A driver identity recognition method and system

Abstract

The present disclosure provides a driver identity recognition method and system, belonging to the technical field of face recognition, which comprises: adjusting a first parameter of a first image based on first environment information to obtain a second image, the first image being a driver image without a background image, and the first parameter being an adjustment parameter of image definition; and performing identity recognition on the driver based on the second image. The present disclosure provides a driver identity recognition method and system to improve the accuracy of face recognition.

Description

Technical Field

[0001] This disclosure belongs to the field of facial recognition technology, and more specifically, relates to a driver identification method and system. Background Technology

[0002] With the intelligent development of enterprise internal vehicle management, accurate driver identification has become crucial for ensuring vehicle safety and improving management efficiency. Currently, many enterprises use image acquisition equipment combined with facial recognition technology to quickly verify driver identity. However, in practical applications, existing image acquisition technologies face a significant problem: image clarity is greatly affected by lighting intensity. In environments with insufficient or excessive lighting, the quality of acquired facial images is often poor, leading to decreased accuracy in feature extraction and comparison by facial recognition algorithms, and even the inability to accurately identify drivers, thus affecting the normal dispatching and use of vehicles. Summary of the Invention

[0003] The purpose of this disclosure is to provide a driver identification method and system to improve the accuracy of facial recognition.

[0004] A first aspect of this disclosure provides a driver identification method, including:

[0005] The first parameter of the first image is adjusted based on the first environmental information to obtain the second image. The first image is a driver image that does not contain a background image, and the first parameter is an adjustment parameter for image sharpness.

[0006] The driver is identified based on the second image.

[0007] A second aspect of this disclosure provides a driver identification system, comprising:

[0008] Image acquisition module: used to adjust the first parameter of the first image based on the first environmental information to obtain the second image, wherein the first image is a driver image that does not contain a background image, and the first parameter is an adjustment parameter for image sharpness;

[0009] Image matching module: used to identify the driver based on the second image.

[0010] A third aspect of this disclosure provides an image acquisition device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the driver identification method described above.

[0011] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the driver identification method described above.

[0012] The beneficial effects of the driver identification method and system provided in this disclosure are as follows:

[0013] This embodiment of the disclosure intelligently analyzes first environmental information to automatically adjust the sharpness parameters of the first image, thereby generating a clearer and more detailed second image. This step greatly optimizes the input data quality of the face recognition algorithm, providing a solid foundation for subsequent identity verification. Therefore, regardless of whether the lighting conditions are insufficient or excessively bright, this method can ensure the clarity of the driver image, thereby improving the accuracy of face recognition. This not only improves the security and efficiency of internal vehicle management for enterprises but also provides drivers with a more convenient and efficient identity verification experience. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a flowchart illustrating a driver identification method according to an embodiment of the present disclosure;

[0016] Figure 2 This is a structural block diagram of a driver identification system provided in one embodiment of the present disclosure;

[0017] Figure 3 This is a schematic block diagram of an image acquisition device provided in one embodiment of the present disclosure. Detailed Implementation

[0018] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0019] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0020] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a driver identification method according to an embodiment of the present disclosure. The method includes:

[0021] S101: Adjust the first parameter of the first image based on the first environmental information to obtain the second image. The first image is a driver image that does not contain a background image, and the first parameter is an adjustment parameter for image sharpness.

[0022] In this embodiment, after the driver gets into the vehicle, an image of the driver can be captured by an image acquisition device (such as a camera). The first image is separated from the original captured image to obtain an image that does not contain a background image and is specifically focused on the driver, that is, an image that only contains the driver's face and does not contain a background, so as to extract the driver's facial features more accurately.

[0023] While acquiring images, this embodiment can automatically analyze the current ambient lighting conditions using an ambient light sensor (such as a light intensity sensor) or image processing algorithm embedded in the image acquisition device. The environmental information in this embodiment may include factors such as ambient light intensity, light direction, and color temperature, forming primary environmental information. This process is performed in real-time during image acquisition to ensure that each shot can be adaptively adjusted according to the current environment.

[0024] In this embodiment, parameters are adjusted for the first image based on detected environmental information. Here, the first parameter refers to adjustment parameters that affect image sharpness, such as exposure time, contrast, and brightness. This embodiment automatically adjusts these parameters according to lighting conditions to improve image sharpness. The adjusted image is referred to as the second image.

[0025] For example, in low light conditions, this embodiment can increase brightness and contrast to make the driver's facial features in the image clearer; while in high light conditions, this embodiment can reduce brightness and contrast to avoid overexposure of the image and blurring of facial features.

[0026] After parameter adjustments, the original first image is processed into a second image. While preserving the driver's facial information, the second image optimizes clarity and reduces the negative impacts of poor lighting conditions, such as blurriness, noise, or insufficient contrast. This ensures high-quality facial images even in complex and variable lighting environments, providing more reliable input for subsequent identity recognition.

[0027] S102: Identify the driver based on the second image.

[0028] After obtaining the second image, this embodiment can use a face recognition algorithm to extract the driver's facial features from the image. These features may include the shape and position of the eyes, nose, and mouth, as well as facial texture information, etc.

[0029] The extracted facial features will be compared with the known driver facial features stored in this embodiment. This comparison process can employ various complex algorithms and models, such as deep learning models and support vector machines.

[0030] Based on the comparison results, this embodiment will output an identification result, namely the identified driver's identity. If the comparison is successful, this embodiment will confirm the driver's identity and allow them to perform subsequent operations (such as starting the vehicle, recording vehicle usage information, etc.); if the comparison fails, this embodiment will reject the driver's request or require the driver to re-identify.

[0031] As can be seen from the above, this embodiment of the present disclosure, by intelligently analyzing the first environmental information, can automatically adjust the sharpness parameters of the first image, thereby generating a clearer and more detailed second image. This step greatly optimizes the input data quality of the face recognition algorithm, providing a solid foundation for subsequent identity verification. Therefore, regardless of whether the lighting is insufficient or excessively bright, this method can ensure the clarity of the driver image, thereby improving the accuracy of face recognition. This not only improves the security and efficiency of internal vehicle management for enterprises but also provides drivers with a more convenient and efficient identity verification experience.

[0032] In one embodiment of this disclosure, before adjusting the first parameter of the first image based on the first environmental information to obtain the second image, the method further includes:

[0033] The first image is obtained by extracting features from the third image, which is a driver image that includes the background image.

[0034] In this embodiment, after the driver gets into the vehicle, a complete image containing the driver and his / her surroundings (i.e., the third image) is captured first. This image is the unprocessed raw image, containing all the information about the driver and the background.

[0035] Then, feature extraction and background removal are performed based on the original image. That is, this embodiment uses image processing and machine learning techniques (such as deep learning image segmentation models) to process the third image. The purpose of this process is to identify and extract the driver's facial region from the complex image while removing the background image. By analyzing the image's color, texture, shape, and other features, the outline of the driver's face can be accurately delineated, thereby separating the first image—that is, the image containing only the driver's face. This ensures that subsequent identity recognition processes focus on the driver's facial features, reduces unnecessary background interference, and improves the accuracy and efficiency of recognition.

[0036] In this embodiment, by extracting features from driver images containing background images and then adjusting the parameters of the extracted images based on environmental information, the interference of background information on driver image analysis can be significantly reduced, improving the accuracy and efficiency of the analysis. Secondly, parameter adjustment based on environmental information can ensure that the image maintains good visual effects in different environments, providing high-quality image data for subsequent tasks such as driving behavior analysis and face recognition.

[0037] In one embodiment of this disclosure, adjusting a first parameter of a first image based on first environmental information to obtain a second image includes:

[0038] The first image is segmented to obtain multiple first image regions;

[0039] Identify the sharpness corresponding to multiple regions of the first image;

[0040] Set any first image region with a resolution greater than the first resolution as the target image region;

[0041] The first parameter of the first image is adjusted based on the sharpness of the target image region to obtain the second image.

[0042] In practical applications, changes in ambient lighting conditions can cause some facial areas to become blurry, potentially affecting the clarity of the driver's facial image and leading to poor accuracy in driver identification.

[0043] Therefore, in this embodiment, the first image is first segmented into multiple smaller image regions. This step can be achieved using image segmentation algorithms, such as semantic segmentation based on deep learning, to automatically identify and segment different regions in the image, for example, segmenting them according to different parts of a face (forehead, eyes, nose, mouth, etc.).

[0044] Then, the sharpness of each segmented first image region is calculated. This embodiment can achieve this by calculating metrics such as contrast, edge strength, or structural similarity for each region. These metrics reflect the sharpness of the image regions, thereby helping to determine which regions contain more detail or are easier to identify.

[0045] Next, any image region with a resolution greater than a first resolution is designated as the target image region. The first resolution is a preset threshold used to determine which regions have sufficiently high resolution. This means that this embodiment focuses on relatively clearer and higher-quality image regions. In this embodiment, these regions are already quite suitable for face recognition and can serve as a benchmark for subsequent adjustments.

[0046] Finally, based on the sharpness characteristics of the target image region, this embodiment automatically adjusts the first parameters of the first image, such as contrast and brightness, and optimizes the entire image based on these regions to ultimately generate the second image. The goal of the adjustment is to make the entire image as close as possible to or reach the sharpness level of the target region, thereby improving the overall image quality while maintaining details in key areas, and providing a more ideal input for subsequent identity recognition.

[0047] In this embodiment, the method described above can also monitor the driver's driving status to ensure driving safety. For example, when entering a tunnel or underground parking garage from a bright sunlight environment, the clarity of the driver's facial image may be affected, causing some areas to become blurry.

[0048] In this embodiment, the first step is to capture an image containing the driver's face, known as the first image. Next, this embodiment segments this first image using an image segmentation algorithm, dividing the driver's facial region into multiple smaller regions, such as the eyes, nose, and mouth; these constitute multiple first image regions. Then, this embodiment identifies the sharpness of each small region. Assuming the sharpness of the eye region exceeds a first sharpness threshold, the eye region is designated as the target image region. Based on the sharpness of the target image region (eye region), this embodiment adjusts the brightness, contrast, and other parameters of the entire first image to make the overall image sharpness more uniform. In this way, this embodiment can automatically adjust the image sharpness when lighting conditions change, ensuring effective monitoring of the driver's driving status even in complex environments, thus improving driving safety.

[0049] In this embodiment, by identifying and adjusting the parameters of the entire image based on areas of high image clarity, it is possible to ensure that the most important information or details in the image are preserved and highlighted. This not only improves the visual effect of the image, making it easier for humans or machines to recognize, but also allows for flexible parameter adjustment according to different environments and needs, achieving personalized optimization of image quality. Furthermore, since adjustments are made only to areas of high clarity, this method can also reduce computational resource consumption and improve processing efficiency to some extent.

[0050] In one embodiment of this disclosure, it further includes:

[0051] If the resolution of multiple first image regions is less than the first resolution, then the first parameter of the first image information is adjusted based on the first resolution.

[0052] In this embodiment, when the sharpness of multiple first image regions is detected to be lower than a preset first sharpness threshold, this embodiment will not use specific regions as optimization references, but will directly adjust the first parameters of the entire image based on the initially set first sharpness requirement. Such adjustments are global, such as increasing the overall brightness of the image or improving the contrast, with the aim of making the entire image or a specific region reach or approach the preset first sharpness standard.

[0053] In this embodiment, by automatically detecting image sharpness and adjusting parameters as needed, it ensures that the image achieves a higher standard of sharpness while maintaining its realism. This not only enhances the user's visual experience but also facilitates subsequent image analysis and processing. Furthermore, since the adjustment process is automated, it significantly saves labor and time costs, improving overall work efficiency.

[0054] In one embodiment of this disclosure, driver identification based on a second image includes:

[0055] The second image is segmented to obtain multiple second image regions, and each second image region contains multiple second image features;

[0056] The first image matrix is ​​obtained based on multiple feature values ​​corresponding to multiple second image regions and multiple second image features;

[0057] The driver's identity information is matched based on the similarity between the first image matrix and the second image matrix;

[0058] The first image matrix is ​​the currently obtained image matrix, and the second image matrix is ​​the image matrix from the face database.

[0059] In this embodiment, the second image is segmented into multiple second image regions. Each region contains multiple second image features related to the driver's facial features. Then, feature values ​​corresponding to each second image feature in these second image regions are extracted, and a first image matrix is ​​constructed using these feature values. This first image matrix is ​​then compared with second image matrices stored in a face database for similarity matching. Each image matrix in the face database corresponds to a person's identity information; they were extracted and constructed from face images of known identities using a similar method previously. Finally, the similarity between the first image matrix and the second image matrix is ​​compared, and the second image matrix most similar to the first image matrix is ​​found, thereby determining the driver's identity information.

[0060] In face recognition, a face is divided into 10 feature regions (second image regions): facial contour, eyes, eyebrows, nose, mouth, chin, left face, right face, left ear, and right ear. These 10 feature regions are transformed into feature vectors. Each region has 22 features (second image features), and the value of each feature ranges from 1 to 100. A reference matrix (first image matrix) is constructed based on the feature vectors and feature values. In the reference matrix, each row represents the feature vector corresponding to one facial feature region, and each column represents the feature value corresponding to each feature.

[0061] If more than 80% of the 22 features in each feature region are similar, then the feature region is considered similar.

[0062] The baseline matrix corresponding to the current driver is obtained by image acquisition. This baseline matrix is ​​then matched with a second image matrix stored in the face database to find the second image matrix that is most similar to the baseline matrix, thereby determining the driver's identity information.

[0063] In one embodiment of this disclosure, it further includes:

[0064] The similarity between the first image matrix and the second image matrix is ​​set based on the effectiveness of multiple second image regions.

[0065] In this embodiment, during the identity recognition process, the validity assessment takes into account that multiple second image regions obtained after image segmentation may be occluded (e.g., the driver wearing a mask), affecting subsequent similarity calculations. The validity of the second image regions is calculated based on the number of occluded second image regions.

[0066] Based on the evaluation results of the aforementioned regional effectiveness, this embodiment dynamically sets the similarity standard or weight used to compare the first image matrix and the second image matrix. This means that for images containing more effective feature regions, this embodiment can appropriately reduce the matching strictness, as these images provide more sufficient identity information; conversely, if there are fewer effective feature regions, this embodiment will require a higher similarity match to confirm identity and avoid misjudgment. This is because occlusions may make some key features invisible, but this does not mean that the two images are dissimilar. By increasing the matching threshold, this embodiment can tolerate such differences to a certain extent, thereby improving the accuracy of recognition.

[0067] In this embodiment, by adjusting the similarity matching threshold according to the occlusion situation, the accuracy and fault tolerance of the identification can be improved while ensuring security. Furthermore, this method also demonstrates the flexibility and adaptability of the design, allowing for adjustments and optimizations based on different usage scenarios and needs.

[0068] In one embodiment of this disclosure, setting the similarity between the first image matrix and the second image matrix based on the validity of multiple second image regions includes:

[0069] When the number of valid second image regions is greater than a threshold, a match is successful if the similarity between the first image matrix and the second image matrix is ​​greater than a first preset value.

[0070] When the number of valid second image regions is less than a threshold, a match is successful if the similarity between the first image matrix and the second image matrix is ​​greater than a second preset value.

[0071] In this embodiment, when performing identity recognition, the similarity calculation method between the first image matrix and the second image matrix is ​​first set based on the validity of multiple second image regions. Specifically, this embodiment first counts the number of image regions that meet the validity condition (occlusion).

[0072] If the number of image regions meeting the validity criteria is greater than a preset threshold, this embodiment uses a first preset value as the similarity matching threshold. In this case, this embodiment will only determine a successful match when the similarity between the first image matrix and the second image matrix is ​​greater than this first preset value. This is because when most image regions are valid, this embodiment can appropriately reduce the stringency of the matching.

[0073] However, if the number of image regions meeting the validity criteria is less than a preset threshold, this embodiment can switch to a second preset value as the similarity matching threshold. The second preset value is greater than the first preset value to address situations where the effective image region is reduced due to factors such as occlusion or blurring. In this case, this embodiment needs to calculate a higher similarity match to confirm identity, thereby improving the recognition success rate under adverse conditions.

[0074] Corresponding to the driver identification method in the above embodiment, Figure 2 This is a structural block diagram of a driver identification system according to an embodiment of the present disclosure. For ease of explanation, only the parts relevant to the embodiment of the present disclosure are shown. Reference Figure 2 The driver identification system 20 includes: an image acquisition module 21 and an image matching module 22.

[0075] Among them, the image acquisition module 21 is used to adjust the first parameter of the first image based on the first environmental information to obtain the second image. The first image is a driver image that does not contain a background image, and the first parameter is an adjustment parameter for image clarity.

[0076] Image matching module 22: used to identify the driver based on the second image.

[0077] In one embodiment of this disclosure, before the image acquisition module 21, a raw image acquisition module is further included;

[0078] The first image is obtained by extracting features from the third image, which is a driver image that includes the background image.

[0079] In one embodiment of this disclosure, the image acquisition module 21 is further configured to:

[0080] The first image is segmented to obtain multiple first image regions;

[0081] Identify the sharpness corresponding to multiple regions of the first image;

[0082] Set any first image region with a resolution greater than the first resolution as the target image region;

[0083] The first parameter of the first image is adjusted based on the sharpness of the target image region to obtain the second image.

[0084] In one embodiment of this disclosure, the image acquisition module 21 is further configured to:

[0085] If the resolution of multiple first image regions is less than the first resolution, then the first parameter of the first image information is adjusted based on the first resolution.

[0086] In one embodiment of this disclosure, the image matching module 22 is specifically used for:

[0087] The second image is segmented to obtain multiple second image regions, and each second image region contains multiple second image features;

[0088] The first image matrix is ​​obtained based on multiple feature values ​​corresponding to multiple second image regions and multiple second image features;

[0089] The driver's identity information is matched based on the similarity between the first image matrix and the second image matrix;

[0090] The first image matrix is ​​the currently obtained image matrix, and the second image matrix is ​​the image matrix from the face database.

[0091] In one embodiment of this disclosure, the image acquisition module 21 is further configured to:

[0092] The similarity between the first image matrix and the second image matrix is ​​set based on the effectiveness of multiple second image regions.

[0093] In one embodiment of this disclosure, the image acquisition module 21 is further configured to:

[0094] When the number of valid second image regions is greater than a threshold, a match is successful if the similarity between the first image matrix and the second image matrix is ​​greater than a first preset value.

[0095] When the number of valid second image regions is less than a threshold, a match is successful if the similarity between the first image matrix and the second image matrix is ​​greater than a second preset value.

[0096] See Figure 3 , Figure 3 This is a schematic block diagram of an image acquisition device provided in one embodiment of the present disclosure. Figure 3 The image acquisition device 300 shown in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the above-described device embodiments, for example... Figure 2 The functions of modules 21 and 22 shown.

[0097] It should be understood that, in the embodiments of this disclosure, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0098] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0099] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store device type information.

[0100] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this disclosure can execute the implementation methods described in the first and second embodiments of the driver identification method provided in the embodiments of this disclosure, or they can execute the implementation methods of the image acquisition device described in the embodiments of this disclosure, which will not be repeated here.

[0101] In another embodiment of this disclosure, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0102] The computer-readable storage medium can be an internal storage unit of the image acquisition device in any of the foregoing embodiments, such as the hard disk or memory of the image acquisition device. The computer-readable storage medium can also be an external storage device of the image acquisition device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., provided on the image acquisition device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the image acquisition device. The computer-readable storage medium is used to store computer programs and other programs and data required by the image acquisition device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0103] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0104] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the image acquisition device and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed image acquisition devices and methods can be implemented in other ways. For example, the device 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 mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or units, or it may be an electrical, mechanical, or other form of connection.

[0106] 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 the embodiments of this disclosure, depending on actual needs.

[0107] Furthermore, the functional units in the various embodiments of this disclosure 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.

[0108] The above are merely specific embodiments of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this disclosure, and these modifications or substitutions should all be covered within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A driver identification method, characterized in that, include: The first parameter of the first image is adjusted based on the first environmental information to obtain the second image. The first image is a driver image that does not contain a background image, and the first parameter is an adjustment parameter for image sharpness. The driver is identified based on the second image; The step of adjusting the first parameter of the first image based on the first environmental information to obtain the second image includes: The first image is segmented to obtain multiple first image regions; Identify the sharpness corresponding to multiple regions of the first image; Set any first image region with a resolution greater than the first resolution as the target image region; The first parameter of the first image is adjusted based on the sharpness of the target image region to obtain the second image; If the sharpness of multiple first image regions is less than the first sharpness, then the first parameter of the first image is adjusted based on the first sharpness. The driver identification based on the second image includes: The second image is segmented to obtain multiple second image regions, and each second image region contains multiple second image features. The first image matrix is ​​obtained based on multiple feature values ​​corresponding to multiple second image regions and multiple second image features; The driver's identity information is matched based on the similarity between the first image matrix and the second image matrix; The first image matrix is ​​the currently obtained image matrix, and the second image matrix is ​​the image matrix in the face database; Driver identification methods also include: The validity of the second image region is calculated based on the number of times the second image region is occluded. When the number of valid second image regions is greater than a threshold, a match is successful if the similarity between the first image matrix and the second image matrix is ​​greater than a first preset value. When the number of valid second image regions is less than a threshold, a match is successful if the similarity between the first image matrix and the second image matrix is ​​greater than a second preset value, where the second preset value is greater than the first preset value.

2. The driver identification method as described in claim 1, characterized in that, Before adjusting the first parameters of the first image based on the first environmental information to obtain the second image, the process also includes: The first image is obtained by extracting features from the third image, wherein the third image is a driver image that includes a background image.

3. A driver identification system, characterized in that, include: Image acquisition module: used to adjust the first parameter of the first image based on the first environmental information to obtain the second image, wherein the first image is a driver image that does not contain a background image, and the first parameter is an adjustment parameter for image sharpness; Image matching module: used to identify the driver based on the second image; The image acquisition module is further configured to: segment the first image to obtain multiple first image regions; Identify the sharpness corresponding to multiple regions of the first image; Set any first image region with a resolution greater than the first resolution as the target image region; The first parameter of the first image is adjusted based on the sharpness of the target image region to obtain the second image; If the sharpness of multiple first image regions is less than the first sharpness, then the first parameter of the first image is adjusted based on the first sharpness. The image matching module is specifically used for: The second image is segmented to obtain multiple second image regions, and each second image region contains multiple second image features. The first image matrix is ​​obtained based on multiple feature values ​​corresponding to multiple second image regions and multiple second image features; The driver's identity information is matched based on the similarity between the first image matrix and the second image matrix; The first image matrix is ​​the currently obtained image matrix, and the second image matrix is ​​the image matrix in the face database; The validity of the second image region is calculated based on the number of times the second image region is occluded. When the number of valid second image regions is greater than a threshold, a match is successful if the similarity between the first image matrix and the second image matrix is ​​greater than a first preset value. When the number of valid second image regions is less than a threshold, a match is successful if the similarity between the first image matrix and the second image matrix is ​​greater than a second preset value, where the second preset value is greater than the first preset value.

4. An image acquisition device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 2.

5. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 2.

Images