Anti-glare function evaluation method, device, equipment, medium and program product

Abstract

The present application relates to an anti-glare function evaluation method, device, equipment, medium and program product. The method comprises: obtaining a headlight mask image of a target position; determining a key area according to the headlight mask image and preset key points to obtain a key field of view area; calculating key point indexes according to the headlight mask image and the key field of view area to obtain key point indexes; performing anti-glare evaluation according to the key point indexes to obtain an anti-glare evaluation result. The method can realize an accurate evaluation of the ADB anti-glare effect of smart headlights.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent vehicle lamps, and in particular to an anti-glare function evaluation method, device, equipment, medium and program product. Background Art

[0002] With the continuous development of automobile headlight technology, in the field of smart headlights, some new energy vehicles have been equipped with the ADB (Adaptive Driving Beam) function. When the ADB function is turned on, the vehicles and pedestrians on the road can be anti-glare, so as not to affect other road participants and provide a better driving environment. However, currently, the method basically used is to observe with the naked eye or use an illuminance probe to detect whether the area where the car body is located has been anti-glare. There is no systematic quantitative evaluation method, which makes it difficult to accurately evaluate the quality of the ADB anti-glare function. There is a lack of quantitative evaluation of the accuracy of its anti-glare area, so it is difficult to conduct more accurate debugging and analysis of the anti-glare area. Summary of the invention

[0003] Based on this, it is necessary to provide an anti-glare function evaluation method, device, computer equipment, computer-readable storage medium and computer program product to address the above technical problems, which can accurately and quantitatively evaluate the anti-glare effect of the ADB function of smart headlights through the bounding box overlap index and combined with the key areas of the vehicle body.

[0004] In a first aspect, the present application provides an anti-glare function evaluation method, comprising:

[0005] Get the headlight mask image of the target location;

[0006] Determine the key area according to the headlight mask image and preset key points to obtain the key field of view area;

[0007] Calculate key point indexes according to the vehicle light mask image and the key visual field area to obtain key point indexes;

[0008] An anti-glare evaluation is performed according to the key point indicators to obtain an anti-glare evaluation result.

[0009] In one embodiment, determining the key area according to the vehicle light mask image and preset key points to obtain the key field of view area includes:

[0010] Determine an obstacle area according to the vehicle light mask image;

[0011] The key area of ​​the obstacle area is determined according to the preset key points to obtain the key field of view area.

[0012] In one embodiment, the key point index is calculated based on the vehicle light mask image and the key field of view area to obtain the key point index, including:

[0013] Determining a vehicle light mask area according to the vehicle light mask image;

[0014] Performing a bounding box overlap calculation based on the vehicle light mask area and the key field of view area to obtain a bounding box overlap index;

[0015] Determine the key point weight according to the key visual field area;

[0016] The key point index is calculated according to the bounding box overlap index and the key point weight to obtain the key point index.

[0017] In one embodiment, determining the key point weight according to the key visual area includes:

[0018] Calculate the area ratio of each key area in the key visual field to obtain area ratio data of the key area;

[0019] The key point weight is determined according to the area ratio data.

[0020] In one embodiment, the method further comprises:

[0021] Obtain key point requirements;

[0022] The preset key points are determined according to the key point requirements.

[0023] In one embodiment, the method further comprises:

[0024] Obtain vehicle light obstacle images at multiple different obstacle locations;

[0025] Determine the key area according to the vehicle light obstacle image and preset key points to obtain the obstacle key area;

[0026] Calculating key point indexes according to the vehicle light obstacle image and the key obstacle area to obtain key obstacle indexes;

[0027] A comprehensive anti-glare evaluation is performed based on the key indicators of the obstacle to obtain a comprehensive anti-glare evaluation result.

[0028] In a second aspect, the present application also provides an anti-glare function evaluation device, comprising:

[0029] An acquisition module is used to acquire a headlight mask image at a target location;

[0030] An area determination module is used to determine a key area according to the headlight mask image and preset key points to obtain a key field of view area;

[0031] An index calculation module, used to calculate key point indexes according to the headlight mask image and the key visual field area to obtain key point indexes;

[0032] The evaluation module is used to perform anti-glare evaluation according to the key point indicators to obtain an anti-glare evaluation result.

[0033] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0034] Get the headlight mask image of the target location;

[0035] Determine the key area according to the headlight mask image and preset key points to obtain the key field of view area;

[0036] Calculate key point indexes according to the vehicle light mask image and the key visual field area to obtain key point indexes;

[0037] An anti-glare evaluation is performed according to the key point indicators to obtain an anti-glare evaluation result.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0039] Get the headlight mask image of the target location;

[0040] Determine the key area according to the headlight mask image and preset key points to obtain the key field of view area;

[0041] Calculate key point indexes according to the vehicle light mask image and the key visual field area to obtain key point indexes;

[0042] An anti-glare evaluation is performed according to the key point indicators to obtain an anti-glare evaluation result.

[0043] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0044] Get the headlight mask image of the target location;

[0045] Determine the key area according to the headlight mask image and preset key points to obtain the key field of view area;

[0046] Calculate key point indexes according to the vehicle light mask image and the key visual field area to obtain key point indexes;

[0047] An anti-glare evaluation is performed according to the key point indicators to obtain an anti-glare evaluation result.

[0048] The above anti-glare function evaluation method, device, computer equipment, computer-readable storage medium and computer program product obtain the headlight mask image of the target position; determine the key area according to the headlight mask image and the preset key points to obtain the key field of view area; calculate the key point index according to the headlight mask image and the key field of view area to obtain the key point index; perform anti-glare evaluation according to the key point index to obtain the anti-glare evaluation result. Therefore, by determining the key area according to the headlight mask image and the preset key points, and accurately quantifying the key point index according to the headlight mask image and the key field of view area, the anti-glare effect of the headlight can be evaluated according to the quantified key point index to obtain an accurate anti-glare evaluation result, thereby realizing an accurate quantitative evaluation of the anti-glare effect of the headlight. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 A diagram showing an application environment of an anti-glare function evaluation method in one embodiment;

[0051] Figure 2 is a schematic flow chart of an anti-glare function evaluation method in one embodiment;

[0052] Figure 3 A schematic diagram of a scene of obtaining a headlight mask image at a target position in an anti-glare function evaluation method in an embodiment;

[0053] Figure 4 A schematic diagram of a key area of ​​a vehicle in an anti-glare function evaluation method in one embodiment;

[0054] Figure 5 is a schematic diagram of a center point distance and a diagonal distance in an anti-glare function evaluation method in one embodiment;

[0055] Figure 6 is a schematic flow chart of an anti-glare function evaluation method in one embodiment;

[0056] Figure 7 A schematic diagram of a table of vehicle light obstacle images at multiple different obstacle locations in an anti-glare function evaluation method in one embodiment;

[0057] Figure 8 is a structural block diagram of an anti-glare function evaluation device in one embodiment;

[0058] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] The anti-glare function evaluation method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the headlight mask image of the target position; determines the key area according to the headlight mask image and the preset key points to obtain the key field of view area; calculates the key point index according to the headlight mask image and the key field of view area to obtain the key point index; performs anti-glare evaluation according to the key point index to obtain the anti-glare evaluation result. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0061] In an exemplary embodiment, Figure 2 As shown, a method for evaluating anti-glare function is provided, and the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S202 to S208. Among them:

[0062] Step S202, obtaining a vehicle headlight mask image at a target position.

[0063] The target position may refer to the driver's position corresponding to the obstacle or an independently set camera position, and the headlight mask image refers to an image of the headlights illuminating the obstacle taken from the target position, but is not limited thereto.

[0064] In some embodiments, the vehicle headlight mask image at the target location may be acquired by real-time shooting, or may be acquired from a mask image database, but is not limited thereto.

[0065] In some embodiments, Figure 3 As shown, Figure 3 The process of obtaining the headlight mask image of the target position in real time and the specific shooting scene diagram are shown. Figure 3 The image capture point in the image represents the target position, where the two image capture points correspond to the driver position corresponding to the obstacle and the independently set camera position respectively. Figure 3 The target area covered by the vehicle headlights may be the location where obstacles are placed. The specific obstacles may be vehicles or people, but are not limited thereto.

[0066] Step S204, determining a key area according to the vehicle light mask image and preset key points to obtain a key field of view area.

[0067] When the obstacle in the headlight mask image is a vehicle, the preset key points refer to the key points in the vehicle where the headlight anti-glare treatment needs to be focused.

[0068] In some embodiments, a key area determination is performed based on a headlight mask image and preset key points to obtain a key field of view area, including: determining an obstacle area based on the headlight mask image; and performing a key area determination on the obstacle area based on preset key points to obtain a key field of view area.

[0069] Among them, the obstacle area refers to the area where the obstacle is located in the headlight mask image. It should be noted that the obstacle area can be determined by performing obstacle recognition on the headlight mask image through a pre-trained obstacle recognition model. Among them, the preset key points can be determined based on the vehicle's default key points, or can be determined based on a pre-trained key point recognition model, but is not limited to this.

[0070] In some embodiments, Figure 4 As shown, Figure 4 The obstacle area images obtained by recognizing the headlight mask image are shown, corresponding to the obstacle area images when the obstacle is the front of the vehicle ( Figure 4 (1) in ), and the obstacle area image when the obstacle is the back of the vehicle ( Figure 4(2) in the above), Figure 4 The key area of ​​the obstacle is also determined, and the key visual area in the obstacle area is screened out through the border, for example Figure 4 The key visual field area determined by (1) is the driver's eye point position, and Figure 4 The key visual field areas determined by (2) are the left exterior mirror position, the right exterior mirror position, and the interior mirror position.

[0071] In some embodiments, the method further includes: obtaining key point requirements; and determining preset key points according to the key point requirements.

[0072] Among them, the key point requirements can be set according to actual environmental conditions or application requirements, but are not limited thereto.

[0073] Step S206, calculating key point indexes according to the vehicle light mask image and the key visual field area to obtain key point indexes.

[0074] Among them, the key point index calculation is a quantitative index calculation process through the bounding box loss function combined with the key point weights corresponding to the key field of view area, among which the bounding box loss function adopts CIOU (Complete Intersection over Union).

[0075] In some embodiments, key point indices are calculated based on the headlight mask image and the key field of view area to obtain the key point indices, including: determining the headlight mask area based on the headlight mask image; performing bounding box overlap calculation based on the headlight mask area and the key field of view area to obtain a bounding box overlap index; determining key point weights based on the key field of view area; calculating the key point indices based on the bounding box overlap index and the key point weights to obtain the key point indices.

[0076] Among them, the headlight mask area refers to the mask area in the headlight mask image where the headlight illuminates obstacles after the anti-glare function is turned on. It should be noted that after the anti-glare function is turned on, the headlight will control the corresponding lamp beads in the area and extinguish the corresponding area, thereby achieving an anti-glare effect. In this process, extinguishing the corresponding area will form a corresponding mask area, or an area that is not illuminated, thereby avoiding the occurrence of glare.

[0077] In some embodiments, the headlight mask area can be determined in the headlight mask image according to the pre-trained target detection model, and the bounding box overlap calculation is performed on the headlight mask area and the key field of view area according to the bounding box loss function to obtain a bounding box overlap index.

[0078] The bounding box loss function uses the CIoU technology. It should be noted that CIoU is based on IoU, takes into account the complete intersection between target boxes, and introduces a correction factor to more accurately measure the similarity between the headlight mask area and the key field of view area. Specifically, the expression of the bounding box loss function is shown in the following formulas (1), (2) and (3):

[0079] ; (1)

[0080] ; (2)

[0081] ; (3)

[0082] It should be noted that IoU is an indicator to measure the degree of overlap between the headlight mask area and the key field of view area. It is the ratio of the intersection area and the union area of ​​the bounding boxes corresponding to the two areas. The larger the IoU, the more accurate the shielding rate. d is the distance between the center points of the headlight mask area and the key field of view area, and c is the diagonal distance between the minimum circumscribed rectangle of the headlight mask area and the key field of view area. For details, please refer to the definitions of d and c. Figure 5 .

[0083] Among them, v is used to characterize the consistency of aspect ratio, and are the width and height of the headlight mask area and the key field of view area respectively. α is the adjustment factor. The larger the iou is, the greater its impact is.

[0084] In some embodiments, determining the key point weights according to the key visual area includes: calculating the area ratio of each key area in the key visual area to obtain area ratio data of the key area; and determining the key point weights according to the area ratio data.

[0085] To further illustrate, the specific process of determining the weights of key points is shown in the following table:

[0086]

[0087] In some embodiments, based on the approximate areas of the four key area categories in the above table, the area percentage data of each is calculated: 68% for the driver's eye position, 2% for the interior rearview mirror position, 15% for the left exterior rearview mirror position, and 15% for the right exterior rearview mirror position, and then the key point weights corresponding to each key area are determined based on the area percentage data.

[0088] In some embodiments, the corresponding key point weight is multiplied by the bounding box overlap index to obtain the key point index for subsequent evaluation of the ADB anti-glare effect.

[0089] Step S208, performing anti-glare evaluation according to the key point indicators to obtain an anti-glare evaluation result.

[0090] The process of the anti-glare evaluation may be to compare the results of key point indicators, or to process the key point indicators using other mathematical methods to improve the accuracy of the anti-glare evaluation, but is not limited thereto.

[0091] In some embodiments, the coverage anti-glare evaluation can be performed by combining the key point index with the key area coverage to obtain the coverage anti-glare evaluation result. Specifically, for example, if the key field of view area in the headlight mask image is completely covered by the headlight mask area, it means that the headlight has effectively performed anti-glare treatment on all key areas, so the key point index can be directly used as the coverage anti-glare evaluation result. If the coverage rate of the key field of view area covered by the headlight mask area in the headlight mask image is 85%, then the key point index is correspondingly multiplied by the coverage rate to obtain the coverage anti-glare evaluation result.

[0092] In the above anti-glare function evaluation method, the headlight mask image of the target position is obtained; the key area is determined according to the headlight mask image and the preset key points to obtain the key field of view area; the key point index is calculated according to the headlight mask image and the key field of view area to obtain the key point index; the anti-glare evaluation is performed according to the key point index to obtain the anti-glare evaluation result. Therefore, by determining the key area according to the headlight mask image and the preset key points, and accurately quantifying the key point index according to the headlight mask image and the key field of view area, the anti-glare effect of the headlight can be evaluated according to the quantified key point index, and an accurate anti-glare evaluation result can be obtained, thereby realizing an accurate quantitative evaluation of the anti-glare effect of the headlight.

[0093] In an exemplary embodiment, since it is not possible to simply conduct an accurate quantitative evaluation of the anti-glare effect of a certain obstacle point in some scenarios, the anti-glare effect of the headlights at all points is evaluated. Therefore, it is necessary to more comprehensively consider the anti-glare effect of the headlights at different points and under different types of obstacles, such as Figure 6 As shown, the method further includes a multi-point quantitative comparison and evaluation step, and the quantitative comparison and evaluation step includes steps S602 to S608. Among them:

[0094] Step S602: Acquire a plurality of vehicle light obstacle images at different obstacle locations.

[0095] The multiple different obstacle points refer to multiple different types of obstacles located at points in different directions of the headlights.

[0096] In some embodiments, obstacles at different pre-set locations may be acquired from the same target location, thereby obtaining vehicle light obstacle images at multiple different obstacle locations.

[0097] Step S604: determining a key area based on the vehicle light obstacle image and preset key points to obtain the obstacle key area.

[0098] The headlight obstacle image includes a headlight contrast mask area and an obstacle contrast area.

[0099] In some embodiments, Figure 7 As shown, the key area of ​​the obstacle in the headlight obstacle image is determined by preset key points to obtain the key area of ​​the obstacle. For example, when the obstacle is a vehicle, it is necessary to determine whether the vehicle is facing the front or the rear, and different preset key points are used for key area determination for different directions. When the obstacle is a pedestrian, the preset key point can be a face position, but is not limited thereto.

[0100] Step S606, calculating key point indexes according to the vehicle light obstacle image and the key obstacle area to obtain key obstacle indexes.

[0101] The key obstacle area is a key area that requires special anti-glare treatment according to the type of obstacle. For example, the key area for pedestrians is the face position.

[0102] In some embodiments, the key point indexes of the vehicle light obstacle image and the key obstacle area are calculated by using CIOU technology and combining the key area weights to obtain the key obstacle indexes.

[0103] Step S608, performing a comprehensive anti-glare evaluation according to the key indicators of the obstacle to obtain a comprehensive anti-glare evaluation result.

[0104] Among them, the comprehensive anti-glare assessment needs to comprehensively consider the key obstacle indicators corresponding to different directions and different types of obstacles for comprehensive anti-glare assessment.

[0105] In some embodiments, a comprehensive anti-glare evaluation can be performed based on common obstacle types and the number or frequency of obstacle directions in actual application scenarios of vehicle lights in combination with key obstacle indicators to obtain a comprehensive anti-glare evaluation result. Alternatively, other commonly used mathematical methods can be used to mathematically process multiple key obstacle indicators and then perform an anti-glare evaluation, but the present invention is not limited thereto.

[0106] In this embodiment, by acquiring vehicle light obstacle images of multiple different obstacle positions, performing key area determination based on the vehicle light obstacle images and preset key points to obtain obstacle key areas, performing key point index calculation based on the vehicle light obstacle images and the obstacle key areas to obtain obstacle key indexes, performing a comprehensive anti-glare evaluation based on the obstacle key indexes to obtain a comprehensive anti-glare evaluation result, the anti-glare effect of vehicle lights in different situations can be accurately quantified and comprehensively evaluated.

[0107] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0108] Based on the same inventive concept, the embodiment of the present application also provides an anti-glare function evaluation device for implementing the anti-glare function evaluation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations of one or more anti-glare function evaluation device embodiments provided below can refer to the limitations of the anti-glare function evaluation method above, and will not be repeated here.

[0109] In an exemplary embodiment, Figure 8 As shown, an anti-glare function evaluation device 800 is provided, comprising: an acquisition module 801, an area determination module 802, an index calculation module 803 and an evaluation module 804, wherein:

[0110] An acquisition module 801 is used to acquire a headlight mask image at a target position;

[0111] The area determination module 802 is used to determine the key area according to the vehicle light mask image and the preset key points to obtain the key visual field area;

[0112] The index calculation module 803 is used to calculate the key point index according to the headlight mask image and the key visual field area to obtain the key point index;

[0113] The evaluation module 804 is used to perform anti-glare evaluation according to key point indicators to obtain an anti-glare evaluation result.

[0114] In some embodiments, the area determination module 802 is further used to determine the obstacle area according to the vehicle light mask image; perform key area determination on the obstacle area according to preset key points to obtain a key field of view area.

[0115] In some embodiments, the index calculation module 803 is also used to determine the headlight mask area based on the headlight mask image; perform bounding box overlap calculation based on the headlight mask area and the key field of view area to obtain a bounding box overlap index; determine the key point weight based on the key field of view area; perform key point index calculation based on the bounding box overlap index and the key point weight to obtain a key point index.

[0116] In some embodiments, the indicator calculation module 803 is also used to calculate the area ratio of each key area in the key visual field to obtain the area ratio data of the key area; and determine the key point weight according to the area ratio data.

[0117] In some embodiments, the device further includes: a point determination module, which is used to obtain key point requirements; and determine preset key points according to the key point requirements.

[0118] In some embodiments, the device also includes: a comprehensive evaluation module, which is used to obtain vehicle light obstacle images at multiple different obstacle points; perform key area determination based on the vehicle light obstacle images and preset key points to obtain obstacle key areas; perform key point index calculation based on the vehicle light obstacle images and obstacle key areas to obtain obstacle key indicators; perform comprehensive anti-glare evaluation based on obstacle key indicators to obtain comprehensive anti-glare evaluation results.

[0119] The above-mentioned anti-glare function evaluation device obtains the headlight mask image of the target position; determines the key area according to the headlight mask image and the preset key points to obtain the key field of view area; calculates the key point index according to the headlight mask image and the key field of view area to obtain the key point index; performs anti-glare evaluation according to the key point index to obtain the anti-glare evaluation result. Therefore, by determining the key area according to the headlight mask image and the preset key points, and accurately quantifying the key point index according to the headlight mask image and the key field of view area, the anti-glare effect of the headlight can be evaluated according to the quantified key point index, and an accurate anti-glare evaluation result can be obtained, thereby realizing an accurate quantitative evaluation of the anti-glare effect of the headlight.

[0120] Each module in the above anti-glare function evaluation device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0121] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store a headlight mask image. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an anti-glare function evaluation method is implemented.

[0122] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0123] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the above anti-glare function evaluation method when executing the computer program.

[0124] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above anti-glare function evaluation method are implemented.

[0125] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of the above anti-glare function evaluation method when executed by a processor.

[0126] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0127] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0128] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0129] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for evaluating anti-glare function, characterized in that: The method comprises: Acquire a headlight mask image of the target position; wherein the headlight mask image is formed by controlling corresponding lamp beads in the area after the anti-glare function of the headlight is turned on, extinguishing the corresponding area to form a corresponding mask area image; Determine the key area according to the headlight mask image and the preset key points to obtain the key field of view area; wherein the preset key points refer to the key points where the headlight anti-glare treatment needs to be focused after the anti-glare function of the vehicle is turned on; The key area determination is performed according to the vehicle light mask image and the preset key points to obtain the key field of view area, including: Determine an obstacle area according to the vehicle light mask image; Performing a key area determination on the obstacle area according to the preset key points to obtain the key field of view area; Calculate key point indexes according to the vehicle light mask image and the key visual field area to obtain key point indexes; The step of calculating key point indicators according to the vehicle light mask image and the key visual field area to obtain key point indicators includes: Determining a vehicle light mask area according to the vehicle light mask image; Performing a bounding box overlap calculation on the headlight mask area and the key field of view area according to a bounding box loss function to obtain a bounding box overlap index; wherein the bounding box loss function adopts CIoU, and the bounding box overlap index is used to measure the similarity between the headlight mask area and the key field of view area; Determine the key point weight according to the key visual field area; Calculating a key point index according to the bounding box overlap index and the key point weight to obtain the key point index; An anti-glare evaluation is performed according to the key point indicators to obtain an anti-glare evaluation result.

2. The method according to claim 1, characterized in that Determining the key point weights according to the key visual field area includes: Calculate the area ratio of each key area in the key visual field to obtain area ratio data of the key area; The key point weight is determined according to the area ratio data.

3. The method according to claim 1, characterized in that The method further comprises: Obtain key point requirements; The preset key points are determined according to the key point requirements.

4. The method according to claim 1, characterized in that: The method further comprises: Obtain vehicle light obstacle images at multiple different obstacle locations; Determine the key area according to the vehicle light obstacle image and preset key points to obtain the obstacle key area; Calculating key point indicators according to the vehicle light obstacle image and the key obstacle area to obtain key obstacle indicators; A comprehensive anti-glare evaluation is performed based on the key indicators of the obstacle to obtain a comprehensive anti-glare evaluation result.

5. An anti-glare function evaluation device, characterized in that: The device comprises: An acquisition module is used to acquire a headlight mask image at a target location; wherein the headlight mask image is formed by controlling corresponding lamp beads in a region after the anti-glare function of the headlight is turned on, extinguishing the corresponding region, thereby forming a corresponding mask region image; An area determination module is used to determine the key area according to the headlight mask image and preset key points to obtain a key field of view area; wherein the preset key points refer to key points where the headlight anti-glare treatment needs to be focused after the anti-glare function of the vehicle is turned on; The area determination module is further used to determine the obstacle area according to the vehicle light mask image; perform key area determination on the obstacle area according to the preset key points to obtain the key field of view area; An index calculation module, used to calculate key point indexes according to the headlight mask image and the key visual field area to obtain key point indexes; The index calculation module is further used to determine the headlight mask area according to the headlight mask image; perform bounding box overlap calculation on the headlight mask area and the key field of view area according to a bounding box loss function to obtain a bounding box overlap index; wherein the bounding box loss function adopts CIoU, and the bounding box overlap index is used to measure the similarity between the headlight mask area and the key field of view area; determine the key point weight according to the key field of view area; perform key point index calculation according to the bounding box overlap index and the key point weight to obtain the key point index; The evaluation module is used to perform anti-glare evaluation according to the key point indicators to obtain an anti-glare evaluation result.

6. The device according to claim 5, characterized in that The indicator calculation module is also used to calculate the area ratio of each key area in the key visual field to obtain the area ratio data of the key area; and determine the key point weight according to the area ratio data.

7. The device according to claim 5 further comprises a point determination module for obtaining key point requirements; and determining preset key points according to the key point requirements.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images