Facial detection method and apparatus, and computer device and storage medium

Abstract

The present application relates to the technical field of computer vision. Specifically provided are a facial detection method and apparatus, and a computer device and a storage medium, which aim to solve the technical problem of the stability of existing pure-vision facial recognition methods being insufficient. For this purpose, the facial detection method in the present application comprises: acquiring an occupant image of an intelligent device and a local pose of an occupant user; on the basis of the local pose, determining whether the pose of the user changes; if the pose of the user changes, performing facial detection on the basis of the occupant image, so as to obtain a first facial detection result; and determining a second facial detection result on the basis of the first facial detection result and the local pose. Thus, the facial recognition effect and stability are improved.

Description

Face detection method, device, computer equipment and storage medium

[0001] This application claims priority to Chinese patent application CN202410234179.0, filed on February 29, 2024, entitled “Face Detection Method, Device, Computer Equipment and Storage Medium”. The entire contents of the above Chinese patent application are incorporated into this application by reference. Technical Field

[0002] The present application relates to the field of computer vision technology, and specifically provides a face detection method, apparatus, computer equipment, and storage medium. Background Art

[0003] With the widespread application of biometric technology in human-computer interaction and identity authentication, as well as the increasing demand for customized services within intelligent cockpits, in-vehicle facial recognition capabilities have become a key factor. A stable and effective facial recognition result is essential for attracting users to use facial recognition.

[0004] Existing face recognition solutions basically use pure visual face recognition. This method is generally subject to significant limitations such as the angle and lighting of the scene. When the user's posture angle is too large, the face cannot be recognized, resulting in insufficient recognition stability and limited user personalized services.

[0005] Accordingly, a new face detection solution is needed in this field to solve the above problems.

[0006] Application Contents

[0007] In order to overcome the above-mentioned defects, the present application is proposed to provide a solution or at least partially solve the technical problem of insufficient stability of existing purely visual face recognition methods. The present application provides a face detection method, apparatus, computer device and storage medium.

[0008] In a first aspect, the present application provides a face detection method, the method comprising:

[0009] Obtain the in-cabin image of the smart device and the local posture of the user in the cabin;

[0010] Determining whether a posture change occurs to the user based on the local posture;

[0011] If yes, perform face detection based on the cabin image to obtain a first face detection result;

[0012] A second face detection result is determined based on the first face detection result and the local pose.

[0013] In one embodiment of the present application, determining whether the user's posture changes based on the local posture includes:

[0014] Comparing the local pose with a preset pose;

[0015] Based on the comparison result, it is determined whether the user's posture changes.

[0016] In one embodiment of the present application, determining the second face detection result based on the first face detection result and the local pose includes:

[0017] Matching the first face detection result with the local pose;

[0018] The second face detection result is determined based on the matching result.

[0019] In one embodiment of the present application, determining the second face detection result based on the matching result includes:

[0020] In a case where the first face detection result matches the local pose, using the first face detection result as the second face detection result;

[0021] In a case where the first face detection result does not match the local posture, a third face detection result is obtained, and the second face detection result is determined based on the third face detection result.

[0022] In one embodiment of the present application, the third face detection result includes a historical face detection result;

[0023] The determining of the second face detection result based on the third face detection result includes: matching the historical face detection result with the local posture, and when the historical face detection result matches the local posture, using the historical face detection result as the second face detection result; otherwise, re-performing face detection within a first preset time range until the second face detection result is obtained.

[0024] In one embodiment of the present application, the third face detection result includes a face detection result obtained after re-face detection;

[0025] Determining the second face detection result based on the third face detection result includes: re-performing face detection within a second preset time range, and using the face detection result obtained after the re-face detection as the second face detection result when the face detection result obtained after the re-face detection matches the local posture.

[0026] In one embodiment of the present application, the local posture of the user in the cabin includes at least one of the user's position and the user's head posture.

[0027] In a second aspect, the present application provides a face detection device, comprising:

[0028] an acquisition module configured to acquire an in-cabin image of the smart device and a local posture of a user in the cabin;

[0029] a judgment module, configured to judge whether a posture change of the user occurs based on the local posture;

[0030] a detection module, the detection module being configured to perform face detection based on the in-cabin image to obtain a first face detection result when the user's posture changes;

[0031] A determination module is configured to determine a second face detection result based on the first face detection result and the local pose.

[0032] In a third aspect, a computer device is provided, comprising at least one processor and at least one memory, wherein the memory is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute any of the aforementioned face detection methods.

[0033] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored in the computer-readable storage medium, wherein the program codes are suitable for being loaded and run by a processor to execute any of the aforementioned face detection methods.

[0034] The above one or more technical solutions of this application have at least one or more of the following beneficial effects:

[0035] The face detection method in this application includes: obtaining an in-cabin image and the local position of a user in the cabin from a smart device; determining whether the user's position has changed based on the local position; if so, performing face detection based on the in-cabin image to obtain a first face detection result; and determining a second face detection result based on the first face detection result and the local position. This improves the effectiveness and stability of face recognition while ensuring user information security. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The disclosure of this application will be more easily understood with reference to the accompanying drawings. Those skilled in the art will readily appreciate that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this application. Furthermore, similar numbers in the figures represent similar components, where:

[0037] FIG1 is a schematic flow chart of the main steps of a face detection method according to an embodiment of the present application;

[0038] FIG2 is a schematic diagram of a stability processing flow of face recognition in one embodiment of the present application;

[0039] FIG3 is a schematic diagram of a complete process for improving the stability of face recognition in one embodiment of the present application;

[0040] FIG4 is a schematic diagram of a process of triggering face detection by a seat sensor signal change in one embodiment of the present application;

[0041] FIG5 is a schematic diagram of a process of triggering face detection by head posture changes in one embodiment of the present application;

[0042] FIG6 is a schematic block diagram of the main structure of a face detection device according to an embodiment of the present application;

[0043] FIG7 is a schematic diagram of the structure of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0044] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the scope of protection of the present application.

[0045] In the description of this application, "module" and "processor" may include hardware, software, or a combination of both. A module may include hardware circuitry, various suitable sensors, communication ports, and memory. It may also include software components, such as program code, or a combination of software and hardware. A processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. A processor has data and / or signal processing capabilities. A processor may be implemented in software, hardware, or a combination of both. Non-transitory computer-readable storage media include any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" refers to all possible combinations of A and B, such as only A, only B, or both A and B. The terms "at least one of A or B" or "at least one of A and B" have similar meanings to "A and / or B" and may include only A, only B, or both A and B. The singular forms "a" and "the" may also include the plural forms.

[0046] Currently, traditional facial recognition solutions rely primarily on pure visual recognition. This method is often subject to significant limitations, such as scene angles and lighting. Face recognition can be incapable of detection when users are posing at excessive angles, resulting in insufficient recognition stability and limited personalized user services. Furthermore, caching facial recognition results can improve user experience in various scenarios. For example, in facial recognition payment scenarios, caching facial recognition results can achieve faster responses. However, this can also lead to significant financial security incidents.

[0047] To this end, this application proposes a face detection method, apparatus, computer device, and storage medium. The method includes: obtaining an in-cabin image and the local position of a user in the cabin from a smart device; determining whether the user's position has changed based on the local position; if so, performing face detection based on the in-cabin image to obtain a first face detection result; and determining a second face detection result based on the first face detection result and the local position. This improves the face recognition effect while ensuring the security of user information and enhances the stability of face recognition.

[0048] The smart devices described in this application may include driving devices, smart vehicles and other devices.

[0049] In order to make the objectives, technical solutions and advantages of this application more clearly understood, the following, in conjunction with the accompanying drawings and embodiments, uses a smart vehicle as an example of a smart device to describe the face detection method of the present application in detail. It should be understood by those skilled in the art that the specific embodiments described herein are only used to explain this application and are not intended to limit the face detection method described in this application to using a smart vehicle as a smart device.

[0050] Please refer to Figure 1, which is a schematic flow chart of the main steps of a face detection method according to an embodiment of the present application.

[0051] As shown in FIG1 , the face detection method in the embodiment of the present application mainly includes the following steps S101 to S104 .

[0052] Step S101: Acquire the in-cabin image of the smart device and the local posture of the user in the cabin.

[0053] The video stream inside the smart vehicle cabin is captured by an image capture device set at a preset position inside the vehicle, and the video stream is framed to obtain an image inside the cabin. For example, the above the rearview mirror inside the vehicle can be used as an example of the preset position.

[0054] An OMS (Occupant monitor system) camera can be used as an example of the image acquisition device. The OMS camera can be an RGB camera or an RGB-IR camera.

[0055] The local posture of the user in the cabin refers to the posture of the user in the local environment of the vehicle, such as the specific position and posture of the user in the vehicle. In a specific embodiment of the present application, the local posture of the user in the cabin includes at least one of the user's position and the user's head posture.

[0056] In one embodiment, the local position of the user can be obtained by detecting and tracking the obtained in-cabin image. In another embodiment, the local position of the user can also be directly obtained by using a sensor set at a preset position.

[0057] Step S102: determining whether the user's posture changes based on the local posture.

[0058] Step S103: If yes, perform face detection based on the cabin image to obtain a first face detection result.

[0059] Specifically, face detection can be performed on the cabin image through computer vision or machine learning algorithms to obtain the first face detection result.

[0060] Step S104: Determine a second face detection result based on the first face detection result and the local pose.

[0061] Since the first face detection result is obtained through pure visual detection, its stability and security are relatively low. Therefore, this step can be used to further determine a final face detection result with higher stability.

[0062] Based on steps S101-S104, the system first obtains an in-cabin image and the local position of the user in the cabin from the smart device. Based on the local position, it determines whether the user's position has changed. If so, face detection is performed based on the in-cabin image to obtain a first face detection result. A second face detection result is determined based on the first face detection result and the local position. This improves the face recognition performance and stability while ensuring user information security.

[0063] The above steps S102 and S104 are further described below.

[0064] Regarding step S102, it can be specifically implemented through the following steps S1021 to S1022.

[0065] Step S1021: Compare the local posture with a preset posture.

[0066] The preset posture is a preset posture threshold, which can be obtained in advance through experiments. At the same time, the preset posture can be adjusted or modified according to different scenarios.

[0067] Step S1022: Determine whether the user's posture changes based on the comparison result.

[0068] Specifically, whether the user's posture changes is determined by comparing the local posture with the preset posture.

[0069] For example, taking the user's specific position in the car as the local posture, the actual pressure value of the pressure sensor set on a certain parking space can be obtained, and the actual pressure value can be compared with the preset pressure threshold. When the actual pressure value is less than the preset pressure threshold, it means that the user has left the seat, indicating that the user's posture on the seat has changed.

[0070] The above is a further description of step S102 , and the following further describes step S104 .

[0071] Regarding step S104, it can be specifically implemented through the following steps S1041 to S1042.

[0072] Step S1041: Match the first face detection result with the local pose.

[0073] Specifically, the facial detection results (first face detection results) for each user in the vehicle are matched with the detected local poses. For example, using the user's specific position in the vehicle as the local pose, this matching process determines whether there is a corresponding first face detection result at each detected user position.

[0074] Step S1042: Determine the second face detection result based on the matching result.

[0075] Step S10421: When the first face detection result matches the local posture, the first face detection result is used as the second face detection result.

[0076] Specifically, when the face detection result (first face detection result) of each user detected in the vehicle completely matches the local posture, the process is terminated and the first face detection result is used as the final face detection result (second face detection result).

[0077] Step S10422: When the first face detection result does not match the local posture, obtain a third face detection result, and determine the second face detection result based on the third face detection result.

[0078] In a specific embodiment of the present application, the third face detection result includes a historical face detection result; determining the second face detection result based on the third face detection result includes: matching the historical face detection result with the local posture, and when the historical face detection result matches the local posture, using the historical face detection result as the second face detection result; otherwise, re-performing face detection within a first preset time range until the second face detection result is obtained.

[0079] The historical face detection result is actually the second face detection result obtained by the last face detection performed and stored in the database.

[0080] The first preset time range is a time threshold obtained in advance through experiments, and can be adaptively adjusted according to actual scenarios.

[0081] Specifically, when the first face detection result at a certain position does not match the local posture, first try to use the historical face detection result in the cache to update the face detection result at the current position, and then judge again whether the face recognition is successful at each position. If so, end the process, otherwise retry the recognition within the first preset time range until the second face detection result is obtained and the face recognition result in the cache is updated. At this time, the second face detection result completely matches the local posture.

[0082] In a specific embodiment of the present application, the third face detection result includes a face detection result obtained after re-face detection; determining the second face detection result based on the third face detection result includes: re-performing face detection within a second preset time range, and when the face detection result obtained after the re-face detection matches the local posture, using the face detection result obtained after the re-face detection as the second face detection result.

[0083] The second preset time range is a time threshold obtained in advance through experiments, and can be adaptively adjusted according to actual scenarios.

[0084] Specifically, when the first face detection result at a certain position does not match the local posture, the detection request can be re-triggered, and the new detection result can be matched with the local posture until the two match. The face detection result obtained after the re-face detection is used as the second face detection result.

[0085] It should be noted that the face detection results (including the first face detection result, the second face detection result, and the third face detection result) in this embodiment refer to the detection of a user in the vehicle cabin.

[0086] The first face detection result is obtained by using a commonly used face detection method to detect the cabin image obtained by the camera. It is the initial face detection result. There may be situations where the detection accuracy is not high or the face detection result fails to keep up with the changes in the user's posture. Therefore, it is necessary to correct it based on the local posture of the user in the cabin to obtain a final face recognition result with higher accuracy, that is, the second face detection result.

[0087] The second face detection result is the final face detection result obtained according to the method in the aforementioned embodiment. Based on the final face detection result, it is possible to determine where the user is in the cabin, thereby conveniently providing personalized services such as smart air conditioning, smart sound field, seat massage, and smart seat adjustment.

[0088] The third face detection result includes a historical face detection result and a face detection result obtained after re-face detection, wherein the historical face detection result is the second face detection result obtained in the last detection and stored in the database.

[0089] The face detection method of the present application is described in detail below using the user's specific position (occupancy) and the user's head posture as examples of local postures.

[0090] In one embodiment of the present application, as shown in Figures 2 and 3, in-vehicle occupancy detection (in-vehicle user position detection) is performed through multiple detection mechanisms, such as object visual detection algorithm, in-vehicle installed sensor detection or sound zone detection, to obtain user position information.

[0091] For example, taking the object vision detection algorithm as an example, first obtain the corresponding position of the in-car camera in the car, and then obtain the in-car image captured by the camera. Based on the in-car image and the camera position, calculate the user's position in the car (the user's specific position).

[0092] If the occupancy rate has not changed, the continuous visual recognition process will not be affected. If the occupancy rate has changed, a new face recognition request will be triggered, and the recognition result cache will be cleared and the occupancy rate in the car will be updated.

[0093] Face detection is triggered after the occupancy changes. Specifically, it obtains the face image captured by the OMS camera, performs face recognition, and outputs the vision-based face detection result.

[0094] The face detection result is compared with the placeholder result, and the final face detection result is determined based on the comparison result.

[0095] If a face is recognized at every location where someone is present in the location information displayed by the placeholder result, the recognition is terminated.

[0096] If the placeholder result shows that there is someone at a certain location, but the face detection result shows that there is no one, it is considered that the recognition of that location has failed. First, try to update the recognition result of that location using the previous result in the cache. After the update is complete, check again whether each location is recognized successfully. If so, the recognition is terminated. Otherwise, try again before the timeout and update the recognition result in the cache.

[0097] If the placeholder result shows that there is no one at a certain location, but the face recognition result shows that there is someone, this situation usually occurs after the placeholder has changed and the face recognition result has not kept up with the placeholder result. Due to the placeholder change, a new recognition request will be triggered again. At this time, the current recognition request will be discarded and the placeholder detection will trigger a new recognition request process. This strategy is mainly to prevent the same user from being bound to multiple different locations in multiple recognition processes due to location changes after adding the cache.

[0098] In this way, by extending the recognition time window and adding a caching mechanism, a recognition effect with higher fault tolerance is achieved. At the same time, the placeholder results are used to control the continuous recognition time and the trigger conditions for storage refresh, which can better ensure the reliability and stability of the user's face recognition results.

[0099] The seat sensor signal is related to the position of the user in the car and is relatively more sensitive. When the seat sensor signal changes, it can be simply regarded as a change in the posture of the user in the car. At this time, a new short-term face detection request is triggered to refresh the face recognition result, but the face recognition cache is not cleared.

[0100] As shown in Figure 4, the system first monitors the seat sensor signal. When the signal changes, it detects a change in the user's posture, triggering a new recognition request and refreshing the face recognition results. This improves the tolerance for failed recognition results when no new recognition requests are triggered by active or seat changes after a timeout.

[0101] In one embodiment of the present application, as shown in FIG5 , a head posture information detection module is added. Similar to occupancy detection, the head posture information of a certain position is detected periodically. If the head posture information changes significantly, a new short-sighted face recognition request is triggered and the face recognition result is refreshed, but the recognition cache result is not cleared.

[0102] Specifically, the head posture detection is triggered at regular intervals to detect the head posture information of the user at each position in the car. If the head posture information at a certain position changes significantly, a new short-term face detection request is issued, and the new face detection result is matched with the detected head posture information until each detected position with head posture information has a corresponding face, and the final face detection result is obtained.

[0103] If a user maintains a high-angle posture for a long time in a vehicle, face recognition may fail even after a timeout. Furthermore, if the user changes from lowering or tilting their head to a smaller angle, the previous failed recognition result will still be used if no new recognition request is issued. In this case, according to this embodiment, triggering a new short-term recognition request based on the user's posture angle changes can promptly refresh the recognition results and simultaneously capture faces with smaller angles, increasing the probability of successful recognition and improving the user experience.

[0104] The technical solution of the present application can effectively solve the pain points of poor recognition effect in special scenarios such as changes in the posture of the user in the car during face recognition, and occasional large facial posture angles. When the position remains unchanged, continuous face recognition is controlled by the position, which can obtain more recognition times and reduce the risk of recognition failure due to occasional large posture angles. At the same time, a cache mechanism is added to save the best recognition result in a round of recognition, avoiding the problem of the recognition effect changing from good to bad due to changes in the user's posture during multiple recognition processes. When the position changes, a new face recognition request can be triggered and the last cached result can be cleared to ensure the validity of the recognition result and avoid the problem of the same user being bound to multiple locations due to cache and position changes.

[0105] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effect of the present application, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present application.

[0106] Furthermore, the present application also provides a face detection device.

[0107] Please refer to FIG6 , which is a main structural block diagram of a face detection device according to an embodiment of the present application.

[0108] As shown in Figure 6, the face detection device in the embodiment of the present application mainly includes an acquisition module 11, a judgment module 12, a detection module 13, and a determination module 14. In some embodiments, one or more of the acquisition module 11, the judgment module 12, the detection module 13, and the determination module 14 can be combined into one module.

[0109] In some embodiments, the acquisition module 11 may be configured to acquire an in-cabin image of the smart device and a local posture of the user in the cabin.

[0110] The judging module 12 may be configured to judge whether the user's posture changes based on the local posture;

[0111] The detection module 13 may be configured to perform face detection based on the in-cabin image to obtain a first face detection result when the user's posture changes.

[0112] The determination module 14 may be configured to determine a second face detection result based on the first face detection result and the local pose.

[0113] In one implementation, the description of specific implementation functions can refer to steps S101 to S104.

[0114] The above-mentioned face detection device is used to execute the face detection method embodiment shown in Figure 1. The technical principles, technical problems solved and technical effects produced by the two are similar. Technical personnel in this technical field can clearly understand that for the convenience and conciseness of description, the specific working process and related instructions of the face detection device can refer to the contents described in the embodiment of the face detection method, and will not be repeated here.

[0115] It will be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment of the present application can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0116] Furthermore, the present application also provides a computer device. In one embodiment of a computer device according to the present application, as shown in FIG7 , the computer device includes at least one processor 71 and at least one memory 72. The memory 72 can be configured to store a program for executing the face detection method of the above-described method embodiment, and the processor 71 can be configured to execute the program in the memory, which includes but is not limited to a program for executing the face detection method of the above-described method embodiment. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method section of the embodiment of the present application.

[0117] In the embodiment of the present application, the computer device may be a control device device formed by various devices. In some possible implementations, the computer device may include multiple memories and multiple processors. The program for executing the face detection method of the above method embodiment can be divided into multiple subroutines, and each subroutine can be loaded and run by the processor to execute different steps of the face detection method of the above method embodiment. Specifically, each subroutine can be stored in different memories respectively, and each processor can be configured to execute the program in one or more memories to jointly implement the face detection method of the above method embodiment, that is, each processor executes different steps of the face detection method of the above method embodiment respectively to jointly implement the face detection method of the above method embodiment.

[0118] The aforementioned multiple processors may be processors deployed on the same device. For example, the aforementioned computer device may be a high-performance device composed of multiple processors, and the aforementioned multiple processors may be processors configured on the high-performance device. Furthermore, the aforementioned multiple processors may also be processors deployed on different devices. For example, the aforementioned computer device may be a server cluster, and the aforementioned multiple processors may be processors on different servers in the server cluster.

[0119] Furthermore, the present application also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present application, the computer-readable storage medium can be configured to store a program for executing the face detection method of the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned face detection method. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The computer-readable storage medium can be a memory device formed by various computer devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-transitory computer-readable storage medium.

[0120] Furthermore, it should be understood that since the configuration of each module is merely for the purpose of illustrating the functional units of the apparatus of the present application, the physical devices corresponding to these modules may be the processor itself, or a portion of the software in the processor, a portion of the hardware, or a combination of software and hardware. Therefore, the number of modules in the figure is merely illustrative.

[0121] Those skilled in the art will appreciate that the various modules in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principles of this application. Therefore, the technical solutions after splitting or merging will fall within the scope of protection of this application.

[0122] The relevant user personal information that may be involved in the various embodiments of this application is strictly in accordance with the requirements of laws and regulations, following the principles of legality, legitimacy and necessity, and based on the reasonable purposes of business scenarios, to process the personal information that users actively provide during the use of products / services or generated due to the use of products / services, as well as the personal information obtained with the user's authorization.

[0123] The user personal information processed by this application will vary depending on the specific product / service scenario and will be based on the specific scenario in which the user uses the product / service. This may involve the user's account information, device information, driving information, vehicle information, or other related information. The applicant will treat the user's personal information and its processing with a high degree of diligence.

[0124] This application attaches great importance to the security of user personal information and has taken reasonable and feasible security protection measures that comply with industry standards to protect user information and prevent personal information from being accessed, disclosed, used, modified, damaged or lost without authorization.

[0125] Thus far, the technical solutions of the present application have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present application.

Claims

1. A face detection method, characterized in that: The method comprises: Obtain the in-cabin image of the smart device and the local posture of the user in the cabin; Determining whether a posture change occurs to the user based on the local posture; If yes, perform face detection based on the cabin image to obtain a first face detection result; A second face detection result is determined based on the first face detection result and the local pose.

2. The face detection method according to claim 1, wherein: The determining whether the user's posture changes based on the local posture includes: Comparing the local pose with a preset pose; Based on the comparison result, it is determined whether the user's posture changes.

3. The face detection method according to claim 1, wherein: The determining a second face detection result based on the first face detection result and the local pose includes: Matching the first face detection result with the local pose; The second face detection result is determined based on the matching result.

4. The face detection method according to claim 3, wherein: The determining the second face detection result based on the matching result includes: In a case where the first face detection result matches the local pose, using the first face detection result as the second face detection result; In a case where the first face detection result does not match the local posture, a third face detection result is obtained, and the second face detection result is determined based on the third face detection result.

5. The face detection method according to claim 4, wherein: The third face detection result includes a historical face detection result; The determining of the second face detection result based on the third face detection result includes: matching the historical face detection result with the local posture, and when the historical face detection result matches the local posture, using the historical face detection result as the second face detection result; otherwise, re-performing face detection within a first preset time range until the second face detection result is obtained.

6. The face detection method according to claim 4, wherein: The third face detection result includes a face detection result obtained after re-face detection; Determining the second face detection result based on the third face detection result includes: re-performing face detection within a second preset time range, and using the face detection result obtained after the re-face detection as the second face detection result when the face detection result obtained after the re-face detection matches the local posture.

7. The face detection method according to any one of claims 1 to 6, characterized in that: The local posture of the user in the cabin includes at least one of the user's position and the user's head posture.

8. A face detection device, characterized in that: The device comprises: an acquisition module configured to acquire an in-cabin image of the smart device and a local posture of a user in the cabin; a judgment module, configured to judge whether a posture change of the user occurs based on the local posture; a detection module, configured to perform face detection based on the in-cabin image to obtain a first face detection result when the user's posture changes; A determination module is configured to determine a second face detection result based on the first face detection result and the local pose.

9. A computer device comprising at least one processor and at least one memory, wherein the memory is adapted to store a plurality of program codes, wherein: The program code is suitable for being loaded and run by the processor to execute the face detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the face detection method according to any one of claims 1 to 7.

Images