Method and system for face detection and recognition in fast-moving mobile law enforcement equipment
By determining and adjusting shooting parameters in mobile law enforcement equipment, the problem of poor face detection and recognition effects during fast movement is solved, and higher shooting clarity and face recognition accuracy are achieved, and the law enforcement effect is improved.
Patent Information
- Application Number
- CN202410296827.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-15
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-03-15
AI Technical Summary
The existing mobile law enforcement equipment has poor face detection and recognition effects during fast movement, making it difficult to ensure the appropriateness of shooting effects, distance and environment, and affects the accuracy of face recognition.
By determining the location, environmental parameters and movement speed of the target object and mobile law enforcement equipment, and calculating and adjusting the shooting parameters to ensure the clarity of the shooting effect and the accuracy of face recognition, including using cameras and environmental sensors to obtain parameters and perform image fusion and facial recognition processing.
It improves the face detection and recognition effect of mobile law enforcement equipment in fast movement, ensures the clarity of background and targets, and improves the accuracy and law enforcement effect of face recognition.
Smart Images

Figure CN118212673B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of electronic technology or computer technology, and in particular to a method and system for detecting and identifying human faces in fast-moving mobile law enforcement equipment. Background Art
[0002] With the progress of social civilization and the rapid development of science and technology, electronic law enforcement is becoming more and more popular, and it will inevitably become a normalized law enforcement trend. In practical applications, from a cost perspective, electronic law enforcement caters to the urgent needs of the times and social development. At present, more and more industries are or will adopt e-government to serve people, so mobile law enforcement equipment will become more and more popular.
[0003] At present, the face detection and recognition effects of mobile law enforcement equipment during movement are relatively poor. Therefore, the problem of how to improve the face detection and recognition effects of mobile law enforcement equipment during rapid movement needs to be solved urgently. Summary of the invention
[0004] The embodiments of the present application provide a method and system for face detection and recognition in a mobile law enforcement device in rapid motion, which helps to improve the face detection and recognition effect in a mobile law enforcement device in rapid motion.
[0005] In a first aspect, an embodiment of the present application provides a method for detecting and recognizing a face in a mobile law enforcement device in rapid motion, which is applied to the mobile law enforcement device, and the method includes:
[0006] Determine a first position of a target object and a second position of the mobile law enforcement device; obtain target environmental parameters of the first position;
[0007] determining a target distance between the target object and the mobile law enforcement device based on the first position and the second position;
[0008] Acquire a first moving speed of the target object and a second moving speed of the mobile law enforcement device;
[0009] Determining a first shooting parameter corresponding to the target distance and the target environment parameter;
[0010] determining a second shooting parameter corresponding to the first moving speed and the second moving speed;
[0011] photographing the target object according to the first photographing parameter and the second photographing parameter to obtain a first target image;
[0012] Perform face recognition on the first target image to obtain a first target face image.
[0013] In a second aspect, an embodiment of the present application provides a face detection and recognition system for a mobile law enforcement device in rapid motion, which is applied to the mobile law enforcement device, and the system includes:
[0014] A determination unit, configured to determine a first position of a target object and a second position of the mobile law enforcement device; and obtain target environment parameters of the first position;
[0015] The determining unit is further used to determine a target distance between the target object and the mobile law enforcement device according to the first position and the second position;
[0016] An acquisition unit, configured to acquire a first moving speed of the target object and a second moving speed of the mobile law enforcement device;
[0017] The determining unit is further configured to determine a first shooting parameter corresponding to the target distance and the target environment parameter; and determine a second shooting parameter corresponding to the first moving speed and the second moving speed;
[0018] a photographing unit, configured to photograph the target object according to the first photographing parameter and the second photographing parameter to obtain a first target image;
[0019] The recognition unit is used to perform face recognition on the first target image to obtain a first target face image.
[0020] The implementation of the embodiments of the present application has the following beneficial effects:
[0021] It can be seen that the face detection and recognition method and system for the fast-moving mobile law enforcement equipment described in the embodiments of the present application are applied to the mobile law enforcement equipment to determine the first position of the target object and the second position of the mobile law enforcement equipment; obtain the target environment parameters of the first position, determine the target distance between the target object and the mobile law enforcement equipment according to the first position and the second position, obtain the first moving speed of the target object and the second moving speed of the mobile law enforcement equipment, determine the first shooting parameters corresponding to the target distance and the target environment parameters, determine the second shooting parameters corresponding to the first moving speed and the second moving speed, shoot the target object according to the first shooting parameters and the second shooting parameters to obtain a first target image, perform face recognition on the first target image to obtain a first target face image. First, the first shooting parameters corresponding to the target distance and the target environment parameters can be determined, thereby ensuring Verify that the shooting effect is suitable for the distance and the environment, which helps to improve the shooting effect. Secondly, determine the corresponding second shooting parameters based on the first moving speed and the second moving speed, which helps to ensure that the subsequent target object obtains a clear image and helps to ensure the accuracy of face recognition. Finally, shoot the target object according to the first shooting parameters and the second shooting parameters to obtain a first target image, which can ensure that the background is clear and the target is clear, which helps to ensure a complete and clear image. Since the first target image can obtain a clear portrait image of the target object, the recognition accuracy of the face recognition image is guaranteed, that is, the clarity of the original image is directly related to the recognition accuracy. Then perform face recognition on the first target image to obtain a first target face image, which not only helps face recognition, but also helps to ensure law enforcement results, and helps to improve the face detection and recognition effects of mobile law enforcement equipment during rapid movement. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art 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 drawings can be obtained based on these drawings without paying creative work.
[0023] Figure 1 It is a flowchart of a method for detecting and identifying a face in a fast-moving mobile law enforcement device provided by an embodiment of the present application;
[0024] Figure 2 It is a structural diagram of a mobile law enforcement device provided in an embodiment of the present application;
[0025] Figure 3 This is a block diagram of the functional units of a face detection and recognition system for a mobile law enforcement device in rapid motion provided by an embodiment of the present application. DETAILED DESCRIPTION
[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0027] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.
[0028] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0029] The embodiments of the present application are described in detail below.
[0030] See also Figure 1 , Figure 1 This is a flow chart of a method for detecting and identifying a face in a mobile law enforcement device in rapid motion provided by an embodiment of the present application, which is applied to a mobile law enforcement device and may include the following steps:
[0031] 101. Determine a first position of a target object and a second position of the mobile law enforcement device; and obtain target environment parameters of the first position.
[0032] In the embodiment of the present application, the target object may be an object of interest to the mobile law enforcement device, or an object specified by a user, and the target object may be a person.
[0033] The target environment parameters may include at least one of the following: environment brightness, environment color temperature, temperature, humidity, background type, ultraviolet intensity, atmospheric pressure, etc., which are not limited here.
[0034] In a specific implementation, the mobile law enforcement device may include a positioning device, through which the second position of the mobile law enforcement device can be determined, and the mobile law enforcement device may include a camera, through which the target object can be hunted, thereby determining the first position of the target object. The mobile law enforcement device may also include an environmental sensor, through which the target environmental parameters can be obtained.
[0035] 102. Determine a target distance between the target object and the mobile law enforcement device according to the first position and the second position.
[0036] In the embodiment of the present application, since the first position and the second position are known, the target distance between the target object and the mobile law enforcement device can be determined based on the first position and the second position, that is, the first position and the second position can be mapped to a coordinate system, and the first position and the second position can be regarded as the second point in the coordinate system, and the target distance can be determined by the distance calculation formula.
[0037] 103. Obtain a first moving speed of the target object and a second moving speed of the mobile law enforcement device.
[0038] In an embodiment of the present application, the mobile law enforcement device may include a speed sensor, through which a first moving speed of the target object can be obtained, and a second moving speed of the mobile law enforcement device itself can also be detected.
[0039] 104. Determine a first shooting parameter corresponding to the target distance and the target environment parameter.
[0040] In the embodiment of the present application, the first shooting parameter may include at least one of the following: sensitivity, exposure time, focal length, shutter speed, color temperature, exposure compensation parameter, white balance parameter, shooting mode, etc., which are not limited here.
[0041] In a specific implementation, a first shooting parameter corresponding to the target distance and the target environment parameter may be determined, thereby ensuring that the shooting effect is suitable for the distance and the environment, which helps to improve the shooting effect.
[0042] 105. Determine a second shooting parameter corresponding to the first moving speed and the second moving speed.
[0043] In the embodiment of the present application, the second shooting parameter may include at least one of the following: sensitivity, exposure time, focal length, shutter speed, color temperature, exposure compensation parameter, white balance parameter, shooting mode, etc., which are not limited here.
[0044] In a specific implementation, the corresponding second shooting parameter can be determined based on the first moving speed and the second moving speed, which helps to ensure that a clear image of the subsequent target object is obtained and helps to ensure the accuracy of face recognition.
[0045] 106. Photograph the target object according to the first photographing parameter and the second photographing parameter to obtain a first target image.
[0046] In the embodiment of the present application, the target object can be photographed according to the first shooting parameter and the second shooting parameter to obtain a first target image, which can ensure that the background is clear and the target is clear, and help to ensure a complete and clear image, which not only helps with face recognition, but also helps to ensure law enforcement effectiveness.
[0047] 107. Perform face recognition on the first target image to obtain a first target face image.
[0048] In the embodiment of the present application, since the first target image can obtain a clear portrait image of the target object, thereby ensuring the recognition accuracy of the face recognition image, that is, the clarity of the original image is directly related to the recognition accuracy, the face recognition algorithm is then used to perform face recognition on the first target image to obtain the first target face image.
[0049] Optionally, the above step 105, determining the second shooting parameter corresponding to the first moving speed and the second moving speed, may include the following steps:
[0050] 51. Perform vector operation according to the first moving speed and the second moving speed to obtain a target moving speed;
[0051] 52. Determine a first portion of shooting parameters corresponding to the target moving speed;
[0052] 53. Determine the shooting time of the current frame;
[0053] 54. Estimate a third position of the target object at the shooting time according to the first position and the first moving speed;
[0054] 55. Estimate a fourth position of the mobile law enforcement device at the time of shooting according to the second position and the second moving speed;
[0055] 55. Determine a target position parameter between the third position and the fourth position;
[0056] 56. Determine a second part of shooting parameters corresponding to the target orientation parameters;
[0057] 57. Determine the second shooting parameters according to the first part of shooting parameters and the second part of shooting parameters.
[0058] In the embodiment of the present application, since the speed is a vector, it includes not only the magnitude but also the direction. Vector operation can be performed based on the first moving speed and the second moving speed, that is, the resultant vector is calculated to obtain the target moving speed, and the target moving speed can include the magnitude and direction of the speed.
[0059] Among them, since the target moving speed includes the speed magnitude and speed direction, the shooting angle can be adjusted based on the speed direction, and at least one shooting parameter among the shutter speed, exposure duration, exposure compensation parameter, and sensitivity can be adjusted based on the speed magnitude. The first part of the shooting parameters can include at least one of the following: shooting angle, shutter speed, exposure duration, exposure compensation parameter, sensitivity, etc., which are not limited here. The mobile law enforcement equipment can include a pan-tilt device, through which the shooting angle can be adjusted.
[0060] Next, the shooting time of the current frame can be determined. The current frame can be understood as an image frame to be taken. The third position of the target object at the shooting time can be estimated based on the first position and the first moving speed. Since the position can be mapped to a coordinate system, the position change at a certain moment can be determined based on the coordinate system and the corresponding moving speed. Correspondingly, the fourth position of the mobile law enforcement equipment at the shooting time can be estimated based on the second position and the second moving speed. The target orientation parameters between the third position and the fourth position can also be determined. The target orientation parameters may include: the distance between the third position and the fourth position and the orientation angle between the third position and the fourth position.
[0061] Among them, the second part of the shooting parameters may include at least one of the following: focal length, focus, focus area, shooting mode. The second part of the shooting parameters may be related to the distance and azimuth angle. Of course, the second part of the shooting parameters may be related to the background related to the distance and azimuth angle. Different distances may correspond to different shooting parameters, and different backgrounds may also correspond to different shooting parameters. Furthermore, the mapping relationship between the preset azimuth parameters and the shooting parameters can be pre-set, and then the second part of the shooting parameters corresponding to the target azimuth parameters can be determined based on the mapping relationship. Finally, the second shooting parameters can be determined based on the first part of the shooting parameters and the second part of the shooting parameters based on the consideration of two dimensions. In this way, the corresponding shooting parameters can be accurately determined based on the movement and position change, which is helpful to capture clear portrait images, thereby helping to improve the face detection and recognition effects of mobile law enforcement equipment during rapid movement.
[0062] Optionally, the mobile law enforcement device includes a first camera and a second camera, and the above step 106, photographing the target object according to the first shooting parameter and the second shooting parameter to obtain a target image, may include the following steps:
[0063] 61. Shooting with the first camera according to the first shooting parameter at the shooting time to obtain a first image;
[0064] 62. Segment a background area image from the first image;
[0065] 63. Shooting with the second camera according to the second shooting parameter at the shooting time to obtain a second image;
[0066] 64. Segment a target area image from the second image;
[0067] 65. Perform image fusion on the background area image and the target area image to obtain the target image.
[0068] Among them, the first camera and the second camera can be calibrated, that is, the shooting ranges of the first camera and the second camera are consistent. Of course, the overlap between the shooting ranges of the first camera and the second camera is greater than a preset threshold. The set threshold can be pre-set or system default, for example, the set threshold is 96%.
[0069] Among them, the first camera may include an infrared camera or a visible light camera, and the second camera may include an infrared camera or a visible light camera. For example, the first camera and the second camera are both visible light cameras. For another example, the first camera may include an infrared camera, and the second camera may include a visible light camera.
[0070] In an embodiment of the present application, the mobile law enforcement equipment may include a first camera and a second camera. The first camera is responsible for capturing the background, and the second camera is responsible for capturing the portrait. Since the two cameras have different focuses, their shooting parameters are also different. Since the first camera is responsible for capturing the background, it can obtain a clear background image and can segment the background area image from the first image. The second camera is responsible for capturing the portrait. The second camera is then used to shoot according to the second shooting parameters at the time of shooting to obtain a second image, and a target area image is segmented from the second image. In this way, a clear portrait image can be obtained. Then, the background area image and the target area image are fused to obtain a target image. For example, not only a clear background image can be obtained, but also a highly recognizable portrait image can be obtained, which helps to improve the face detection and recognition effects of mobile law enforcement equipment during rapid movement.
[0071] In a specific implementation, during the execution of step 107, the target area image may be used to directly perform face recognition to obtain a first target face image.
[0072] Optionally, the above step 104, determining the first shooting parameter corresponding to the target distance and the target environment parameter, may include the following steps:
[0073] 41. Obtaining default shooting parameters; the default shooting parameters include m shooting parameters, where m is an integer greater than 1;
[0074] 42. Determine initial shooting parameters corresponding to the target distance; the initial shooting parameters include n shooting parameters, where n is an integer less than or equal to m;
[0075] 43. Using the n shooting parameters to update the m shooting parameters, to obtain m target shooting parameters;
[0076] 44. Obtain adjustable shooting parameters and non-adjustable shooting parameters from the m target shooting parameters to obtain p adjustable shooting parameters and q non-adjustable shooting parameters, m=p+q;
[0077] 45. Determine a target adjustment parameter corresponding to the target environmental parameter;
[0078] 46. Adjust the p adjustable shooting parameters according to the target adjustment parameter to obtain p target adjustable shooting parameters;
[0079] 47. Determine the first shooting parameter according to the p target adjustable shooting parameters and the q non-adjustable shooting parameters.
[0080] Different shooting parameters may correspond to different parameter identifiers, and the parameter identifier is used to uniquely identify the type of the shooting parameter.
[0081] In an embodiment of the present application, default shooting parameters can be obtained, and the default shooting parameters include m shooting parameters, where m is an integer greater than 1. A mapping relationship between a preset distance and a shooting parameter can also be pre-stored, and then, an initial shooting parameter corresponding to the target distance can be determined based on the mapping relationship; the initial shooting parameters include n shooting parameters, where n is an integer less than or equal to m, and then, the n shooting parameters can be used to update the m shooting parameters to obtain m target shooting parameters, that is, the n shooting parameters are used to replace the shooting parameters with the same parameter identifier in the m shooting parameters to obtain m target shooting parameters.
[0082] Next, the adjustable shooting parameters and non-adjustable shooting parameters among the m target shooting parameters can be obtained to obtain p adjustable shooting parameters and q non-adjustable shooting parameters, m=p+q, that is, the shooting parameters among all the shooting parameters can be divided into a non-adjustable part and an adjustable part, and a mapping relationship between preset shooting parameters and adjustment parameters can be pre-set, and then the target adjustment parameters corresponding to the target environmental parameters are determined based on the mapping relationship, so that an effect suitable for the environment can be obtained, and the shooting parameters are guaranteed to be suitable for the environmental depth. Finally, the p adjustable shooting parameters can be adjusted according to the target adjustment parameters to obtain p target adjustable shooting parameters, and the first shooting parameters are determined according to the p target adjustable shooting parameters and the q non-adjustable shooting parameters. On the one hand, the shooting parameters can be divided into a non-adjustable part and an adjustable part, and on the other hand, the adjustable part can be adjusted based on the environmental parameters to obtain an effect suitable for the environment, and the shooting parameters are guaranteed to be suitable for the environmental depth, so that a clear background can be ensured.
[0083] Optionally, the following steps may also be included:
[0084] S1, detecting whether the target moving speed is greater than a preset threshold;
[0085] S2, when the target moving speed is greater than the preset threshold, executing the step of determining a second shooting parameter corresponding to the first moving speed and the second moving speed;
[0086] S3, when the target moving speed is less than or equal to the preset threshold, photographing according to the first photographing parameter to obtain a second target image;
[0087] S4. Perform face recognition on the second target image to obtain the second target face image.
[0088] The preset threshold value may be preset or set by system default.
[0089] In an embodiment of the present application, it is possible to detect whether the target moving speed is greater than a preset threshold. When the target moving speed is greater than the preset threshold, it means that the mobile law enforcement device is in a fast-moving state, and the step of determining the second shooting parameter corresponding to the first moving speed and the second moving speed and its subsequent steps can be executed, thereby obtaining a clear portrait image, and then, the background area image and the target area image are fused to obtain the target image. For example, not only a clear background image can be obtained, but also a highly recognizable portrait image can be obtained, which helps to improve the face detection and recognition effect of the mobile law enforcement device during rapid movement.
[0090] In addition, when the target moving speed is less than or equal to the preset threshold, it means that the mobile law enforcement equipment is not in a fast-moving state, and it can be shot according to the first shooting parameters to obtain a second target image, and then the second target image is subjected to face recognition to obtain a second target face image. This can ensure that the mobile law enforcement equipment is not in a fast-moving state, and a clear background image and portrait image can be obtained. A portrait image with high recognition can also be obtained, which helps to improve the face detection and recognition effect of the mobile law enforcement equipment during rapid movement.
[0091] Optionally, the above step 107, performing face recognition on the first target image to obtain a first target face image, may include the following steps:
[0092] 71. Perform image segmentation on the first target image to obtain a target face area image;
[0093] 72. Determine the target blur of the target face area image;
[0094] 73. Determine a target image enhancement algorithm corresponding to the target ambiguity, wherein the target image enhancement algorithm includes a high-frequency image enhancement algorithm and a low-frequency image enhancement algorithm;
[0095] 74. Obtain a first algorithm control parameter corresponding to the high-frequency image enhancement algorithm;
[0096] 75. Obtain a second algorithm control parameter corresponding to the low-frequency image enhancement algorithm;
[0097] 76. Perform multi-scale decomposition on the target face region image to obtain a high-frequency component image and a low-frequency component image;
[0098] 77. Determine a target first algorithm control parameter corresponding to the high-frequency component image, and determine a target second algorithm control parameter corresponding to the low-frequency component image;
[0099] 78. Perform image enhancement on the high-frequency component image according to the target first algorithm control parameter and the high-frequency image enhancement algorithm to obtain a target high-frequency component image, and perform image enhancement on the low-frequency component image according to the target second algorithm control parameter and the low-frequency image enhancement algorithm to obtain a target low-frequency component image;
[0100] 79. Perform an inverse transformation corresponding to the multi-scale decomposition on the target high-frequency component image and the target low-frequency component image to obtain an image-enhanced target face region image, perform face recognition on the image, and obtain the first target face image.
[0101] In an embodiment of the present application, an image segmentation algorithm can be used to perform image segmentation on the first target image to obtain a target face area image. A Gaussian blur detection algorithm can also be used to determine the target blur of the target face area image. The mapping relationship between the preset blur and the image enhancement algorithm can be pre-stored. Then, the target image enhancement algorithm corresponding to the target blur can be determined based on the mapping relationship. The target image enhancement algorithm includes a high-frequency image enhancement algorithm and a low-frequency image enhancement algorithm, that is, the high-frequency and low-frequency parts can be enhanced separately. Since the low frequency represents the main energy part of the image and the high frequency represents the detail part of the image, the characteristics of the two are quite different. Therefore, targeted image enhancement processing based on the characteristics of the two not only helps to enhance the details, but also helps to enhance the main body, so that the details are highlighted and the accuracy of face recognition can be better guaranteed. The enhancement of the main part makes the image fuller.
[0102] Specifically, a first algorithm control parameter corresponding to a high-frequency image enhancement algorithm can be obtained, and a second algorithm control parameter corresponding to a low-frequency image enhancement algorithm can be obtained. Different image enhancement algorithms can correspond to different algorithm control parameters. The algorithm control parameters are used to control the image enhancement effect, that is, the degree of image enhancement, which helps to prevent over-enhancement or under-enhancement and obtain an appropriate depth of image enhancement effect.
[0103] In a specific implementation, the target face region image can be multi-scale decomposed to obtain a high-frequency component image and a low-frequency component image. Based on the characteristics of the high-frequency component image, the target first algorithm control parameter corresponding to the high-frequency component image can be determined. Based on the characteristics of the low-frequency component image, the target second algorithm control parameter corresponding to the low-frequency component image can be determined. Then, the high-frequency component image is specifically enhanced according to the target first algorithm control parameter and the high-frequency image enhancement algorithm to obtain the target high-frequency component image. The low-frequency component image is enhanced according to the target second algorithm control parameter and the low-frequency image enhancement algorithm to obtain the target low-frequency component image. Finally, the target high-frequency component image and the target low-frequency component image are inversely transformed corresponding to the multi-scale decomposition to obtain the enhanced target face region image, which is then subjected to face recognition to obtain the first target face image. In this way, since the low frequency represents the main energy part of the image and the high frequency represents the detail part of the image, the characteristics of the two are quite different. Therefore, the targeted image enhancement processing according to the characteristics of the two is not only helpful for detail enhancement, but also for main enhancement, so that the details are highlighted and the accuracy of face recognition can be better guaranteed, while the main part is enhanced to make the image fuller.
[0104] Optionally, the above step 77, determining the target first algorithm control parameter corresponding to the high-frequency component image, and determining the target second algorithm control parameter corresponding to the low-frequency component image, may include the following steps:
[0105] 771. Determine a first energy ratio between the high-frequency component image and the target face region image;
[0106] 772. Determine the distribution density of target feature points of the high-frequency component image;
[0107] 773. Determine a target adjustment coefficient corresponding to the first energy ratio, and determine a target fine-tuning coefficient corresponding to the target feature point distribution density;
[0108] 774. Adjust the first algorithm control parameter according to the target adjustment coefficient and the target fine-tuning coefficient to obtain a target first algorithm control parameter;
[0109] 775. Determine a target signal-to-noise ratio corresponding to the low-frequency component image;
[0110] 776. Determine a reference optimization coefficient corresponding to the target signal-to-noise ratio;
[0111] 777. Determine a target interference factor corresponding to the first energy ratio;
[0112] 778. Use the target interference factor to interfere with the reference optimization coefficient to obtain a target optimization coefficient;
[0113] 779. Optimize the second algorithm control parameters according to the target optimization coefficient to obtain target second algorithm control parameters.
[0114] In an embodiment of the present application, a first energy ratio between a high-frequency component image and a target facial area image can be determined, and a target feature point distribution density of the high-frequency component image can also be determined. A mapping relationship between a preset energy ratio and an adjustment coefficient can be pre-stored, and a target adjustment coefficient corresponding to the first energy ratio can be determined based on the mapping relationship. A mapping relationship between a preset feature point distribution density and a fine-tuning coefficient can also be pre-stored, and a target fine-tuning coefficient corresponding to the target feature point distribution density can be determined based on the mapping relationship, wherein the value range of the adjustment coefficient can be -0.2 to 0.2, and the value range of the fine-tuning coefficient can be -0.05 to 0.05. Next, the first algorithm control parameter can be adjusted according to the target adjustment coefficient and the target fine-tuning coefficient to obtain the target first algorithm control parameter. Specifically, the target first algorithm control parameter = (1 + target adjustment coefficient) * (1 + target fine-tuning coefficient) * first algorithm control parameter. Different energy ratios reflect the richness of details, and the feature point distribution density reflects the distribution degree of details. Therefore, the corresponding algorithm control parameters can be adjusted based on the richness of details to ensure that the details are enriched, and then the algorithm control parameters can be dynamically fine-tuned based on the distribution degree of details, so that the richness of details is further converged, thereby ensuring the high-frequency image enhancement effect.
[0115] Furthermore, the target signal-to-noise ratio corresponding to the low-frequency component image can be determined, and then, according to the mapping relationship between the preset signal-to-noise ratio and the optimization coefficient, the reference optimization coefficient corresponding to the target signal-to-noise ratio can be determined based on the mapping relationship. The target interference factor corresponding to the first energy ratio can also be determined, that is, the mapping relationship between the preset energy ratio and the interference factor can be pre-stored, and the target interference factor corresponding to the first energy ratio can be determined based on the mapping relationship. The setting of the interference factor can make the high frequency and the low frequency restrain each other, that is, ensure consistency, avoid over-enhancement or under-enhancement of one of the low frequency and the high frequency, and use the target interference factor to obtain the target interference factor. The factor interferes with the reference optimization coefficient to obtain the target optimization coefficient. In the specific implementation, the target optimization coefficient = reference optimization coefficient + (1 + target interference factor), the value range of the interference factor can be between -0.3 and 0.3. Finally, the second algorithm control parameters can be optimized according to the target optimization coefficient to obtain the target second algorithm control parameters. In this way, the image enhancement effect of the low-frequency part can be made suitable for its own characteristics, and the setting of the interference factor can also be used to make the high frequency and the low frequency restrain each other, that is, to ensure consistency and avoid over-enhancement or under-enhancement of one of the low frequency and high frequency, thereby ensuring the accuracy of subsequent face recognition.
[0116] It can be seen that the face detection and recognition method for the fast-moving mobile law enforcement device described in the embodiment of the present application is applied to the mobile law enforcement device to determine the first position of the target object and the second position of the mobile law enforcement device; obtain the target environment parameters of the first position, determine the target distance between the target object and the mobile law enforcement device according to the first position and the second position, obtain the first moving speed of the target object and the second moving speed of the mobile law enforcement device, determine the first shooting parameters corresponding to the target distance and the target environment parameters, determine the second shooting parameters corresponding to the first moving speed and the second moving speed, shoot the target object according to the first shooting parameters and the second shooting parameters to obtain a first target image, perform face recognition on the first target image to obtain a first target face image. First, the first shooting parameters corresponding to the target distance and the target environment parameters can be determined, thereby ensuring The shooting effect is suitable for the distance and the environment, which helps to improve the shooting effect. Secondly, determining the corresponding second shooting parameters based on the first moving speed and the second moving speed helps to ensure that the subsequent target object obtains a clear image, which helps to ensure the accuracy of face recognition. Finally, the target object is photographed according to the first shooting parameters and the second shooting parameters to obtain a first target image, which can ensure that the background is clear and the target is clear, which helps to ensure a complete and clear image. Since the first target image can obtain a clear portrait image of the target object, the recognition accuracy of the face recognition image is guaranteed, that is, the clarity of the original image is directly related to the recognition accuracy. Then, face recognition is performed on the first target image to obtain a first target face image, which not only helps face recognition, but also helps to ensure law enforcement results, and helps to improve the face detection and recognition effects of mobile law enforcement equipment during rapid movement.
[0117] In accordance with the above embodiment, please refer to Figure 2 , Figure 3 1 is a structural diagram of a mobile law enforcement device provided in an embodiment of the present application. As shown in the figure, the mobile law enforcement device includes a processor, a memory, a communication interface, and one or more programs. The one or more programs are stored in the memory and configured to be executed by the processor. In the embodiment of the present application, the program includes instructions for executing the following steps:
[0118] Determine a first position of a target object and a second position of the mobile law enforcement device; obtain target environmental parameters of the first position;
[0119] determining a target distance between the target object and the mobile law enforcement device based on the first position and the second position;
[0120] Acquire a first moving speed of the target object and a second moving speed of the mobile law enforcement device;
[0121] Determining a first shooting parameter corresponding to the target distance and the target environment parameter;
[0122] determining a second shooting parameter corresponding to the first moving speed and the second moving speed;
[0123] photographing the target object according to the first photographing parameter and the second photographing parameter to obtain a first target image;
[0124] Perform face recognition on the first target image to obtain a first target face image.
[0125] Optionally, in determining the second shooting parameter corresponding to the first moving speed and the second moving speed, the program includes instructions for performing the following steps:
[0126] Performing vector operation according to the first moving speed and the second moving speed to obtain a target moving speed;
[0127] Determining a first portion of shooting parameters corresponding to the target moving speed;
[0128] Determine the shooting time of the current frame;
[0129] estimating a third position of the target object at the shooting moment according to the first position and the first moving speed;
[0130] estimating a fourth position of the mobile law enforcement device at the time of shooting according to the second position and the second moving speed;
[0131] determining a target position parameter between the third position and the fourth position;
[0132] Determining a second portion of shooting parameters corresponding to the target orientation parameters;
[0133] The second shooting parameters are determined according to the first part of shooting parameters and the second part of shooting parameters.
[0134] Optionally, the mobile law enforcement device includes a first camera and a second camera, and in terms of photographing the target object according to the first shooting parameter and the second shooting parameter to obtain a target image, the program includes instructions for executing the following steps:
[0135] Taking a picture at the shooting time according to the first shooting parameter by the first camera to obtain a first image;
[0136] Segmenting a background area image from the first image;
[0137] capturing, by the second camera, at the capturing time according to the second capturing parameter to obtain a second image;
[0138] Segmenting a target area image from the second image;
[0139] The background area image and the target area image are fused to obtain the target image.
[0140] Optionally, in determining the first shooting parameter corresponding to the target distance and the target environment parameter, the program includes instructions for performing the following steps:
[0141] Obtaining default shooting parameters; the default shooting parameters include m shooting parameters, where m is an integer greater than 1;
[0142] Determine initial shooting parameters corresponding to the target distance; the initial shooting parameters include n shooting parameters, where n is an integer less than or equal to m;
[0143] Using the n shooting parameters to update the m shooting parameters, to obtain m target shooting parameters;
[0144] Obtaining adjustable shooting parameters and non-adjustable shooting parameters from the m target shooting parameters to obtain p adjustable shooting parameters and q non-adjustable shooting parameters, m=p+q;
[0145] Determining a target adjustment parameter corresponding to the target environmental parameter;
[0146] Adjust the p adjustable shooting parameters according to the target adjustment parameter to obtain p target adjustable shooting parameters;
[0147] The first shooting parameter is determined according to the p target adjustable shooting parameters and the q non-adjustable shooting parameters.
[0148] Optionally, the program further includes instructions for executing the following steps:
[0149] Detecting whether the target moving speed is greater than a preset threshold;
[0150] When the target moving speed is greater than the preset threshold, performing the step of determining a second shooting parameter corresponding to the first moving speed and the second moving speed;
[0151] When the target moving speed is less than or equal to the preset threshold, photographing according to the first photographing parameter to obtain a second target image;
[0152] Perform face recognition on the second target image to obtain the second target face image.
[0153] It can be seen that the mobile law enforcement equipment described in the embodiment of the present application determines the first position of the target object and the second position of the mobile law enforcement equipment; obtains the target environment parameters of the first position, determines the target distance between the target object and the mobile law enforcement equipment based on the first position and the second position, obtains the first moving speed of the target object and the second moving speed of the mobile law enforcement equipment, determines the first shooting parameters corresponding to the target distance and the target environment parameters, determines the second shooting parameters corresponding to the first moving speed and the second moving speed, shoots the target object according to the first shooting parameters and the second shooting parameters to obtain a first target image, performs face recognition on the first target image to obtain a first target face image. First, the first shooting parameters corresponding to the target distance and the target environment parameters can be determined, thereby ensuring that the shooting effect is suitable for the distance and the environment. , which helps to improve the shooting effect. Secondly, determining the corresponding second shooting parameters based on the first moving speed and the second moving speed helps to ensure that the subsequent target object obtains a clear image, which helps to ensure the accuracy of face recognition. Finally, the target object is photographed according to the first shooting parameters and the second shooting parameters to obtain a first target image, which can ensure that the background is clear and the target is clear, which helps to ensure a complete and clear image. Since the first target image can obtain a clear portrait image of the target object, the recognition accuracy of the face recognition image is guaranteed, that is, the clarity of the original image is directly related to the recognition accuracy. Then, face recognition is performed on the first target image to obtain a first target face image, which not only helps face recognition, but also helps to ensure law enforcement effects, and helps to improve the face detection and recognition effects of mobile law enforcement equipment during rapid movement.
[0154] Figure 3 1 is a functional unit block diagram of a face detection and recognition system 300 for a mobile law enforcement device in rapid motion involved in an embodiment of the present application, which is applied to a mobile law enforcement device. The face detection and recognition system 300 for a mobile law enforcement device in rapid motion includes:
[0155] The determination unit 301 is used to determine a first position of a target object and a second position of the mobile law enforcement device; and obtain target environment parameters of the first position;
[0156] The determining unit 301 is further configured to determine a target distance between the target object and the mobile law enforcement device according to the first position and the second position;
[0157] An acquisition unit 302 is used to acquire a first moving speed of the target object and a second moving speed of the mobile law enforcement device;
[0158] The determining unit 301 is further configured to determine a first shooting parameter corresponding to the target distance and the target environment parameter; and determine a second shooting parameter corresponding to the first moving speed and the second moving speed;
[0159] A shooting unit 303, configured to shoot the target object according to the first shooting parameter and the second shooting parameter to obtain a first target image;
[0160] The recognition unit 304 is configured to perform face recognition on the first target image to obtain a first target face image.
[0161] Optionally, in determining the second shooting parameter corresponding to the first moving speed and the second moving speed, the determining unit 301 is specifically configured to:
[0162] Performing vector operation according to the first moving speed and the second moving speed to obtain a target moving speed;
[0163] Determining a first portion of shooting parameters corresponding to the target moving speed;
[0164] Determine the shooting time of the current frame;
[0165] estimating a third position of the target object at the shooting moment according to the first position and the first moving speed;
[0166] estimating a fourth position of the mobile law enforcement device at the time of shooting according to the second position and the second moving speed;
[0167] determining a target position parameter between the third position and the fourth position;
[0168] Determining a second portion of shooting parameters corresponding to the target orientation parameters;
[0169] The second shooting parameters are determined according to the first part of shooting parameters and the second part of shooting parameters.
[0170] Optionally, the mobile law enforcement device includes a first camera and a second camera, and in photographing the target object according to the first shooting parameter and the second shooting parameter to obtain the target image, the photographing unit 303 is specifically used to:
[0171] Taking a picture at the shooting time according to the first shooting parameter by the first camera to obtain a first image;
[0172] Segmenting a background area image from the first image;
[0173] capturing, by the second camera, at the capturing time according to the second capturing parameter to obtain a second image;
[0174] Segmenting a target area image from the second image;
[0175] The background area image and the target area image are fused to obtain the target image.
[0176] Optionally, in determining the first shooting parameter corresponding to the target distance and the target environment parameter, the determining unit 301 is specifically configured to:
[0177] Obtaining default shooting parameters; the default shooting parameters include m shooting parameters, where m is an integer greater than 1;
[0178] Determine initial shooting parameters corresponding to the target distance; the initial shooting parameters include n shooting parameters, where n is an integer less than or equal to m;
[0179] Using the n shooting parameters to update the m shooting parameters, to obtain m target shooting parameters;
[0180] Obtaining adjustable shooting parameters and non-adjustable shooting parameters from the m target shooting parameters to obtain p adjustable shooting parameters and q non-adjustable shooting parameters, m=p+q;
[0181] Determining a target adjustment parameter corresponding to the target environmental parameter;
[0182] Adjust the p adjustable shooting parameters according to the target adjustment parameter to obtain p target adjustable shooting parameters;
[0183] The first shooting parameter is determined according to the p target adjustable shooting parameters and the q non-adjustable shooting parameters.
[0184] Optionally, the face detection and recognition system 300 for the mobile law enforcement device in rapid motion is further specifically used for:
[0185] Detecting whether the target moving speed is greater than a preset threshold;
[0186] When the target moving speed is greater than the preset threshold, performing the step of determining a second shooting parameter corresponding to the first moving speed and the second moving speed;
[0187] When the target moving speed is less than or equal to the preset threshold, photographing according to the first photographing parameter to obtain a second target image;
[0188] Perform face recognition on the second target image to obtain the second target face image.
[0189] It can be seen that the face detection and recognition system for the fast-moving mobile law enforcement equipment described in the embodiment of the present application is applied to the mobile law enforcement equipment to determine the first position of the target object and the second position of the mobile law enforcement equipment; obtain the target environment parameters of the first position, determine the target distance between the target object and the mobile law enforcement equipment according to the first position and the second position, obtain the first moving speed of the target object and the second moving speed of the mobile law enforcement equipment, determine the first shooting parameters corresponding to the target distance and the target environment parameters, determine the second shooting parameters corresponding to the first moving speed and the second moving speed, shoot the target object according to the first shooting parameters and the second shooting parameters to obtain a first target image, perform face recognition on the first target image to obtain a first target face image. First, the first shooting parameters corresponding to the target distance and the target environment parameters can be determined, thereby ensuring The shooting effect is suitable for the distance and the environment, which helps to improve the shooting effect. Secondly, determining the corresponding second shooting parameters based on the first moving speed and the second moving speed helps to ensure that the subsequent target object obtains a clear image, which helps to ensure the accuracy of face recognition. Finally, the target object is photographed according to the first shooting parameters and the second shooting parameters to obtain a first target image, which can ensure that the background is clear and the target is clear, which helps to ensure a complete and clear image. Since the first target image can obtain a clear portrait image of the target object, the recognition accuracy of the face recognition image is guaranteed, that is, the clarity of the original image is directly related to the recognition accuracy. Then, face recognition is performed on the first target image to obtain a first target face image, which not only helps face recognition, but also helps to ensure law enforcement results, and helps to improve the face detection and recognition effects of mobile law enforcement equipment during rapid movement.
[0190] It can be seen that the functions of each program module of the face detection and recognition system for the mobile law enforcement equipment in rapid motion described in the embodiments of the present application can be specifically implemented according to the methods in the above-mentioned method embodiments. The specific implementation process can refer to the relevant description of the above-mentioned method embodiments, which will not be repeated here.
[0191] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments.
[0192] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the above method embodiment. The computer program product may be a software installation package.
[0193] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0194] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0195] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0196] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0197] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0198] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.
[0199] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.
[0200] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for general technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A method for detecting and identifying faces in fast-moving mobile law enforcement equipment, characterized in that: Applied to mobile law enforcement equipment, the method comprises: Determine a first position of a target object and a second position of the mobile law enforcement device; obtain target environmental parameters of the first position; determining a target distance between the target object and the mobile law enforcement device based on the first position and the second position; Acquire a first moving speed of the target object and a second moving speed of the mobile law enforcement device; Determining a first shooting parameter corresponding to the target distance and the target environment parameter; determining a second shooting parameter corresponding to the first moving speed and the second moving speed; photographing the target object according to the first photographing parameter and the second photographing parameter to obtain a first target image; Performing face recognition on the first target image to obtain a first target face image; Wherein, determining the second shooting parameter corresponding to the first moving speed and the second moving speed includes: Performing vector operation according to the first moving speed and the second moving speed to obtain a target moving speed; Determining a first portion of shooting parameters corresponding to the target moving speed; Determine the shooting time of the current frame; estimating a third position of the target object at the shooting moment according to the first position and the first moving speed; estimating a fourth position of the mobile law enforcement device at the time of shooting according to the second position and the second moving speed; determining a target position parameter between the third position and the fourth position; Determining a second portion of shooting parameters corresponding to the target orientation parameters; Determine the second shooting parameter according to the first part of shooting parameters and the second part of shooting parameters; The mobile law enforcement device includes a first camera and a second camera, and photographing the target object according to the first photographing parameter and the second photographing parameter to obtain a target image includes: Taking a picture at the shooting time according to the first shooting parameter by the first camera to obtain a first image; Segmenting a background area image from the first image; capturing, by the second camera, at the capturing time according to the second capturing parameter to obtain a second image; Segmenting a target area image from the second image; The background area image and the target area image are fused to obtain the target image.
2. The method according to claim 1, characterized in that: The determining of a first shooting parameter corresponding to the target distance and the target environment parameter includes: Obtaining default shooting parameters; the default shooting parameters include m shooting parameters, where m is an integer greater than 1; Determine initial shooting parameters corresponding to the target distance; the initial shooting parameters include n shooting parameters, where n is an integer less than or equal to m; Using the n shooting parameters to update the m shooting parameters, to obtain m target shooting parameters; Obtaining adjustable shooting parameters and non-adjustable shooting parameters from the m target shooting parameters, to obtain p adjustable shooting parameters and q non-adjustable shooting parameters, m=p+q; Determining a target adjustment parameter corresponding to the target environmental parameter; Adjust the p adjustable shooting parameters according to the target adjustment parameter to obtain p target adjustable shooting parameters; The first shooting parameter is determined according to the p target adjustable shooting parameters and the q non-adjustable shooting parameters.
3. The method according to claim 1, characterized in that The method further comprises: Detecting whether the target moving speed is greater than a preset threshold; When the target moving speed is greater than the preset threshold, performing the step of determining a second shooting parameter corresponding to the first moving speed and the second moving speed; When the target moving speed is less than or equal to the preset threshold, photographing according to the first photographing parameter to obtain a second target image; Perform face recognition on the second target image to obtain a second target face image.
4. A face detection and recognition system for mobile law enforcement equipment in rapid motion, characterized in that: Applied to mobile law enforcement equipment, the system comprises: A determination unit, configured to determine a first position of a target object and a second position of the mobile law enforcement device; and obtain target environment parameters of the first position; The determining unit is further used to determine a target distance between the target object and the mobile law enforcement device according to the first position and the second position; An acquisition unit, configured to acquire a first moving speed of the target object and a second moving speed of the mobile law enforcement device; The determining unit is further configured to determine a first shooting parameter corresponding to the target distance and the target environment parameter; and determine a second shooting parameter corresponding to the first moving speed and the second moving speed; a photographing unit, configured to photograph the target object according to the first photographing parameter and the second photographing parameter to obtain a first target image; A recognition unit, configured to perform face recognition on the first target image to obtain a first target face image; Wherein, in determining the second shooting parameter corresponding to the first moving speed and the second moving speed, the determining unit is specifically used to: Performing vector operation according to the first moving speed and the second moving speed to obtain a target moving speed; Determining a first portion of shooting parameters corresponding to the target moving speed; Determine the shooting time of the current frame; estimating a third position of the target object at the shooting moment according to the first position and the first moving speed; estimating a fourth position of the mobile law enforcement device at the time of shooting according to the second position and the second moving speed; determining a target position parameter between the third position and the fourth position; Determining a second portion of shooting parameters corresponding to the target orientation parameters; Determine the second shooting parameter according to the first part of shooting parameters and the second part of shooting parameters; Wherein, the mobile law enforcement device includes a first camera and a second camera, and in terms of photographing the target object according to the first photographing parameter and the second photographing parameter to obtain the target image, the photographing unit is specifically used for: Taking a picture at the shooting time according to the first shooting parameter by the first camera to obtain a first image; Segmenting a background area image from the first image; capturing, by the second camera, at the capturing time according to the second capturing parameter to obtain a second image; Segmenting a target area image from the second image; The background area image and the target area image are fused to obtain the target image.
5. The system according to claim 4, characterized in that In the aspect of determining the first shooting parameter corresponding to the target distance and the target environment parameter, the determining unit is specifically used to: Obtaining default shooting parameters; the default shooting parameters include m shooting parameters, where m is an integer greater than 1; Determine initial shooting parameters corresponding to the target distance; the initial shooting parameters include n shooting parameters, where n is an integer less than or equal to m; Using the n shooting parameters to update the m shooting parameters, to obtain m target shooting parameters; Obtaining adjustable shooting parameters and non-adjustable shooting parameters from the m target shooting parameters, to obtain p adjustable shooting parameters and q non-adjustable shooting parameters, m=p+q; Determining a target adjustment parameter corresponding to the target environmental parameter; Adjust the p adjustable shooting parameters according to the target adjustment parameter to obtain p target adjustable shooting parameters; The first shooting parameter is determined according to the p target adjustable shooting parameters and the q non-adjustable shooting parameters.
6. The system according to claim 4, characterized in that The system is also specifically used for: Detecting whether the target moving speed is greater than a preset threshold; When the target moving speed is greater than the preset threshold, performing the step of determining a second shooting parameter corresponding to the first moving speed and the second moving speed; When the target moving speed is less than or equal to the preset threshold, photographing according to the first photographing parameter to obtain a second target image; Perform face recognition on the second target image to obtain a second target face image.
