A vision-based access control method, storage medium and access control device
By acquiring camera brightness information to control the image acquisition and recognition process, the problem of energy saving in access control equipment at night is solved, and efficient use of resources is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN HUITONG INTELLIGENT TECHNOLOGY CO LTD
- Filing Date
- 2026-02-11
- Publication Date
- 2026-06-05
AI Technical Summary
The problem of how to save energy in existing access control equipment at night has not been effectively solved.
The system acquires brightness information of the shooting area using a camera, discards images or captures videos based on the brightness conditions, and uses a pan-tilt-zoom (PTZ) to control the camera to capture videos from different angles and synthesize target images for recognition, thereby reducing resource consumption.
This reduces the waste of storage and computing resources at night, improving the energy efficiency of access control equipment.
Smart Images
Figure CN122157404A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of access control technology, specifically to vision-based access control methods, storage media, and access control devices. Background Technology
[0002] Facial recognition technology is an image-based technology for identifying people. Improving the accuracy and reliability of facial recognition is the foundation for its application in access control equipment. In access control systems, how to save energy at night is an urgent problem to be solved. Summary of the Invention
[0003] This invention addresses the problem of energy saving in access control devices at night.
[0004] In a first aspect, this application provides a vision-based access control method applied to access control equipment, the access control equipment including a pan-tilt unit and a camera mounted on the pan-tilt unit; the method includes: When the camera captures images, obtain the brightness information of the camera's shooting area; When the brightness of the shooting area meets the first preset condition, the image captured by the camera is discarded; When the brightness of the shooting area meets the second preset condition, the image captured by the camera is sent to the first recognizer to identify the identity of the target object in the image; When the brightness conditions in the shooting area meet the third preset condition, the user is prompted to keep their face facing the same direction. The camera is controlled by the gimbal to capture video from different angles. After the video is processed, the target image is obtained and sent to the first recognizer to identify the identity of the target object in the image.
[0005] In some embodiments, when the camera captures an image, obtaining brightness information of the camera's shooting area includes: Acquire the initial image captured by the camera and identify whether the initial image contains a human figure; If the initial image contains a human figure, the brightness information of the face region is obtained, and the second or third preset condition is confirmed based on the brightness information of the face region. If the initial image captured by the camera cannot identify a human figure, the overall brightness information of the initial image is obtained to determine whether the first preset condition is met based on the overall brightness information of the initial image.
[0006] In some embodiments, the first preset condition includes: in the overall brightness of the initial image, the average brightness of one-third of the region is less than a first brightness threshold, where the first brightness threshold indicates that the shooting area is in a dark state.
[0007] In some embodiments, the second preset condition includes: the average brightness of the face region is greater than a second brightness threshold; The third preset condition includes: the average brightness of the face region is greater than the third brightness threshold; among which... The second brightness threshold is greater than the third brightness threshold, and the third brightness threshold is greater than the second brightness threshold. The second brightness threshold indicates that the shooting area is in a bright state; the third brightness threshold indicates that the shooting area is in a dim state with poor lighting.
[0008] In some embodiments, when the brightness conditions in the shooting area meet a third preset condition, the user is prompted to keep their face facing the same direction. The camera is controlled by the gimbal to capture video at different angles, and the video is processed to obtain a target image, which is then sent to the first recognizer to identify the identity of the target object in the image. This includes: Face images are captured from various angles based on multiple trigger locations; each face image from a different angle has a different high-quality facial region. The target image is obtained by high-quality region rendering of each face image; The target image is fed into the first recognizer to identify the target object in the image.
[0009] In some embodiments, the gimbal includes a horizontal track, a drive mechanism, and a triggering mechanism; it acquires facial images corresponding to various angles based on multiple triggering positions, including: When the control drive mechanism moves along the horizontal track to the first position and triggers the trigger mechanism at the first position, the first face image is acquired; When the control drive mechanism moves along the horizontal track to the second position and triggers the trigger mechanism at the second position, a second face image is acquired; When the control drive mechanism moves along the horizontal track to the third position and triggers the trigger mechanism at the third position, a third face image is acquired; The target image is obtained by high-quality region rendering of each face image, including: stitching together the first face image, the second face image, and the third face image to obtain the target image.
[0010] In some embodiments, the first position, the second position, and the third position are equally spaced and located on the left, the midpoint, and the right side of the horizontal track, respectively; stitching the first face image, the second face image, and the third face image to obtain the target image includes: The first stitched image is obtained by stitching together the overlapping areas of the first face image and the second face image; Based on the overlapping area of the first stitched image and the third face image, a second stitched image is obtained; Using the area where the face is located in the second stitched image as the center, the second stitched image is cropped to obtain the target image, and the image size of the target image is the same as the size of the first face image, the second face image, and the third face image.
[0011] In some embodiments, a first stitched image is obtained by stitching together the overlapping areas of a first face image and a second face image, including: using the pixels of the overlapping area to perform weighted fusion to obtain a target pixel, wherein the target pixel is a pixel at the corresponding position in the first stitched image; A second stitched image is obtained by stitching together the overlapping area of the first stitched image and the third face image, including: using the pixels of the overlapping area to perform weighted fusion to obtain a target pixel, wherein the target pixel is the pixel at the corresponding position in the second stitched image.
[0012] Secondly, this application provides a storage medium that stores a computer program that can be executed by a processor to implement the above-described method.
[0013] Thirdly, this application provides an access control device, comprising: A pan-tilt unit that houses a camera; Memory, storing the facial recognition program; A processor, connected to the gimbal and the memory, implements the above-described method when executing the identification program.
[0014] The technical solution of this embodiment acquires environmental images through a camera, obtains brightness information of the camera's shooting area, and discards the acquired image when the brightness information meets a first preset condition to save storage resources. When the brightness information meets a third preset condition, the synthesized target image is used to identify authorized users, and the identifier under the second preset condition is reused to reduce resource consumption. Attached Figure Description
[0015] Figure 1 This is a flowchart of one embodiment of the vision-based access control method of this application; Figure 2 This is a flowchart of another embodiment of the vision-based access control method of this application; Figure 3 This is a flowchart of yet another embodiment of the vision-based access control method of this application. Detailed Implementation
[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0017] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.
[0018] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.
[0019] In a first aspect, this application provides a vision-based access control method, applied to access control equipment, the access control equipment including a pan-tilt unit and a camera mounted on the pan-tilt unit; Reference Figure 1 In one embodiment, the method includes: S100: When the camera captures an image, obtain the brightness information of the camera's shooting area; In this application, the camera has a certain field of view and cannot be zoomed; at this time, the shooting area is the brightness information of the image / video captured by the camera's field of view; the brightness information is used to identify the ambient brightness. For example, based on predetermined exposure parameters, the feature value of the pixel brightness of the captured image can be the brightness information. The feature value can be the median, variance, mean, standard deviation, etc., which are not limited here.
[0020] S200: When the brightness of the shooting area meets the first preset condition, discard the image captured by the camera; The first preset condition indicates that the shooting area is in a dark state. At this time, the environment corresponding to the door with access control equipment is at night and there is no light. At this time, the camera can be controlled to capture images, but not to store images, so as to reduce power consumption and waste of storage resources.
[0021] When it is daytime or the user has turned on the lights at the entrance, the brightness of the shooting area does not meet the first preset condition. In other words, the first preset condition is set to meet the condition of darkness, when the camera cannot capture a valid photo. In this case, the photo has no value for storage and can be discarded.
[0022] S300: When the brightness of the shooting area meets the second preset condition, the image captured by the camera is sent to the first recognizer to identify the identity of the target object in the image. S400: When the brightness conditions in the shooting area meet the third preset condition, the user is prompted to keep their face facing the same direction. The camera is controlled by the gimbal to capture video from different angles. After the video is processed, the target image is obtained and sent to the first recognizer to identify the identity of the target object in the image.
[0023] When it is daytime or the user has turned on the lights at the door, the brightness of the shooting area meets the second or third preset condition; in other words, the first, second, and third preset conditions cover the various brightness ranges of the camera.
[0024] The second preset condition is when it is daytime or when the user has turned on the door light and the lighting conditions are good. In order to reduce computing and storage resources, only one image needs to be captured and then sent to the face recognition device to identify whether it is an authorized user. If yes, the door will be unlocked; otherwise, it will not be unlocked.
[0025] However, when it is evening or night and the lighting conditions at the entrance are poor, a single image is not enough to identify the user, and sending the entire video to the recognizer requires a large amount of computing resources.
[0026] Therefore, this application controls the camera to capture video from different angles via the pan-tilt unit, processes the video, and obtains the target image. Then, the identifier used in the second preset condition is reused to identify whether the user is authorized; if so, the door unlocks; otherwise, it remains locked.
[0027] The technical solution of this embodiment acquires environmental images through a camera, obtains brightness information of the camera's shooting area, and discards the acquired image when the brightness information meets a first preset condition to save storage resources. When the brightness information meets a third preset condition, the synthesized target image is used to identify authorized users, and the identifier under the second preset condition is reused to reduce resource consumption.
[0028] Reference Figure 2 In some embodiments, S100, when the camera captures an image, obtaining the brightness information of the camera's shooting area includes: S101. Acquire the initial image captured by the camera and identify whether the initial image contains a human figure; S102. If the initial image contains a human figure, obtain the brightness information of the face region, and determine whether the second preset condition or the third preset condition is met based on the brightness information of the face region. S103. If the initial image captured by the camera cannot identify a human figure, obtain the overall brightness information of the initial image to confirm whether the first preset condition is met based on the overall brightness information of the initial image.
[0029] In this embodiment, the overall brightness information of the initial image is first used to determine whether it is in a state of nighttime and no lights on (first preset condition) or a state of not being in nighttime and no lights on. If it is in a state of not being in nighttime and no lights on, the brightness information of the face area is further used to determine whether it is in a second preset condition or a third preset condition, so that the distinction between the second preset condition and the third preset condition is more accurate.
[0030] For example, the first preset condition includes: in the overall brightness of the initial image, the average brightness of one-third of the region is less than a first brightness threshold, where the first brightness threshold indicates that the shooting area is in a dark state.
[0031] The second preset condition includes: the average brightness of the face region is greater than the second brightness threshold; The third preset condition includes: the average brightness of the face region is greater than the third brightness threshold; among which... The second brightness threshold is greater than the third brightness threshold, and the third brightness threshold is greater than the second brightness threshold. The second brightness threshold indicates that the shooting area is in a bright state; the third brightness threshold indicates that the shooting area is in a dim state with poor lighting.
[0032] Reference Figure 3 In some embodiments, S400, when the brightness conditions in the shooting area meet the third preset condition, prompts the user to keep their face facing the same direction, controls the camera to capture video at different angles via the gimbal, processes the video to obtain a target image, and sends it to the first recognizer to identify the identity of the target object in the image, including: S401. Collect face images from various angles based on multiple trigger positions; the face images from each angle have different high-quality face regions; S402. Target image is obtained by high-quality region rendering based on each face image; In this embodiment, rendering can refer to selecting appropriate pixel values from the pixels of the face images corresponding to various angles as the pixel values of the target image to obtain the target image. In other embodiments, rendering can also refer to stitching together high-quality regions of various face images.
[0033] S403. The target image is sent to the first recognizer to identify the identity of the target object in the image.
[0034] In some embodiments, the gimbal includes a horizontal track, a drive mechanism, and a triggering mechanism; S401, acquiring face images corresponding to various angles based on multiple triggering positions, including: S4011. When the control drive mechanism moves along the horizontal track to the first position and triggers the trigger mechanism at the first position, the first face image is acquired. S4012. When the control drive mechanism moves along the horizontal track to the second position and triggers the trigger mechanism at the second position, the second face image is acquired. S4013. When the control drive mechanism moves along the horizontal track to the third position and triggers the trigger mechanism at the third position, a third face image is acquired. The target image is obtained by high-quality region rendering of each face image, including: stitching together the first face image, the second face image, and the third face image to obtain the target image.
[0035] In this embodiment of the application, the access control device is located in the middle of the gate, and the length of the horizontal track is greater than or equal to 10cm. At this time, three trigger positions can be set at the four equal divisions of the horizontal track. Each trigger position is equipped with a mechanical micro switch or other triggering device. When the device moves to the first position, the micro switch at the first position is triggered. When the device moves to the second position, the micro switch at the second position is triggered. When the device moves to the third position, the micro switch at the third position is triggered.
[0036] Three microswitches are connected to the processor. The processor can record the timestamps corresponding to the trigger times of the three microswitches. Based on the timestamps, the first face image, the second face image, and the third face image can be found in the video. Since the shooting positions of the three face images are fixed, the three face images can be stitched together to obtain the second stitched image.
[0037] Furthermore, in order to send the image into the first recognizer, the size of the target image needs to be consistent with the size of the image acquired under the first preset conditions. Therefore, the target image is obtained by cropping the second stitched image with the face area as the center.
[0038] For example, the first position, the second position, and the third position are equally spaced and located on the left, the midpoint, and the right side of the horizontal track; stitching the first face image, the second face image, and the third face image to obtain the target image includes: The first stitched image is obtained by stitching together the overlapping areas of the first face image and the second face image; Based on the overlapping area of the first stitched image and the third face image, a second stitched image is obtained; Using the area where the face is located in the second stitched image as the center, the second stitched image is cropped to obtain the target image, and the image size of the target image is the same as the size of the first face image, the second face image, and the third face image.
[0039] In some embodiments, a first stitched image is obtained by stitching together the overlapping areas of a first face image and a second face image, including: using the pixels of the overlapping area to perform weighted fusion to obtain a target pixel, wherein the target pixel is a pixel at the corresponding position in the first stitched image; A second stitched image is obtained by stitching together the overlapping area of the first stitched image and the third face image, including: using the pixels of the overlapping area to perform weighted fusion to obtain a target pixel, wherein the target pixel is the pixel at the corresponding position in the second stitched image.
[0040] Secondly, this application provides a storage medium that stores a computer program that can be executed by a processor to implement the above-described method.
[0041] Thirdly, this application provides an access control device, comprising: A pan-tilt unit that houses a camera; Memory, storing the facial recognition program; A processor, connected to the gimbal and the memory, implements the above-described method when executing the identification program.
[0042] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0043] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0044] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0045] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0046] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0047] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.
[0048] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
Claims
1. A vision-based access control method, characterized in that, The method is applied to access control equipment, which includes a pan-tilt unit and a camera mounted on the pan-tilt unit; the method includes: When the camera captures images, obtain the brightness information of the camera's shooting area; When the brightness of the shooting area meets the first preset condition, the image captured by the camera is discarded; When the brightness of the shooting area meets the second preset condition, the image captured by the camera is sent to the first recognizer to identify the identity of the target object in the image; When the brightness conditions in the shooting area meet the third preset condition, the user is prompted to keep their face facing the same direction. The camera is controlled by the gimbal to capture video from different angles. After the video is processed, the target image is obtained and sent to the first recognizer to identify the identity of the target object in the image.
2. The vision-based access control method as described in claim 1, characterized in that, When the camera captures an image, it obtains the brightness information of the camera's shooting area, including: Acquire the initial image captured by the camera and identify whether the initial image contains a human figure; If the initial image contains a human figure, the brightness information of the face region is obtained, and the second or third preset condition is confirmed based on the brightness information of the face region. If the initial image captured by the camera cannot identify a human figure, the overall brightness information of the initial image is obtained to determine whether the first preset condition is met based on the overall brightness information of the initial image.
3. The vision-based access control method as described in claim 1, characterized in that, The first preset condition includes: in the overall brightness of the initial image, the average brightness of one-third of the area is less than a first brightness threshold, where the first brightness threshold indicates that the shooting area is in a dark state.
4. The vision-based access control method as described in claim 1, characterized in that, The second preset condition includes: the average brightness of the face region is greater than the second brightness threshold; The third preset condition includes: the average brightness of the face region is greater than the third brightness threshold; among which... The second brightness threshold is greater than the third brightness threshold, and the third brightness threshold is greater than the second brightness threshold. The second brightness threshold indicates that the shooting area is in a bright state; the third brightness threshold indicates that the shooting area is in a dim state with poor lighting.
5. The vision-based access control method as described in claim 1, characterized in that, When the brightness conditions in the shooting area meet the third preset condition, the user is prompted to keep their face facing the same direction. The pan-tilt unit controls the camera to capture video from different angles. After processing the video, the target image is obtained and sent to the first recognizer to identify the identity of the target object in the image, including: Face images are captured from various angles based on multiple trigger locations; each face image from a different angle has a different high-quality facial region. The target image is obtained by high-quality region rendering of each face image; The target image is fed into the first recognizer to identify the target object in the image.
6. The vision-based access control method as described in claim 5, characterized in that, The gimbal includes a horizontal track, a drive mechanism, and a triggering mechanism; it acquires facial images corresponding to various angles based on multiple triggering positions, including: When the control drive mechanism moves along the horizontal track to the first position and triggers the trigger mechanism at the first position, the first face image is acquired; When the control drive mechanism moves along the horizontal track to the second position and triggers the trigger mechanism at the second position, a second face image is acquired; When the control drive mechanism moves along the horizontal track to the third position and triggers the trigger mechanism at the third position, a third face image is acquired; The target image is obtained by high-quality region rendering of each face image, including: stitching together the first face image, the second face image, and the third face image to obtain the target image.
7. The vision-based access control method as described in claim 6, characterized in that, The first position, the second position, and the third position are equally spaced and are located on the left, the middle, and the right side of the horizontal track, respectively. The target image is obtained by stitching together the first face image, the second face image, and the third face image, including: The first stitched image is obtained by stitching together the overlapping areas of the first face image and the second face image; Based on the overlapping area of the first stitched image and the third face image, a second stitched image is obtained; Using the area where the face is located in the second stitched image as the center, the second stitched image is cropped to obtain the target image, and the image size of the target image is the same as the size of the first face image, the second face image, and the third face image.
8. The vision-based access control method as described in claim 7, characterized in that, Based on the overlapping areas of the first face image and the second face image, a first stitched image is obtained by stitching together the images, including: using the pixels of the overlapping areas to perform weighted fusion to obtain a target pixel, wherein the target pixel is the pixel at the corresponding position in the first stitched image; A second stitched image is obtained by stitching together the overlapping area of the first stitched image and the third face image, including: using the pixels of the overlapping area to perform weighted fusion to obtain a target pixel, wherein the target pixel is the pixel at the corresponding position in the second stitched image.
9. A storage medium storing a computer program that can be executed by a processor to implement the method as claimed in any one of claims 1-8.
10. An access control device, characterized in that, include: A pan-tilt unit that houses a camera; Memory, storing the facial recognition program; A processor, connected to the gimbal and the memory, wherein when the processor executes the identification program, it implements the method as described in any one of claims 1-8.