
| CN111582256A (en) * | 2020-04-26 | 2020-08-25 | 智慧互通科技有限公司 | Parking management method and device based on radar and visual information |
| CN111624610A (en) * | 2020-04-29 | 2020-09-04 | 东风汽车集团有限公司 | Parking space angle-based self-adaptive parking ultrasonic radar adjusting method |
| CN111830519A (en) * | 2020-06-03 | 2020-10-27 | 江西江铃集团新能源汽车有限公司 | Multi-sensor fusion distance measurement method |
| CN111881955A (en) * | 2020-07-15 | 2020-11-03 | 北京经纬恒润科技有限公司 | Multi-source sensor information fusion method and device |
| CN112330754A (en) * | 2020-11-25 | 2021-02-05 | 上海欧菲智能车联科技有限公司 | Binocular vision correction method and device, electronic equipment and storage medium |
| CN112550278A (en) * | 2020-12-03 | 2021-03-26 | 上汽大众汽车有限公司 | Automatic parking method and system based on look-around camera and ultrasonic radar detection |
| CN112633152A (en) * | 2020-12-22 | 2021-04-09 | 深圳佑驾创新科技有限公司 | Parking space detection method and device, computer equipment and storage medium |
| CN112735174A (en) * | 2020-12-25 | 2021-04-30 | 广州小鹏自动驾驶科技有限公司 | Parking method and device |
| CN112835019A (en) * | 2020-12-30 | 2021-05-25 | 广州小鹏自动驾驶科技有限公司 | Vehicle sensor calibration method and device, vehicle and storage medium |
| CN112712129A (en) * | 2021-01-11 | 2021-04-27 | 深圳力维智联技术有限公司 | Multi-sensor fusion method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 胡远志;刘俊生;何佳;肖航;宋佳;: "基于激光雷达点云与图像融合的车辆目标检测方法", 汽车安全与节能学报, no. 04 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106952308B (en) | Method and system for determining position of moving object | |
| US20150154458A1 (en) | Lane change determining apparatus, junction entry determining apparatus and method thereof | |
| JP4943034B2 (en) | Stereo image processing device | |
| CN112289070B (en) | Parking space detection method and device, vehicle and readable medium | |
| CN107609483A (en) | Risk object detection method, device towards drive assist system | |
| CN113920487A (en) | Obstacle detection processing method, device and system | |
| CN114088114B (en) | Vehicle pose calibration method and device and electronic equipment | |
| CN110853366A (en) | Method and device for detecting parking position of vehicle | |
| CN111950504B (en) | Vehicle detection method and device and electronic equipment | |
| CN114187579A (en) | Target detection method, apparatus and computer-readable storage medium for automatic driving | |
| CN113256729A (en) | External parameter calibration method, device, equipment and storage medium for laser radar and camera | |
| WO2024016524A1 (en) | Connected vehicle position estimation method and apparatus based on independent non-uniform incremental sampling | |
| CN112598743A (en) | Pose estimation method of monocular visual image and related device | |
| CN113284194A (en) | Calibration method, device and equipment for multiple RS (remote sensing) equipment | |
| CN113486795A (en) | Visual identification performance test method, device, system and equipment | |
| CN115761668A (en) | Camera stain recognition method and device, vehicle and storage medium | |
| CN113870754B (en) | Method and system for judging defects of panel detection electronic signals | |
| CN106874837B (en) | Vehicle detection method based on video image processing | |
| CN114494200A (en) | Method and device for measuring trailer rotation angle | |
| CN114049394A (en) | Monocular distance measuring method, device, equipment and storage medium | |
| CN113538546B (en) | Target detection method, device and equipment for automatic driving | |
| CN113075709A (en) | Vehicle-mounted satellite navigation method and device, storage medium and processor | |
| CN113513985B (en) | Optimization method and device for precision detection, electronic equipment and medium | |
| CN115082899A (en) | Parking space detection method, device, equipment and storage medium | |
| CN113838149B (en) | Camera internal parameter calibration method, server and system for automatic driving vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |