A blind area detection accuracy determination method of a BSD system and related devices

Abstract

The application discloses a blind area detection accuracy determination method of a BSD system and related equipment. The method comprises the following steps: acquiring BSD blind area monitoring information of a target vehicle, wherein the BSD blind area monitoring information is acquired by a BSD system of the target vehicle; acquiring binocular camera blind area test results of the target vehicle, wherein the binocular camera blind area test results are acquired by testers through a binocular camera pre-installed on the target vehicle; and determining the blind area detection accuracy of the BSD system based on the BSD blind area monitoring information and the binocular camera blind area test results. The BSD system blind area detection accuracy determination method provided in the application embodiment can achieve the purposes of automatic judgment and automatic testing, improves the test efficiency, and changes the current subjective evaluation of the whole vehicle BSD performance related road test into objective testing, so that the accuracy of the test results is greatly improved.

Description

Technical Field

[0001] This specification relates to the field of intelligent vehicles, and more specifically, to a method and related equipment for determining the accuracy of blind spot detection in a BSD system. Background Technology

[0002] The "Blind Spot Detection" (BSD) function uses onboard side radar to detect whether a target vehicle is approaching from behind in an adjacent lane or whether a vehicle is in the blind spot of the rearview mirror. When there is a vehicle in the blind spot or a vehicle to the side or rear that poses a collision risk to the vehicle, the BSD monitoring system will alert the driver through lights and sounds to indicate the risk of changing lanes. However, when testing key performance indicators such as BSD-related performance and false alarm rate on public roads, it is impossible to accurately conduct BSD public road tests based on actual road conditions and parameter design because it is difficult to obtain relevant BSD parameters such as the speed, distance, or position of other vehicles on public roads. Currently, BSD public road tests can only rely on subjective human judgment and comparison or simulated BSD public road tests with two vehicles in a test area. This testing method has a limited testing scenario, insufficient coverage, low efficiency of manual judgment and comparison, and low reliability of test output results. Summary of the Invention

[0003] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. The summary section of this invention is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0004] In a first aspect, the present invention proposes a method for determining the accuracy of blind zone detection in a BSD system, the method comprising:

[0005] Obtain the BSD blind spot monitoring information of the target vehicle, wherein the BSD blind spot monitoring information is obtained through the BSD system of the target vehicle;

[0006] Obtain the blind spot test results of the binocular camera of the target vehicle, wherein the binocular camera blind spot test results are obtained by the tester through a binocular camera pre-installed on the target vehicle;

[0007] The blind spot detection accuracy of the BSD system is determined based on the above BSD blind spot monitoring information and the above binocular camera blind spot test results.

[0008] Optionally, the above-mentioned acquisition of the binocular camera blind spot test results of the target vehicle includes:

[0009] Environmental image information is acquired based on the aforementioned binocular camera;

[0010] The above environmental image information is identified using an intelligent recognition algorithm to obtain the blind spot test results of the binocular camera.

[0011] Optionally, the aforementioned BSD blind spot monitoring information includes BSD blind spot collision warning information and BSD lane change warning information, and the aforementioned binocular camera blind spot test results include blind spot collision test results and blind spot lane change test results;

[0012] The above determination of the blind spot detection accuracy of the BSD system based on the aforementioned BSD blind spot monitoring information and the aforementioned binocular camera blind spot test results includes:

[0013] The collision detection accuracy is determined based on the above BSD blind spot collision warning information and the above blind spot collision test results;

[0014] The accuracy of lane change detection was determined by the above BSD lane change warning information and the above blind spot lane change test results;

[0015] The accuracy of blind spot detection is determined based on the above-mentioned collision detection accuracy and lane change detection accuracy.

[0016] Optionally, the above-mentioned BSD blind spot collision warning information includes BSD blind spot collision boundary information and BSD blind spot collision warning duration information, and the above-mentioned blind spot collision test results include blind spot collision boundary test results and blind spot collision warning duration test results;

[0017] The above determination of collision detection accuracy based on the aforementioned BSD blind spot collision warning information and the aforementioned blind spot collision test results includes:

[0018] The boundary overlap is obtained based on the above BSD blind zone collision boundary information and the above blind zone collision boundary test results.

[0019] The time overlap is obtained by using the above BSD blind spot collision warning duration information and blind spot collision warning duration test results;

[0020] The collision detection accuracy is determined based on the aforementioned boundary overlap and time overlap.

[0021] Optionally, the aforementioned BSD lane change warning information includes BSD TTC boundary information and lane change warning time information, and the aforementioned blind spot lane change test results include TTC boundary test results and lane change warning time test results.

[0022] The accuracy of lane change detection is determined using the aforementioned BSD lane change warning information and the aforementioned blind spot lane change test results, including:

[0023] The TTC boundary overlap is determined based on the aforementioned BSD TTC boundary information and TTC boundary test results.

[0024] The overlap of lane change warning times is obtained by combining the above lane change warning time information with the above lane change warning time test results.

[0025] The test results for the lane change warning time were obtained based on the TTC boundary overlap and the lane change warning time overlap.

[0026] Optionally, determining the blind spot detection accuracy based on the collision detection accuracy and lane change detection accuracy includes:

[0027] The above-mentioned blind spot detection accuracy is determined based on the above-mentioned collision detection accuracy, the above-mentioned lane change detection accuracy, the collision detection weight coefficient, and the lane change detection weight coefficient, wherein the above-mentioned collision detection weight coefficient is greater than the above-mentioned lane change detection weight coefficient.

[0028] Optionally, the above-mentioned BSD blind spot monitoring information includes curve BSD blind spot monitoring information and straight road BSD blind spot monitoring information, and the above-mentioned binocular camera blind spot test results include curve binocular camera blind spot test results and straight road binocular camera blind spot test results;

[0029] The above determination of the blind spot detection accuracy of the BSD system based on the aforementioned BSD blind spot monitoring information and the aforementioned binocular camera blind spot test results includes:

[0030] The accuracy of blind spot detection on curves is obtained by using the above-mentioned curve BSD blind spot monitoring information and the above-mentioned curve binocular camera blind spot test results.

[0031] The accuracy of blind spot detection on straight roads was determined by the above-mentioned BSD blind spot monitoring information and the above-mentioned blind spot test results of the binocular camera on straight roads.

[0032] The accuracy of blind spot detection is determined by the above-mentioned accuracy of blind spot detection on curves, the above-mentioned accuracy of blind spot detection on straight roads, the curve detection weight coefficient, and the straight road detection weight coefficient, wherein the above-mentioned curve detection weight coefficient is greater than the above-mentioned straight road detection weight coefficient.

[0033] Secondly, the present invention also proposes a device for determining the accuracy of blind zone detection in a BSD system, comprising:

[0034] The first acquisition unit is used to acquire the BSD blind spot monitoring information of the target vehicle, wherein the BSD blind spot monitoring information is acquired through the BSD system of the target vehicle.

[0035] The second acquisition unit is used to acquire the binocular camera blind spot test results of the target vehicle, wherein the binocular camera blind spot test results are acquired by the tester through a binocular camera pre-installed on the target vehicle.

[0036] The determination unit is used to determine the blind spot detection accuracy of the BSD system based on the above-mentioned BSD blind spot monitoring information and the above-mentioned binocular camera blind spot test results.

[0037] Thirdly, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the blind zone detection accuracy determination method for a BSD system as described in any of the first aspects above.

[0038] Fourthly, the present invention also proposes a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the method for determining the accuracy of blind zone detection in a BSD system according to any one of the preceding claims of the first aspect.

[0039] In summary, the method for determining the blind spot detection accuracy of the BSD system according to the embodiments of this application includes: acquiring BSD blind spot monitoring information of the target vehicle, wherein the BSD blind spot monitoring information is acquired through the BSD system of the target vehicle; acquiring the binocular camera blind spot test results of the target vehicle, wherein the binocular camera blind spot test results are acquired by a tester through a binocular camera pre-installed on the target vehicle; and determining the blind spot detection accuracy of the BSD system based on the BSD blind spot monitoring information and the binocular camera blind spot test results. The method for determining the blind spot detection accuracy of the BSD system provided in the embodiments of this application, by installing binocular cameras around the target vehicle to collect driving image information of the vehicle, and calculating the binocular camera blind spot test results based on the driving images, uses these results as a standard reference. By comparing the BSD blind spot detection information and the binocular camera blind spot test results, the accuracy of the BSD system's blind spot detection is determined. This achieves the purpose of automatic judgment and automatic testing, improves testing efficiency, and changes the current subjective evaluation of vehicle BSD performance-related road testing to objective testing, greatly improving the accuracy of test results. This system automates the statistical testing of vehicle BSD (Browser Detection and Slow Error) false alarm rates, replacing manual judgment with automated system analysis, significantly improving testing efficiency and accuracy. Furthermore, it allows BSD performance testing to move from multi-vehicle simulation testing on a test track to real-world road testing, greatly enriching the testing scenarios and facilitating the discovery and resolution of defects, thus enhancing the user experience.

[0040] The method for determining the accuracy of blind zone detection in a BSD system. Other advantages, objectives and features of the present invention will be apparent in part from the following description, and in part from what those skilled in the art will understand through study and practice of the invention. Attached Figure Description

[0041] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0042] Figure 1 This application provides a schematic flowchart of a method for determining the accuracy of blind zone detection in a BSD system.

[0043] Figure 2 A schematic diagram of an alarm zone provided in an embodiment of this application;

[0044] Figure 3 A schematic diagram of a testing system provided in an embodiment of this application;

[0045] Figure 4 This application provides a schematic flowchart of a method for determining the accuracy of blind zone detection in a BSD system.

[0046] Figure 5 A schematic diagram of a device for determining the accuracy of blind zone detection in a BSD system provided in an embodiment of this application;

[0047] Figure 6 This is a schematic diagram of an electronic device structure for determining the blind zone detection accuracy of a BSD system, provided in an embodiment of this application. Detailed Implementation

[0048] The blind spot detection accuracy determination method for the BSD system provided in this application embodiment acquires vehicle driving image information by installing binocular cameras around the target vehicle, and calculates the binocular camera blind spot test results based on the driving images. This result serves as a standard reference. By comparing the BSD blind spot detection information with the binocular camera blind spot test results, the accuracy of the BSD system's blind spot detection is determined. This achieves automatic judgment and automatic testing, improving testing efficiency and transforming the current subjective evaluation of vehicle BSD performance-related road testing into objective testing, significantly improving the accuracy of test results. It also transforms the current manual judgment and statistics of vehicle BSD false alarm rates into automatic system judgment and statistics, greatly improving testing efficiency and accuracy. Furthermore, it allows vehicle BSD performance-related testing to move from multi-vehicle simulation testing in a test track to real-vehicle road testing, greatly enriching and diversifying test scenarios, which is beneficial for discovering and resolving defects and other problems, and improving user experience.

[0049] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The technical solutions of the embodiments of this application will now be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0050] Please see Figure 1 This is a flowchart illustrating a method for determining the accuracy of blind zone detection in a BSD system, provided in an embodiment of this application. Specifically, it may include:

[0051] S110. Obtain the BSD blind spot monitoring information of the target vehicle, wherein the BSD blind spot monitoring information is obtained through the BSD system of the target vehicle.

[0052] For example, BSD (Blind Spot Vehicle Discern System) is a system that uses onboard side radar to detect whether a target vehicle is approaching from behind in an adjacent lane or whether a vehicle is in the blind spot of the rearview mirror. When there is a vehicle in the blind spot or a vehicle to the side or rear that poses a collision risk to the vehicle, the blind spot monitoring system will alert the driver through lights, sounds, etc., to the risk of changing lanes. Before a vehicle leaves the factory, the accuracy of the BSD system needs to be evaluated. Currently, the method usually involves comparing the judgment of the testing personnel with the judgment result of the BSD system to determine the accuracy of the blind spot detection. This method not only wastes manpower and resources, but also cannot meet the needs of timely testing when mass-producing vehicles.

[0053] This application first obtains blind spot detection information based on the BSD system and collects it into a relevant memory or computer device. Blind spot detection information of the vehicle can be obtained through relevant CAN information.

[0054] S120. Obtain the blind spot test results of the binocular camera of the target vehicle, wherein the binocular camera blind spot test results are obtained by the tester through a binocular camera pre-installed on the target vehicle.

[0055] For example, binocular cameras are installed around the target vehicle to continuously acquire images of other vehicles in the vicinity while the vehicle is moving. The depth of field of environmental vehicle feature points is calculated based on the stereo matching results of each frame, thereby determining the binocular camera blind spot test results. This allows the determination of the relative positions and speeds of the surrounding vehicles. Based on the ground truth information such as the positions and speeds of the surrounding vehicles obtained from the binocular camera test, the lateral and longitudinal relative positions and TTC (Time to Collision) are calculated.

[0056] S130. Determine the blind spot detection accuracy of the BSD system based on the above BSD blind spot monitoring information and the above binocular camera blind spot test results.

[0057] For example, the blind spot detection accuracy of the BSD system is determined by comparing BSD blind spot monitoring information with binocular camera blind spot tests. The information compared includes at least one of the following: lateral boundary distance between the two vehicles, longitudinal boundary distance between the two vehicles, and TTC (Time to Collision). The proposed solution objectively judges whether the BSD performance of the test vehicle is qualified from the BSD logic parameter design level. The relative information calculated from the basic truth value collected by the binocular camera is used as a standard reference and compared with the CAN information output results related to the BSD of the test vehicle, and automatic judgment is performed to ultimately achieve the purpose of automatic testing. It should be noted that BSD performance failures can be defined as: no alarm in the blind spot alarm area (including boundary point and duration not conforming to design parameters); no alarm in the lane change alarm area (including TTC boundary and duration not conforming to design parameters); BSD missed alarm (including complete missed alarm and missed alarm with unreasonable duration).

[0058] In summary, the blind spot detection accuracy determination method for the BSD system provided in this application embodiment acquires vehicle driving image information by installing binocular cameras around the target vehicle, calculates the binocular camera blind spot test results based on the driving images, and uses this as a standard reference. By comparing the BSD blind spot detection information with the binocular camera blind spot test results, the accuracy of the BSD system's blind spot detection is determined. This achieves automatic judgment and automatic testing, improving testing efficiency and transforming the current subjective evaluation of vehicle BSD performance-related road testing into objective testing, greatly improving the accuracy of test results. It also transforms the current manual judgment and statistics of vehicle BSD false alarm rates and other related statistical tests into automatic system judgment and statistics, greatly improving testing efficiency and accuracy. Simultaneously, it allows vehicle BSD performance-related testing to move from multi-vehicle simulation testing in a test track to real-vehicle road testing, greatly enriching and diversifying test scenarios, which is beneficial for discovering and resolving defects and other problems, and improving user experience.

[0059] In some examples, the above-mentioned acquisition of the blind spot test results of the binocular camera of the target vehicle includes:

[0060] Environmental image information is acquired based on the aforementioned binocular camera;

[0061] The above environmental image information is identified using an intelligent recognition algorithm to obtain the blind spot test results of the binocular camera.

[0062] For example, while binocular cameras can acquire richer and more comprehensive information about the vehicle's surroundings, enabling them to effectively identify objects in blind spots, their application in BSD (Blind Spot Detection) systems is limited by cost and adverse weather conditions. The method proposed in this application uses the blind spot test results obtained from binocular cameras as a standard value to correct and verify the blind spot detection accuracy of radar-based BSD systems. The acquired environmental image information is first downsampled, and then objects within the blind spot are identified using intelligent recognition algorithms such as deep learning, thereby obtaining binocular camera blind spot test results for different scenarios.

[0063] In summary, the method for determining the accuracy of blind spot detection in the BSD system provided in this application is more objective and accurate because it uses environmental image information acquired by a binocular camera and the binocular camera blind spot test results obtained by an intelligent recognition algorithm as a standard value for evaluating the comparison of BSD blind spot monitoring information.

[0064] In some examples, the aforementioned BSD blind spot monitoring information includes BSD blind spot collision warning information and BSD lane change warning information, and the aforementioned binocular camera blind spot test results include blind spot collision test results and blind spot lane change test results;

[0065] The above determination of the blind spot detection accuracy of the BSD system based on the aforementioned BSD blind spot monitoring information and the aforementioned binocular camera blind spot test results includes:

[0066] The collision detection accuracy is determined based on the above BSD blind spot collision warning information and the above blind spot collision test results;

[0067] The accuracy of lane change detection was determined by the above BSD lane change warning information and the above blind spot lane change test results;

[0068] The accuracy of blind spot detection is determined based on the above-mentioned collision detection accuracy and lane change detection accuracy.

[0069] For example, such as Figure 2As shown, blind spot monitoring is divided into blind spot alarm areas and lane change alarm areas. Correspondingly, BSD blind spot monitoring information includes BSD blind spot collision warning information and BSD lane change warning information, while the binocular camera blind spot test results include blind spot collision test results and blind spot lane change test results. The accuracy of collision detection can be determined by comparing the BSD blind spot collision warning information and the blind spot collision test results, and the accuracy of lane change detection can be determined by comparing the aforementioned BSD lane change warning information and the aforementioned blind spot lane change test results. The overall accuracy of blind spot detection is derived by combining the accuracy of collision detection and lane change detection.

[0070] In summary, the blind spot detection accuracy determination method for the BSD system provided in this application provides a more accurate result by comparing the results obtained from the BSD system and the blind spot alarm area and lane change alarm area acquired by the binocular camera.

[0071] In some examples, the aforementioned BSD blind spot collision warning information includes BSD blind spot collision boundary information and BSD blind spot collision warning duration information, as well as the aforementioned blind spot collision test results, blind spot collision boundary test results, and blind spot collision warning duration test results;

[0072] The above determination of collision detection accuracy based on the aforementioned BSD blind spot collision warning information and the aforementioned blind spot collision test results includes:

[0073] The boundary overlap is obtained based on the above BSD blind zone collision boundary information and the above blind zone collision boundary test results.

[0074] The time overlap is obtained by using the above BSD blind spot collision warning duration information and blind spot collision warning duration test results;

[0075] The collision detection accuracy is determined based on the aforementioned boundary overlap and time overlap.

[0076] For example, the information that needs to be considered for the blind spot warning area can be the blind spot collision boundary and the collision warning duration. The boundary overlap obtained through BSD blind spot collision boundary information and blind spot collision boundary test results can be used to evaluate the accuracy of identifying the position of other vehicles; the time overlap obtained through BSD blind spot collision warning duration information and blind spot collision warning duration test results can evaluate the speed of identifying other vehicles. The collision detection accuracy determined by combining boundary overlap and time overlap can provide a more accurate evaluation of collision detection accuracy by combining the identified position and the identified speed.

[0077] In summary, the blind spot detection accuracy determination method for the BSD system provided in this application can make a more accurate evaluation of collision detection accuracy by combining the collision detection accuracy determined by the obtained boundary overlap and time overlap, and the collision detection accuracy can be determined by combining the identified position and the identified speed.

[0078] In some examples, the aforementioned BSD lane change warning information includes BSD TTC boundary information and lane change warning time information, and the aforementioned blind spot lane change test results include TTC boundary test results and lane change warning time test results;

[0079] The accuracy of lane change detection is determined using the aforementioned BSD lane change warning information and the aforementioned blind spot lane change test results, including:

[0080] The TTC boundary overlap is determined based on the aforementioned BSD TTC boundary information and TTC boundary test results.

[0081] The overlap of lane change warning times is obtained by combining the above lane change warning time information with the above lane change warning time test results.

[0082] The test results for the lane change warning time were obtained based on the TTC boundary overlap and the lane change warning time overlap.

[0083] For example, TTC (Time to Collision) requires combining the position information of the vehicles behind and the speed difference between the target vehicle and the vehicles behind. TTC boundary overlap can evaluate the accuracy of the target vehicle's recognition of vehicle position and speed. Lane change warning time reflects when the target vehicle detects the vehicle behind and the duration of the warning, reflecting the accuracy and speed of the recognition.

[0084] In summary, the blind spot detection accuracy determination method for the BSD system provided in this application, which obtains the lane change warning time test results through the TTC boundary overlap and lane change warning time overlap, can fully characterize the recognition accuracy and speed of the BSD system.

[0085] In some examples, the determination of the blind spot detection accuracy based on the collision detection accuracy and lane change detection accuracy includes:

[0086] The above-mentioned blind spot detection accuracy is determined based on the above-mentioned collision detection accuracy, the above-mentioned lane change detection accuracy, the collision detection weight coefficient, and the lane change detection weight coefficient, wherein the above-mentioned collision detection weight coefficient is greater than the above-mentioned lane change detection weight coefficient.

[0087] For example, when evaluating blind spot detection accuracy, collision detection accuracy is calculated using a collision detection weighting coefficient, and lane change detection accuracy is calculated using a lane change detection weighting coefficient. The results of these two weighted calculations are then combined to evaluate blind spot detection accuracy. Furthermore, missed or false alarms in the blind spot warning area can directly lead to a collision between the vehicle and vehicles to the side. Vehicles behind the lane change warning area may also adjust the vehicle's driving path and speed. Therefore, the collision detection weighting coefficient should be greater than the lane change detection weighting coefficient.

[0088] In summary, the blind spot detection accuracy determination method of the BSD system provided in this application takes into account the different degrees of danger to the target vehicle caused by false alarms or missed alarms in different areas, and sets different weight coefficients for different areas, resulting in a more objective blind spot detection accuracy.

[0089] In some examples, the aforementioned BSD blind spot monitoring information includes curve BSD blind spot monitoring information and straight-line BSD blind spot monitoring information, and the aforementioned binocular camera blind spot test results include curve binocular camera blind spot test results and straight-line binocular camera blind spot test results;

[0090] The above determination of the blind spot detection accuracy of the BSD system based on the aforementioned BSD blind spot monitoring information and the aforementioned binocular camera blind spot test results includes:

[0091] The accuracy of blind spot detection on curves is obtained by using the above-mentioned curve BSD blind spot monitoring information and the above-mentioned curve binocular camera blind spot test results.

[0092] The accuracy of blind spot detection on straight roads was determined by the above-mentioned BSD blind spot monitoring information and the above-mentioned blind spot test results of the binocular camera on straight roads.

[0093] The accuracy of blind spot detection is determined by the above-mentioned accuracy of blind spot detection on curves, the above-mentioned accuracy of blind spot detection on straight roads, the curve detection weight coefficient, and the straight road detection weight coefficient, wherein the above-mentioned curve detection weight coefficient is greater than the above-mentioned straight road detection weight coefficient.

[0094] For example, in order to fully evaluate the accuracy of vehicle blind spot detection, the test phase can be divided into straight road detection and curve detection according to road conditions. Since the driver's reaction space and risk factor are greater when there are missed or false alarms in the case of curves, the weight coefficient of curve detection is set to be greater than that of straight road detection. This can better combine different road condition information into the accuracy judgment process.

[0095] In summary, the blind spot detection accuracy determination method for the BSD system provided in this application sets the curve detection weight coefficient to be greater than the straight road detection weight coefficient, which can fully consider the impact of different road condition information on the blind spot detection accuracy.

[0096] In some examples, such as Figure 3 The diagram shown is a hardware connection schematic provided in an embodiment of this application, comprising a binocular camera truth acquisition module, a vehicle CAN information module, a laptop computer, and a host computer module. Specific testing procedures can be found in... Figure 4 The test vehicle is equipped with fixed-position, fixed-angle binocular cameras on both sides, which collect real-time BSD performance data such as the relative lateral distance, relative longitudinal distance, and relative longitudinal speed of surrounding vehicles relative to the test vehicle. This data is output to a host computer software. Based on this data, the host computer software calculates BSD parameters such as TTC (Traffic Troubleshooting) for surrounding vehicles relative to the test vehicle. Based on the calculation results and according to preset judgment logic, it determines in real-time whether surrounding vehicles are within the blind spot warning area or lane change warning area of ​​the test vehicle model. This data is used as the true value result. Simultaneously, the host computer monitors and collects CAN BSD related information for the test vehicle and automatically compares it with the true value result in real time, thereby achieving automatic statistical testing of BSD performance and false alarm / missed alarm rates. This solution also has a certain degree of horizontal scalability; for different vehicle models, only the corresponding preset judgment parameters of the host computer need to be changed to collect and calculate the true BSD performance of different vehicle models.

[0097] Please see Figure 5 One embodiment of the blind zone detection accuracy determination device for the BSD system in this application may include:

[0098] The first acquisition unit 21 is used to acquire the BSD blind spot monitoring information of the target vehicle, wherein the BSD blind spot monitoring information is acquired through the BSD system of the target vehicle;

[0099] The second acquisition unit 22 is used to acquire the binocular camera blind spot test results of the target vehicle, wherein the binocular camera blind spot test results are acquired by a binocular camera that has been pre-installed on the target vehicle by a tester.

[0100] The determining unit 23 is used to determine the blind spot detection accuracy of the BSD system based on the BSD blind spot monitoring information and the blind spot test results of the binocular camera.

[0101] like Figure 6 As shown, this application embodiment also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 320 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of any of the methods for determining the blind zone detection accuracy of the BSD system described above.

[0102] Since the electronic device described in this embodiment is the device used to implement the blind zone detection accuracy determination device of a BSD system in the embodiments of this application, those skilled in the art can understand the specific implementation method and its various variations of the electronic device in this embodiment based on the method described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. Any device used by those skilled in the art to implement the method in the embodiments of this application is within the scope of protection of this application.

[0103] In practical implementation, when the computer program 311 is executed by the processor, it can achieve the following: Figure 1 Any of the corresponding implementation methods in the embodiments.

[0104] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0105] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0107] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0108] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0109] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform actions such as... Figure 1 The process for determining the blind zone detection accuracy of the BSD system in the corresponding embodiment.

[0110] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0111] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0113] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0114] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0115] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0116] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for determining the accuracy of blind zone detection in a BSD system, characterized in that, include: Obtain BSD blind spot monitoring information of the target vehicle, wherein the BSD blind spot monitoring information is obtained through the BSD system of the target vehicle; Obtain the blind spot test results of the binocular camera of the target vehicle, wherein the blind spot test results of the binocular camera are obtained by the tester through a binocular camera pre-installed on the target vehicle; The blind spot detection accuracy of the BSD system is determined based on the BSD blind spot monitoring information and the binocular camera blind spot test results. The BSD blind spot monitoring information includes BSD blind spot collision warning information and BSD lane change warning information, and the binocular camera blind spot test results include blind spot collision test results and blind spot lane change test results. The determination of the blind spot detection accuracy of the BSD system based on the BSD blind spot monitoring information and the binocular camera blind spot test results includes: The collision detection accuracy is determined based on the BSD blind spot collision warning information and the blind spot collision test results; The accuracy of lane change detection is determined by the BSD lane change warning information and the blind spot lane change test results; The blind spot detection accuracy is determined based on the collision detection accuracy and the lane change detection accuracy. The BSD blind spot collision warning information includes BSD blind spot collision boundary information and BSD blind spot collision warning duration information, and the blind spot collision test results include blind spot collision boundary test results and blind spot collision warning duration test results; The step of determining the collision detection accuracy based on the BSD blind spot collision warning information and the blind spot collision test results includes: The boundary overlap is obtained based on the BSD blind zone collision boundary information and the blind zone collision boundary test results. The time overlap is obtained by using the BSD blind spot collision warning duration information and the blind spot collision warning duration test results; The collision detection accuracy is determined based on the boundary overlap and the time overlap. The BSD lane change warning information includes BSD TTC boundary information and lane change warning time information, and the blind spot lane change test results include TTC boundary test results and lane change warning time test results; The process of determining lane change detection accuracy using the BSD lane change warning information and the blind spot lane change test results includes: The TTC boundary overlap is determined based on the TTC boundary information and TTC boundary test results of the BSD. The overlap of lane change warning times is obtained by combining the lane change warning time information with the lane change warning time test results. The lane change warning time test result is obtained based on the TTC boundary overlap degree and the lane change warning time overlap degree.

2. The method as described in claim 1, characterized in that, The acquisition of the blind spot test results of the binocular camera of the target vehicle includes: Environmental image information is acquired based on the binocular camera; The environmental image information is identified using an intelligent recognition algorithm to obtain the blind spot test results of the binocular camera.

3. The method as described in claim 1, characterized in that, Determining the blind spot detection accuracy based on the collision detection accuracy and the lane change detection accuracy includes: The blind spot detection accuracy is determined based on the collision detection accuracy, the lane change detection accuracy, the collision detection weight coefficient, and the lane change detection weight coefficient, wherein the collision detection weight coefficient is greater than the lane change detection weight coefficient.

4. The method as described in claim 1, characterized in that, The BSD blind spot monitoring information includes curve BSD blind spot monitoring information and straight road BSD blind spot monitoring information, and the binocular camera blind spot test results include curve binocular camera blind spot test results and straight road binocular camera blind spot test results; The determination of the blind spot detection accuracy of the BSD system based on the BSD blind spot monitoring information and the binocular camera blind spot test results includes: The accuracy of blind spot detection on curves is obtained by using the curve BSD blind spot monitoring information and the curve binocular camera blind spot test results. The accuracy of the straight-line blind spot detection is determined by the straight-line BSD blind spot monitoring information and the straight-line binocular camera blind spot test results; The blind spot detection accuracy is determined by the blind spot detection accuracy of the curve, the blind spot detection accuracy of the straight road, the curve detection weight coefficient, and the straight road detection weight coefficient, wherein the curve detection weight coefficient is greater than the straight road detection weight coefficient.

5. A device for determining the accuracy of blind zone detection in a BSD system, characterized in that, include: The first acquisition unit is used to acquire BSD blind spot monitoring information of the target vehicle, wherein the BSD blind spot monitoring information is acquired through the BSD system of the target vehicle; the BSD blind spot monitoring information includes BSD blind spot collision warning information and BSD lane change warning information. The second acquisition unit is used to acquire the binocular camera blind spot test results of the target vehicle, wherein the binocular camera blind spot test results are acquired by a binocular camera pre-installed on the target vehicle by a tester; the binocular camera blind spot test results include blind spot collision test results and blind spot lane change test results. The determining unit is used to determine the blind spot detection accuracy of the BSD system based on the BSD blind spot monitoring information and the binocular camera blind spot test results; The determining unit is further configured to determine the collision detection accuracy based on the BSD blind spot collision warning information and the blind spot collision test results; the BSD blind spot collision warning information includes BSD blind spot collision boundary information and BSD blind spot collision warning duration information, and the blind spot collision test results include blind spot collision boundary test results and blind spot collision warning duration test results; The accuracy of lane change detection is determined by the BSD lane change warning information and the blind spot lane change test results; the BSD lane change warning information includes BSD TTC boundary information and lane change warning time information, and the blind spot lane change test results include TTC boundary test results and lane change warning time test results. The blind spot detection accuracy is determined based on the collision detection accuracy and the lane change detection accuracy. The determining unit is further configured to obtain the boundary overlap based on the BSD blind zone collision boundary information and the blind zone collision boundary test results; The time overlap is obtained by using the BSD blind spot collision warning duration information and the blind spot collision warning duration test results; The collision detection accuracy is determined based on the boundary overlap and the time overlap. The determining unit is further configured to determine the TTC boundary coincidence degree based on the BSD's TTC boundary information and TTC boundary test results; The overlap of lane change warning times is obtained by combining the lane change warning time information with the lane change warning time test results. The lane change warning time test result is obtained based on the TTC boundary overlap degree and the lane change warning time overlap degree.

6. An electronic device, comprising: The memory and processor are characterized in that the processor, when executing a computer program stored in the memory, implements the steps of the method for determining the accuracy of blind zone detection in a BSD system as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the method for determining the accuracy of blind zone detection in the BSD system as described in any one of claims 1-4.

Images