Laser radar fusion algorithm detection method, device, equipment and readable storage medium

Abstract

The present invention provides a laser radar fusion algorithm detection method, device, equipment and readable storage medium. The laser radar fusion algorithm detection method includes: in a simulation test environment, obtaining the detection overlap area of ​​multiple laser radars; selecting the type of target to be detected from the identification range of the multiple laser radars; selecting the target under the type of target to be detected as the target to be detected; in the detection overlap area, traversing and detecting the target to be detected, outputting the statistical results of the recognition accuracy of the target to be detected by the fusion algorithm; summarizing the statistical results of the recognition accuracy of the target to be detected, and outputting a summary report of the recognition accuracy of the fusion algorithm. Through the present invention, the types of targets to be detected and targets are configured for radar products of different manufacturers, and efficient, comprehensive and automated detection of the fusion algorithm is achieved. The adaptability of the fusion algorithm can also be detected by detecting different types of targets.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving testing, and in particular to a laser radar fusion algorithm detection method, device, equipment and readable storage medium. Background Art

[0002] As an active sensor, LiDAR can actively sense objects and is less affected by the external environment. Its reliability and accuracy are higher than those of passive sensors. Therefore, it is widely used in the environmental perception system of intelligent driving vehicles. When using multiple LiDARs, it is necessary to identify the target through a fusion algorithm. The recognition accuracy of the LiDAR fusion algorithm directly affects the driving safety of intelligent driving vehicles. Therefore, it is very necessary to test the recognition accuracy and reliability of the LiDAR fusion algorithm. However, the current test scheme for the LiDAR fusion algorithm is to repeatedly test the LiDAR fusion algorithm to improve the accuracy of the test results. The process of a test is as follows: in the test scene, a static obstacle is placed, and a vehicle with intelligent driving function drives towards the obstacle. When the obstacle appears in the radar point cloud map and is displayed as an obstacle, the tester obtains and analyzes the results of the LiDAR fusion algorithm perception, verifies whether the LiDAR fusion algorithm accurately identifies the obstacle, and completes a test. This detection method for the LiDAR fusion algorithm undoubtedly has the problems of low efficiency and high cost. Summary of the invention

[0003] The main purpose of the present invention is to provide a laser radar fusion algorithm detection method, device, equipment and readable storage medium, aiming to solve the current technical problems of low efficiency and high cost in the detection of laser radar fusion algorithms.

[0004] In a first aspect, the present invention provides a laser radar fusion algorithm detection method, the laser radar fusion algorithm detection method comprising:

[0005] In a simulation test environment, obtain the detection overlap area of ​​multiple lidars;

[0006] Selecting a type of target object to be detected from the identification ranges of the multiple laser radars;

[0007] Selecting a target under the type of target to be detected as the target to be detected;

[0008] In the detection overlap area, traversal detection is performed on the target object to be detected, and the statistical result of the recognition accuracy rate of the target object to be detected by the fusion algorithm is output;

[0009] If all the targets of the target type to be detected have not been detected, a new target of the target type to be detected is selected as the target to be detected, and the step of performing traversal detection on the target to be detected in the detection overlap area is returned to output the statistical result of the recognition accuracy of the target to be detected by the fusion algorithm;

[0010] If all target types within the recognition range of the multiple laser radars have not been detected, a new target type is selected from the recognition range of the multiple laser radars as the target type to be detected, and the step of selecting the target under the target type to be detected as the target to be detected is returned to execute;

[0011] The statistical results of the recognition accuracy of the target object to be detected are summarized, and a summary report of the recognition accuracy of the fusion algorithm is output.

[0012] Optionally, the traversal detection of the target to be detected is performed in the detection overlap area, and the statistical result of the recognition accuracy of the target to be detected by the output fusion algorithm includes:

[0013] In the detection overlap area, setting a position to be detected of the target object to be detected;

[0014] Setting the detection angle of the target object to be detected;

[0015] Detecting the target object to be detected, and outputting the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm;

[0016] If the angle of the target object to be detected has not been detected, the angle of the target object to be detected is adjusted, and the adjusted angle is used as a new angle to be detected, and the step of detecting the target object to be detected and outputting the result of the recognition accuracy of the target object to be detected by the fusion algorithm is returned. If the angle of the target object to be detected has been detected, the target object to be detected is moved according to the traversal step length;

[0017] If the detection overlap area has not been completely detected, the position of the target object to be detected after the movement is used as a new position to be detected, and the process returns to the step of setting the angle to be detected of the target object to be detected;

[0018] The results of the recognition accuracy of each position and posture of the target object to be detected are counted, and the statistical results of the recognition accuracy of the target object to be detected by the fusion algorithm are output.

[0019] Optionally, setting a position to be detected of the target object to be detected in the detection overlapping area includes:

[0020] In the detection overlap region, the position of the target to be detected is set according to the width of the target to be detected and the width of the detection overlap region.

[0021] Optionally, the detecting the target object to be detected and outputting the result of the recognition accuracy of the target object to be detected by the fusion algorithm includes:

[0022] Through the simulation test environment, the first position information of the target object to be detected is obtained;

[0023] The second posture information of the target object to be detected is obtained through the fusion algorithm;

[0024] The first posture information and the second posture information are compared and calculated, and the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm is output.

[0025] Optionally, if the angle of the target object to be detected is not detected, the angle of the target object to be detected is adjusted, the adjusted angle is used as a new angle to be detected, and the step of detecting the target object to be detected and outputting the result of the fusion algorithm on the recognition accuracy of the target object to be detected is returned. If the angle of the target object to be detected is detected, before moving the target object to be detected according to the traversal step length, it also includes:

[0026] The traversal step length is set according to the width of the detection overlap area, the width of the target object to be detected, and the number of line groups of the multiple laser radars.

[0027] In a second aspect, the present invention further provides a laser radar fusion algorithm detection device, the laser radar fusion algorithm detection device comprising:

[0028] An acquisition module is used to acquire the detection overlap area of ​​multiple laser radars in a simulation test environment;

[0029] A first selection module, used to select the type of target object to be detected from the identification range of the multiple laser radars;

[0030] A second selection module is used to select a target under the type of target to be detected as the target to be detected;

[0031] A detection module, used to perform traversal detection on the target object to be detected in the detection overlap area, and output the statistical result of the recognition accuracy rate of the target object to be detected by the fusion algorithm;

[0032] A third selection module is used for selecting a new target under the type of target to be detected as the target to be detected if all targets under the type of target to be detected have not been detected, and returning to the step of performing traversal detection on the target to be detected in the detection overlap area, and outputting the statistical result of the recognition accuracy of the target to be detected by the fusion algorithm;

[0033] A fourth selection module, configured to select a new target type from the recognition range of the multiple laser radars as the target type to be detected if all target types in the recognition range of the multiple laser radars have not been detected, and return to execute the step of selecting the target under the target type to be detected as the target to be detected;

[0034] The output module is used to summarize the statistical results of the recognition accuracy of the target object to be detected and output a summary report of the recognition accuracy of the fusion algorithm.

[0035] Optionally, the detection module includes:

[0036] A first setting unit, used for setting a position to be detected of a target object to be detected in the detection overlap area;

[0037] A second setting unit is used to set a detection angle of the target object to be detected;

[0038] A detection unit, used to detect the target object to be detected and output the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm;

[0039] A third setting unit is used for adjusting the angle of the target object to be detected if the angle of the target object to be detected has not been detected, taking the adjusted angle as a new angle to be detected, and returning to execute the step of detecting the target object to be detected and outputting the result of the recognition accuracy of the target object to be detected by the fusion algorithm; if the angle of the target object to be detected has been detected, moving the target object to be detected according to the traversal step length;

[0040] A fourth setting unit is used to set the position of the target object to be detected after the movement as a new position to be detected if the detection overlap area has not been detected, and return to execute the step of setting the angle to be detected of the target object to be detected;

[0041] The output unit is used to collect statistics on the recognition accuracy of each position of the target object to be detected, and output the statistical results of the recognition accuracy of the target object to be detected by the fusion algorithm.

[0042] Optionally, the detection unit is used to:

[0043] Through the simulation test environment, the first position information of the target object to be detected is obtained;

[0044] The second posture information of the target object to be detected is obtained through the fusion algorithm;

[0045] The first posture information and the second posture information are compared and calculated, and the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm is output.

[0046] In a third aspect, the present invention also provides a laser radar fusion algorithm detection device, which includes a processor, a memory, and a laser radar fusion algorithm detection program stored in the memory and executable by the processor, wherein when the laser radar fusion algorithm detection program is executed by the processor, the steps of the laser radar fusion algorithm detection method described above are implemented.

[0047] In a fourth aspect, the present invention also provides a readable storage medium, on which a laser radar fusion algorithm detection program is stored, wherein when the laser radar fusion algorithm detection program is executed by a processor, the steps of the laser radar fusion algorithm detection method as described above are implemented.

[0048] In the present invention, in a simulation test environment, the detection overlapping area of ​​multiple laser radars is obtained; the type of target to be detected is selected from the identification range of the multiple laser radars; the target under the target type to be detected is selected as the target to be detected; in the detection overlapping area, the target to be detected is traversed and detected, and the statistical result of the recognition accuracy of the target to be detected by the fusion algorithm is output; if all the targets under the target type to be detected have not been detected, a new target under the target type to be detected is selected as the target to be detected, and the step of performing traversal detection on the target to be detected in the detection overlapping area and outputting the statistical result of the recognition accuracy of the target to be detected by the fusion algorithm is returned; if all the target types in the identification range of the multiple laser radars have not been detected, a new target type is selected from the identification range of the multiple laser radars as the target type to be detected, and the step of selecting the target under the target type to be detected as the target to be detected is returned; the statistical results of the recognition accuracy of the target to be detected are summarized, and a summary report of the recognition accuracy of the fusion algorithm is output. The present invention selects the type of target to be detected from the identification range of multiple laser radars in a simulation test environment, and then selects the target to be detected from the type of target to be detected, traverses and detects the target to be detected in the detection overlap area of ​​multiple laser radars, outputs the statistical results of the recognition accuracy of the target to be detected by the fusion algorithm of multiple laser radars, and then changes the target and then the type of target, until all the target types and targets under each target type in the identification range of multiple laser radars are detected, and finally the statistical results of the recognition accuracy of each target type and each target type in the identification range of multiple laser radars are summarized, and a summary report of the recognition accuracy of the fusion algorithm is output. Through the present invention, the types of target to be detected and the targets are configured in a targeted manner for different radar products of different manufacturers. According to the above-mentioned detection process of the fusion algorithm of multiple laser radars, the detection of the fusion algorithm of multiple laser radars can be realized in an efficient, comprehensive and automated manner, and the adaptability of the fusion algorithm can also be detected by detecting different types of targets. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic diagram of the hardware structure of an embodiment of a laser radar fusion algorithm detection device of the present invention;

[0050] Figure 2 A schematic diagram of a flow chart of an embodiment of a laser radar fusion algorithm detection method of the present invention;

[0051] Figure 3 A schematic diagram of the detection overlap area of ​​an embodiment of the laser radar fusion algorithm detection method of the present invention;

[0052] Figure 4 for Figure 2 A detailed flow chart of step S40;

[0053] Figure 5 This is a schematic diagram of the functional modules of an embodiment of a laser radar fusion algorithm detection device of the present invention.

[0054] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0056] In a first aspect, an embodiment of the present invention provides a laser radar fusion algorithm detection device.

[0057] Reference Figure 1 , Figure 1 The hardware structure diagram of an embodiment of the laser radar fusion algorithm detection device of the present invention. In the embodiment of the present invention, the laser radar fusion algorithm detection device may include a processor 1001 (such as a central processing unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components; the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a wireless interface (such as wireless fidelity WIreless-FIdelity, WI-FI interface); the memory 1005 may be a high-speed random access memory (random access memory, RAM), or a stable memory (non-volatile memory), such as a disk storage, and the memory 1005 may optionally be a storage device independent of the aforementioned processor 1001. Those skilled in the art will understand that Figure 1 The hardware structure shown in the figure does not constitute a limitation of the present invention, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0058] Continue to refer to Figure 1 , Figure 1 The memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a laser radar fusion algorithm detection program. The processor 1001 may call the laser radar fusion algorithm detection program stored in the memory 1005 and execute the laser radar fusion algorithm detection method provided in the embodiment of the present invention.

[0059] In a second aspect, an embodiment of the present invention provides a laser radar fusion algorithm detection method.

[0060] In order to more clearly demonstrate the laser radar fusion algorithm detection method provided in the embodiment of the present application, the application scenario of the laser radar fusion algorithm detection method provided in the embodiment of the present application is first introduced.

[0061] The laser radar fusion algorithm detection method provided in the embodiment of the present application is applied in an intelligent driving vehicle using multiple laser radars, and the target is identified through the fusion algorithm. The recognition accuracy of the laser radar fusion algorithm directly affects the driving safety of the intelligent driving vehicle, so the recognition accuracy and reliability of the laser radar fusion algorithm are tested.

[0062] In one embodiment, referring to Figure 2 , Figure 2 FIG. 1 is a flow chart of an embodiment of a laser radar fusion algorithm detection method according to the present invention. Figure 2 As shown, the laser radar fusion algorithm detection method includes:

[0063] Step S10: obtaining overlapping detection areas of multiple laser radars in a simulation test environment.

[0064] In this embodiment, the installation postures of multiple virtual laser radars in the simulation environment can be configured according to the postures of multiple laser radars installed in real vehicles in the real environment. In order to test the fusion algorithm of multiple laser radars, the configured multiple laser radars need to have overlapping detection areas. In the simulation environment, the location and area of ​​the overlapping detection area are obtained through the system function of the simulation environment. There can be two or more laser radars, refer to Figure 3 , Figure 3 FIG. 1 is a schematic diagram of the detection overlap area of ​​an embodiment of the laser radar fusion algorithm detection method of the present invention. Figure 3 As shown, the detection overlap area of ​​LiDAR A and LiDAR B is represented by the shaded part in FIG3 .

[0065] Step S20, selecting the type of target object to be detected from the identification ranges of the multiple laser radars.

[0066] In this embodiment, different models of laser radar products manufactured by different manufacturers have different target types that they are good at identifying and the corresponding accuracy. For example, the identification range of laser radar A is vehicles and pedestrians, and the identification range of laser radar B is vehicles and traffic signs. Targeted configuration is performed according to the product model of the laser radar, and the type of target to be detected is selected from the identification ranges of multiple laser radars.

[0067] Step S30: selecting a target under the type of target to be detected as the target to be detected.

[0068] In this embodiment, the target objects to be detected are selected from the types of target objects to be detected. For example, typical targets under the type of target object to be detected "vehicle" may include a car, a bus, a tractor, etc. The number of typical targets can be adjusted according to actual test needs.

[0069] Step S40, performing traversal detection on the target object to be detected in the detection overlapping area, and outputting the statistical result of the recognition accuracy rate of the target object to be detected by the fusion algorithm.

[0070] In this embodiment, according to the positions and areas of the detection areas of multiple laser radars, the target object to be detected is traversed and detected in the entire detection area, and after the detection, the statistical results of the recognition accuracy of the target object to be detected by the fusion algorithm are output.

[0071] Step S50, if all the targets under the type of target to be detected have not been detected, a new target under the type of target to be detected is selected as the target to be detected, and the process returns to the step of traversing and detecting the targets to be detected in the detection overlapping area, and outputting the statistical results of the recognition accuracy of the target to be detected by the fusion algorithm.

[0072] In this embodiment, if all the targets of the target type to be detected have not been detected, a new target is selected as the target to be detected, and the process returns to step S40, that is, the detection of the new target to be detected continues.

[0073] Step S60, if all target types within the recognition range of the multiple laser radars have not been detected, a new target type is selected from the recognition range of the multiple laser radars as the target type to be detected, and the step of selecting the target under the target type to be detected as the target to be detected is returned to execute.

[0074] In this embodiment, if all target types within the identification range of multiple laser radars have not been detected, a new target type is selected as the target type to be detected, and the process returns to step S30, and then the target to be detected is selected from the new target type to continue detection.

[0075] Step S70, summarizing the statistical results of the recognition accuracy of the target to be detected, and outputting a summary report of the recognition accuracy of the fusion algorithm.

[0076] In this embodiment, in each of the above steps, based on each target type within the identification range of multiple laser radars and the typical targets under each target type, the fusion algorithms of multiple laser radars are tested respectively, the statistical results of the above recognition accuracy are summarized, and a summary report of the fusion algorithm recognition accuracy is output to complete the entire detection process.

[0077] In this embodiment, in a simulation environment, the types of targets to be detected and typical targets to be detected are configured specifically for different radar products from different manufacturers. Each target type and typical targets under each target type are detected in turn in the overlapping detection area of ​​multiple lidars. After the detection results are summarized, a summary report on the recognition accuracy of the fusion algorithm is output. The entire detection process has obvious advantages of high efficiency, comprehensiveness and automation, which can significantly reduce the detection cost of the lidar fusion algorithm. The adaptability of the lidar fusion algorithm can also be tested by detecting different types of targets. The comprehensive detection report output makes it convenient for fusion algorithm designers to improve and upgrade the fusion algorithm based on the report results, thereby further improving the recognition accuracy and reliability of the lidar fusion algorithm.

[0078] Further, in one embodiment, referring to Figure 4 , Figure 4 for Figure 2 The detailed flow chart of step S40 is as follows: Figure 4 As shown, step S40 includes:

[0079] Step S401, setting a position to be detected of a target object to be detected in the detection overlap area.

[0080] In this embodiment, within the detection overlap area, a detection position is set for the target object to be detected.

[0081] Step S402, setting the detection angle of the target object to be detected.

[0082] In this embodiment, a detection angle is set for the target object to be detected.

[0083] Step S403 , detecting the target object to be detected, and outputting the result of the recognition accuracy of the target object to be detected by the fusion algorithm.

[0084] In this embodiment, after the target object to be detected is detected, the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm is output.

[0085] Step S404, if the angle of the target object to be detected has not been detected, the angle of the target object to be detected is adjusted, and the adjusted angle is used as the new angle to be detected, and the step of returning to execute the detection of the target object to be detected and outputting the result of the fusion algorithm's recognition accuracy of the target object to be detected is returned. If the angle of the target object to be detected has been detected, the target object to be detected is moved according to the traversal step length.

[0086] In this embodiment, the angle of the target object to be detected includes a roll angle, a pitch angle and a heading angle. The detection angle can be selected according to specific detection requirements. For example, at a certain position to be detected, the heading angle of the target object to be detected can be adjusted and detected at 0 degrees, 30 degrees, 60 degrees, 90 degrees, 120 degrees, 150 degrees and 180 degrees in sequence. If the above angles are not detected, the detection will be continued after adjusting the angles at the position to be detected. If the above angles are detected, the target object to be detected will be moved to a new position to be detected according to the traversal step.

[0087] Step S405, if the detection overlap area has not been completely detected, the position of the target object to be detected after the movement is used as a new position to be detected, and the process returns to the step of setting the detection angle of the target object to be detected.

[0088] In this embodiment, at the new position of the target object to be detected, various angles are continuously adjusted for detection until the entire detection overlap area is detected.

[0089] Step S406, statistically analyzing the recognition accuracy of each position of the target object to be detected, and outputting the statistical result of the recognition accuracy of the target object to be detected by the fusion algorithm.

[0090] In this embodiment, after obtaining the recognition accuracy results of the fusion algorithm for the target object to be detected at each position and each angle in the detection overlap area, statistics are performed, and then the statistical results of the recognition accuracy results of the fusion algorithm for the target object to be detected are output.

[0091] Furthermore, in one embodiment, step S401 includes:

[0092] In the detection overlap region, the position of the target to be detected is set according to the width of the target to be detected and the width of the detection overlap region.

[0093] In this embodiment, since the target to be detected has a width dimension, in the detection overlap area, a suitable detection position is set for the target to be detected according to the width of the target to be detected and the width of the detection overlap area, which can improve the efficiency of traversal detection.

[0094] Furthermore, in one embodiment, step S403 includes:

[0095] Through the simulation test environment, the first position information of the target object to be detected is obtained;

[0096] The second posture information of the target object to be detected is obtained through the fusion algorithm;

[0097] The first posture information and the second posture information are compared and calculated, and the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm is output.

[0098] In this embodiment, the first pose information of the target object to be detected is obtained through a simulated test environment, which is usually referred to as the "true value". The second pose information of the target object to be detected is obtained through a fusion algorithm of multiple laser radars, which can be called the "fusion value". According to the designer of the fusion algorithm's requirements for the accuracy of the fusion algorithm and the method of calculating the accuracy rate, the "true value" and the "fusion value" are compared and calculated to obtain the result of the fusion algorithm's recognition accuracy of the target object to be detected.

[0099] Furthermore, in one embodiment, before step S404, the method further includes:

[0100] The traversal step length is set according to the width of the detection overlap area, the width of the target object to be detected, and the number of line groups of the multiple laser radars.

[0101] In this embodiment, the wider the width of the detection overlapping area, the larger the traversal step length can be set; the wider the width of the target object to be detected, the smaller the traversal step length can be set; the larger the number of line groups of multiple laser radars, the larger the traversal step length can be set. The traversal step length can be set according to specific test requirements to better improve the efficiency of traversal detection.

[0102] In a third aspect, an embodiment of the present invention also provides a laser radar fusion algorithm detection device.

[0103] Reference Figure 5 , Figure 5 This is a schematic diagram of the functional modules of an embodiment of a laser radar fusion algorithm detection device of the present invention.

[0104] In this embodiment, the laser radar fusion algorithm detection device includes:

[0105] An acquisition module 10 is used to acquire the detection overlap area of ​​multiple laser radars in a simulation test environment;

[0106] A first selection module 20, configured to select a type of target object to be detected from the identification ranges of the plurality of laser radars;

[0107] A second selection module 30 is used to select a target under the type of target to be detected as the target to be detected;

[0108] A detection module 40 is used to perform traversal detection on the target object to be detected in the detection overlap area, and output a statistical result of the recognition accuracy of the target object to be detected by the fusion algorithm;

[0109] A third selection module 50 is used for selecting a new target of the type of target to be detected as the target to be detected if all targets of the type of target to be detected have not been detected, and returning to the step of performing traversal detection on the target to be detected in the detection overlap area, and outputting the statistical result of the recognition accuracy of the target to be detected by the fusion algorithm;

[0110] A fourth selection module 60 is used for selecting a new target type from the recognition range of the multiple laser radars as the target type to be detected if all target types in the recognition range of the multiple laser radars have not been detected, and returning to execute the step of selecting the target under the target type to be detected as the target to be detected;

[0111] The output module 70 is used to summarize the statistical results of the recognition accuracy of the target object to be detected and output a summary report of the recognition accuracy of the fusion algorithm.

[0112] Furthermore, in one embodiment, the detection module 40 includes:

[0113] A first setting unit, used for setting a position to be detected of a target object to be detected in the detection overlap area;

[0114] A second setting unit is used to set a detection angle of the target object to be detected;

[0115] A detection unit, used to detect the target object to be detected and output the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm;

[0116] A third setting unit is used for adjusting the angle of the target object to be detected if the angle of the target object to be detected has not been detected, taking the adjusted angle as a new angle to be detected, and returning to execute the step of detecting the target object to be detected and outputting the result of the recognition accuracy of the target object to be detected by the fusion algorithm; if the angle of the target object to be detected has been detected, moving the target object to be detected according to the traversal step length;

[0117] A fourth setting unit is used to set the position of the target object to be detected after the movement as a new position to be detected if the detection overlap area has not been detected, and return to execute the step of setting the angle to be detected of the target object to be detected;

[0118] The output unit is used to collect statistics on the recognition accuracy of each position of the target object to be detected, and output the statistical results of the recognition accuracy of the target object to be detected by the fusion algorithm.

[0119] Furthermore, in one embodiment, the first setting unit is used to:

[0120] In the detection overlap region, the position of the target to be detected is set according to the width of the target to be detected and the width of the detection overlap region.

[0121] Furthermore, in one embodiment, the detection unit is used to:

[0122] Through the simulation test environment, the first position information of the target object to be detected is obtained;

[0123] The second posture information of the target object to be detected is obtained through the fusion algorithm;

[0124] The first posture information and the second posture information are compared and calculated, and the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm is output.

[0125] Furthermore, in one embodiment, the detection module 40 further includes a fifth setting unit, which is used to:

[0126] The traversal step length is set according to the width of the detection overlap area, the width of the target object to be detected, and the number of line groups of the multiple laser radars.

[0127] Among them, the functional implementation of each module in the above-mentioned laser radar fusion algorithm detection device corresponds to the various steps in the above-mentioned laser radar fusion algorithm detection method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0128] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium.

[0129] The readable storage medium of the present invention stores a laser radar fusion algorithm detection program, wherein when the laser radar fusion algorithm detection program is executed by a processor, the steps of the laser radar fusion algorithm detection method as described above are implemented.

[0130] Among them, the method implemented when the laser radar fusion algorithm detection program is executed can refer to the various embodiments of the laser radar fusion algorithm detection method of the present invention, and will not be repeated here.

[0131] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0132] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0133] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present invention.

[0134] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A laser radar fusion algorithm detection method, characterized in that: The laser radar fusion algorithm detection method comprises: In a simulation test environment, obtain the detection overlap area of ​​multiple lidars; Selecting a type of target object to be detected from the identification ranges of the multiple laser radars; Selecting a target under the type of target to be detected as the target to be detected; In the detection overlap area, traversal detection is performed on the target object to be detected, and the statistical result of the recognition accuracy rate of the target object to be detected by the fusion algorithm is output; If all the targets of the target type to be detected have not been detected, a new target of the target type to be detected is selected as the target to be detected, and the step of performing traversal detection on the target to be detected in the detection overlap area is returned to output the statistical result of the recognition accuracy of the target to be detected by the fusion algorithm; If all target types within the recognition range of the multiple laser radars have not been detected, a new target type is selected from the recognition range of the multiple laser radars as the target type to be detected, and the step of selecting the target under the target type to be detected as the target to be detected is returned to execute; The statistical results of the recognition accuracy of the target object to be detected are summarized, and a summary report of the recognition accuracy of the fusion algorithm is output.

2. The laser radar fusion algorithm detection method according to claim 1, characterized in that: The traversal detection of the target to be detected in the detection overlap area and the output of the statistical results of the recognition accuracy of the target to be detected by the fusion algorithm include: In the detection overlap area, setting a position to be detected of the target object to be detected; Setting the detection angle of the target object to be detected; Detecting the target object to be detected, and outputting the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm; If the angle of the target object to be detected has not been detected, the angle of the target object to be detected is adjusted, and the adjusted angle is used as a new angle to be detected, and the step of detecting the target object to be detected and outputting the result of the recognition accuracy of the target object to be detected by the fusion algorithm is returned. If the angle of the target object to be detected has been detected, the target object to be detected is moved according to the traversal step length; If the detection overlap area has not been completely detected, the position of the target object to be detected after the movement is used as a new position to be detected, and the process returns to the step of setting the angle to be detected of the target object to be detected; The results of the recognition accuracy of each position and posture of the target object to be detected are counted, and the statistical results of the recognition accuracy of the target object to be detected by the fusion algorithm are output.

3. The laser radar fusion algorithm detection method according to claim 2, characterized in that: The step of setting the position of the target object to be detected in the detection overlapping area includes: In the detection overlap region, the position of the target to be detected is set according to the width of the target to be detected and the width of the detection overlap region.

4. The laser radar fusion algorithm detection method according to claim 2, characterized in that: The detecting of the target object to be detected and outputting the result of the recognition accuracy of the target object to be detected by the fusion algorithm include: Through the simulation test environment, the first position information of the target object to be detected is obtained; The second posture information of the target object to be detected is obtained through the fusion algorithm; The first posture information and the second posture information are compared and calculated, and the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm is output.

5. The laser radar fusion algorithm detection method according to claim 2, characterized in that: If the angle of the target object to be detected is not detected, the angle of the target object to be detected is adjusted, the adjusted angle is used as a new angle to be detected, and the step of returning to execute the detection of the target object to be detected and outputting the result of the recognition accuracy of the target object to be detected by the fusion algorithm is returned. If the angle of the target object to be detected is detected, before moving the target object to be detected according to the traversal step length, it also includes: The traversal step length is set according to the width of the detection overlap area, the width of the target object to be detected, and the number of line groups of the multiple laser radars.

6. A laser radar fusion algorithm detection device, characterized in that: The laser radar fusion algorithm detection device comprises: An acquisition module is used to acquire the detection overlap area of ​​multiple laser radars in a simulation test environment; A first selection module, used to select the type of target object to be detected from the identification range of the multiple laser radars; A second selection module is used to select a target under the type of target to be detected as the target to be detected; A detection module, used to perform traversal detection on the target object to be detected in the detection overlap area, and output the statistical result of the recognition accuracy rate of the target object to be detected by the fusion algorithm; A third selection module is used for selecting a new target under the type of target to be detected as the target to be detected if all targets under the type of target to be detected have not been detected, and returning to the step of performing traversal detection on the target to be detected in the detection overlap area, and outputting the statistical result of the recognition accuracy of the target to be detected by the fusion algorithm; A fourth selection module, configured to select a new target type from the recognition range of the multiple laser radars as the target type to be detected if all target types in the recognition range of the multiple laser radars have not been detected, and return to execute the step of selecting the target under the target type to be detected as the target to be detected; The output module is used to summarize the statistical results of the recognition accuracy of the target object to be detected and output a summary report of the recognition accuracy of the fusion algorithm.

7. The laser radar fusion algorithm detection device according to claim 6, characterized in that: The detection module comprises: A first setting unit, used for setting a position to be detected of a target object to be detected in the detection overlap area; A second setting unit is used to set a detection angle of the target object to be detected; A detection unit, used to detect the target object to be detected and output the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm; A third setting unit is used for adjusting the angle of the target object to be detected if the angle of the target object to be detected has not been detected, taking the adjusted angle as a new angle to be detected, and returning to execute the step of detecting the target object to be detected and outputting the result of the recognition accuracy of the target object to be detected by the fusion algorithm; if the angle of the target object to be detected has been detected, moving the target object to be detected according to the traversal step length; A fourth setting unit is used to set the position of the target object to be detected after the movement as a new position to be detected if the detection overlap area has not been detected, and return to execute the step of setting the angle to be detected of the target object to be detected; The output unit is used to collect statistics on the recognition accuracy of each position of the target object to be detected, and output the statistical results of the recognition accuracy of the target object to be detected by the fusion algorithm.

8. The laser radar fusion algorithm detection device according to claim 7, characterized in that: The detection unit is used for: Through the simulation test environment, the first position information of the target object to be detected is obtained; The second posture information of the target object to be detected is obtained through the fusion algorithm; The first posture information and the second posture information are compared and calculated, and the result of the recognition accuracy rate of the target object to be detected by the fusion algorithm is output.

9. A laser radar fusion algorithm detection device, characterized in that: The laser radar fusion algorithm detection device includes a processor, a memory, and a laser radar fusion algorithm detection program stored in the memory and executable by the processor, wherein when the laser radar fusion algorithm detection program is executed by the processor, the steps of the laser radar fusion algorithm detection method as described in any one of claims 1 to 5 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a laser radar fusion algorithm detection program, wherein when the laser radar fusion algorithm detection program is executed by the processor, the steps of the laser radar fusion algorithm detection method as described in any one of claims 1 to 5 are implemented.

Images