Unlocking device, unlocking method, vehicle stand column assembly and vehicle
Through the detection module, the proximity of the moving body around the vehicle is monitored and the face recognition module is automatically activated, which solves the problem of cumbersome and low efficiency in the existing technology, and realizes sensorless intelligent unlocking, improving the user experience.
Patent Information
- Application Number
- CN202411164461.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-11-29
AI Technical Summary
The existing vehicle face recognition unlocking system requires users to approach the car pillar, hold down the keys and wait for 5 to 8 seconds to start face recognition, which has poor experience and low efficiency.
Through the detection module, the face recognition module is automatically triggered to start, realizing senseless unlocking, and only when the human body is detected to be approached, reducing energy consumption.
Improve the convenience and efficiency of unlocking, reduce user operation needs, and improve intelligence level and user experience.
Smart Images

Figure CN119037340A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of information security technology, and in particular to an unlocking device, an unlocking method, a vehicle pillar assembly and a vehicle. Background Art
[0002] Face recognition technology is becoming more and more mature. This technology has been applied to vehicles. At present, some OEMs have tried to apply face recognition technology to unlocking doors. The face information of users outside the car is collected through the camera, the owner's identity is identified and the door is opened. The main function of this recognition system is to replace the key. In some special cases, such as without the key, it can make it easier for the driver to open the door. When in use, the driver can activate the face recognition system by touching the column. At the same time, the 3D TOF (Time of Flight) camera of the column will scan the face, and the car can be started after unlocking. However, the existing recognition system requires the user to approach the car column and press the button on the column of the car. During the module startup process, the user needs to wait for 5 to 8 seconds. After the recognition module is started, face recognition is performed again. It is not convenient, efficient, and has a poor experience. Summary of the invention
[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides an unlocking device, an unlocking method, a vehicle pillar assembly and a vehicle.
[0004] To achieve the above-mentioned object, a first aspect of the present application provides an unlocking device, the unlocking device comprising a detection module and a face recognition module;
[0005] The detection module is used to acquire an image of the moving object when a moving object is detected, and when it is determined based on the image that the moving object is a human body approaching the detection module, determine whether to control the face recognition module to start based on the distance between the human body and the detection module;
[0006] The face recognition module is used to perform face recognition on the human body after startup, and output an unlocking instruction to control the unlocking of the object to be unlocked after the face recognition is passed.
[0007] The unlocking device provided by the present application obtains the image of the moving object through the detection module when monitoring the moving object, and when determining based on the image that the moving object is a human body approaching the detection module, determines whether to control the face recognition module to start based on the distance between the human body and the detection module, and uses the face recognition module to perform face recognition on the human body after startup. In this way, when the user approaches the detection module, the face recognition module will be automatically triggered to start the face recognition function to unlock. On the one hand, the face recognition module is only started when the detection module monitors the moving object and determines that the moving object is a human body approaching the detection module, and the energy consumption is lower. On the other hand, in the entire unlocking process, the user can realize the senseless unlocking without operation and waiting, and the intelligence level is higher, the unlocking is more convenient and efficient, and the user experience is better.
[0008] A second aspect of the present application provides an unlocking method, the unlocking method comprising:
[0009] When the detection module detects a moving object, it acquires an image of the moving object, and when it is determined based on the image that the moving object is a human body approaching the detection module, it determines whether to control the face recognition module to start based on the distance between the human body and the detection module; and
[0010] The face recognition module performs face recognition on the human body after startup, and outputs an unlocking instruction to control the unlocking of the object to be unlocked after the face recognition is passed.
[0011] A third aspect of the present application provides a vehicle pillar assembly, the vehicle pillar assembly comprising the unlocking device described in the first aspect.
[0012] A fourth aspect of the present application provides a vehicle, the vehicle comprising the unlocking device described in the first aspect above, the unlocking device being used to control the unlocking of the vehicle.
[0013] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 is a topological diagram of the unlocking device provided in an embodiment of the present application;
[0015] Figure 2 This is a schematic diagram of an application scenario of the unlocking device provided in an embodiment of the present application;
[0016] Figure 3 This is a schematic diagram of another application scenario of the unlocking device provided in an embodiment of the present application;
[0017] Figure 4 is a schematic diagram of the Euler angles of a human head provided in an embodiment of the present application;
[0018] Figure 5 This is another schematic diagram of an application scenario of the unlocking device provided in an embodiment of the present application;
[0019] Figure 6 is a flowchart of the unlocking method provided in an embodiment of the present application;
[0020] Figure 7 is a schematic diagram of the back structure of a vehicle pillar assembly provided in an embodiment of the present application;
[0021] Figure 8 It is a front structural schematic diagram of a vehicle pillar assembly provided in an embodiment of the present application.
[0022] The following are the descriptions of the reference numerals:
[0023] Unlocking device 100
[0024] Body Control Module 200
[0025] Detection module 10
[0026] Face recognition module 20
[0027] Face detection module 12
[0028] Moving object detection module 11
[0029] Radar 112
[0030] First processor 111
[0031] Low power camera122
[0032] The second processor 121
[0033] Fill light 123
[0034] Time of flight camera 22
[0035] TOF transmitting unit 221
[0036] TOF receiving unit 222
[0037] The third processor 21
[0038] Display unit 23
[0039] Memory 24
[0040] Preset Area U
[0041] The first preset distance d1
[0042] The second preset distance d2
[0043] The third preset distance d3
[0044] Fourth preset distance d4
[0045] Vehicle pillar assembly 1
[0046] Bracket 2
[0047] Sealing strip 3
[0048] The following specific implementation methods will illustrate the present application in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION
[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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.
[0050] In addition, the terms "first", "second", etc. in the specification of the present invention are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations 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 necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0051] It should be noted that, in the absence of conflict, the features in the embodiments of the present application may be combined with each other.
[0052] See also Figure 1 , Figure 1 : is a topological diagram of an unlocking device provided in an embodiment of the present application. The present application provides an unlocking device 100, the unlocking device 100 comprising a detection module 10 and a face recognition module 20. The unlocking device 100 is installed on an object to be unlocked.
[0053] The detection module 10 is used to acquire an image of a moving object when a moving object is detected, and when it is determined based on the image that the moving object is a human body approaching the detection module 10 , determine whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10 .
[0054] The face recognition module 20 is used to perform face recognition on the human body after startup, and output an unlocking instruction to control the unlocking of the object to be unlocked after the face recognition is passed.
[0055] The unlocking device 100 provided in the present application obtains the image of the moving object through the detection module 10 when monitoring the moving object, and when determining that the moving object is a human body approaching the detection module 10 based on the image, determines whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10, and uses the face recognition module 20 to perform face recognition on the human body after startup. In this way, when the user approaches the detection module 10, the face recognition module 20 will be automatically triggered to start the face recognition function to unlock. On the one hand, the face recognition module 20 is only started when the detection module 10 monitors the moving object and determines that the moving object is a human body approaching the detection module 10, and the energy consumption is lower. On the other hand, in the entire unlocking process, the user does not need to operate or wait to achieve senseless unlocking, and the intelligence level is higher, the unlocking is more convenient and efficient, and the user experience is better.
[0056] Vehicles generally have pillars, such as A-pillars, B-pillars, and C-pillars.
[0057] In some embodiments, the object to be unlocked may include a vehicle, and the unlocking device 100 may be installed on a pillar of the vehicle, and the unlocking device 100 is used to control the locking device on the door to unlock or lock. Specifically, the vehicle includes a body control module (BCM) 200, which is a very important electronic control unit in the car, responsible for controlling and managing the vehicle's body electrical system. Among them, the detection module 10 is electrically connected to the body control module 200. When the user approaches the vehicle pillar, the detection module 10 will control the face recognition module 20 to start face recognition, and the face recognition module 20 will send an unlocking instruction to the body control module 200 through the detection module 10 after the face recognition is passed. The body control module 200 controls the locking device on the door to unlock in response to the unlocking instruction, so that the user can directly open the door and enter the car without performing any unlocking action. In other embodiments, the face recognition module 20 may also be electrically connected to the body control module 200, and the face recognition module 20 may directly send an unlocking instruction to the body control module 200 after the face recognition is passed. In other embodiments, the object to be unlocked may also be a door, a safe, etc., which is not limited here.
[0058] In some embodiments, the detection module 10 includes a face detection module 12. The face detection module 12 is used to obtain multiple images of the moving object at preset time intervals, determine whether each image includes a face image, and when it is determined that the multiple images all include face images, determine that the moving object is a human body, and determine whether the movement trend of the human body is approaching the detection module 10 based on at least the change of the head posture information of the human body in the multiple images, and when it is determined that the movement trend of the human body is approaching the detection module 10, determine whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10.
[0059] In some embodiments, the face detection module 12 is further configured to be turned off when it is determined that the movement trend of the human body is not to approach the detection module 10 .
[0060] In this way, it is possible to avoid the face detection module 12 being continuously turned on when it is determined that the movement trend of the human body is not to approach the detection module 10 , and the energy consumption of the face detection module 12 can be further reduced.
[0061] In some embodiments, the face detection module 12 is also used to obtain multiple new images of the human body at a preset time interval again when it is determined that the movement trend of the human body is not approaching the detection module 10, and to judge whether the movement trend of the human body is approaching the detection module 10 based at least on the change of the head posture information of the human body in the new multiple images, and when it is determined that the movement trend of the human body is approaching the detection module 10, determine whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10.
[0062] In actual application scenarios, after the face detection module 12 is turned on, the user may stop moving (for example, stop at the same place to make a phone call). At this time, the face detection module 12 will determine that the user's movement trend is not approaching the detection module 10. In this embodiment, when the face detection module 12 determines that the movement trend of the human body is not approaching the detection module 10, it will re-acquire multiple new images of the human body at a preset time interval to detect the user's movement trend. Then, if the user continues to approach the detection module 10 after making a phone call, the face detection module 12 can still detect the user's movement trend and control the face recognition module 20 to start, thereby improving the success rate of unlocking.
[0063] In some embodiments, the face detection module 12 is further used to record the on-time, and when it is determined that the movement trend of the human body is not approaching the detection module 10 and the on-time is less than the preset time, multiple new images of the human body are acquired again at preset time intervals, and whether the movement trend of the human body is approaching the detection module 10 is determined based on at least the change of the head posture information of the human body in the new multiple images, and when it is determined that the movement trend of the human body is approaching the detection module 10, it is determined whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10. The face detection module 12 is also used to shut down when it is determined that the movement trend of the human body is not approaching the detection module 10 and the on-time is greater than the preset time.
[0064] In this embodiment, if the user stays still for a long time, the face detection module 12 will be turned off when the on time reaches the preset time. This can avoid the face detection module 12 from continuously detecting the movement trend of the human body when it determines that the movement trend of the human body is not approaching the detection module 10, thereby reducing the power consumption of the face detection module 12.
[0065] In some embodiments, the face detection module 12 is specifically used to determine that the image includes a face image when the image includes image information that matches a preset face template. Exemplarily, the face detection module 12 can use Hough Transform to search for the local maximum of a specific shape (such as a straight line, a circle, an ellipse, etc.) in the accumulator of the parameter space to detect the shape, thereby extracting feature points in the image (such as eyes, nose, mouth, etc.), and then matching these feature points with the preset face template to determine whether the image includes a face image.
[0066] For example, taking the object to be unlocked as a vehicle as an example, Figure 2 As shown, in one scenario, when the detection module 10 detects a cat passing by a vehicle, the detection module 10, after acquiring multiple images of the moving object, will determine that the image does not include a face image, thereby determining that the moving object is not a human body, and will no longer judge the movement trend, and will not control the face recognition module 20 to start.
[0067] In this way, it is first determined whether the moving body is a human body, and the moving trend is determined only when the moving body is a human body, which can save computing power.
[0068] In some embodiments, the face detection module 12 is specifically configured to determine that the image includes a face image when image features match preset structural distribution features of a face.
[0069] In some embodiments, the face detection module 12 is specifically used to obtain the face feature points of the face images in each image when it is determined that the multiple images all include face images, and judge whether the face images in each image all include the face images of the same person according to the face feature points of the face images in each image, and when it is determined that the face images in each image all include the face images of the same person, judge whether the movement trend of the target person is approaching the detection module 10 based on at least the change of the head posture information of the target person in the multiple images. The target person is the person corresponding to the face images that appear in each image.
[0070] Exemplarily, the face detection module 12 can enable a facial feature point detector to obtain preset facial feature points (such as the left eye, the right eye, the tip of the nose, the left corner of the mouth, and the right corner of the mouth) in the face images in each image, and enable a deep learning model to perform similarity judgment on the preset facial feature points of the face images in each image, thereby obtaining corresponding similarity measurement values, and when the similarity measurement values between the face images in different images are all lower than a preset similarity threshold (such as 1.1), it is determined that the multiple images include face images of the same person.
[0071] In some embodiments, the face detection module 12 is specifically used to determine whether the target person's movement trend is approaching the detection module 10 based on changes in the head posture information of the target person in the multiple images and changes in the distance between the target person and the detection module 10.
[0072] In some embodiments, the face detection module 12 is specifically used to derive the movement direction of the target person based on changes in the head posture information of the target person in the multiple images and changes in the distance between the target person and the detection module 10, and to judge whether the target person's movement trend is approaching the detection module 10 based on the relationship between the angle between the movement direction of the target person and the direction in which the target person points to the detection module 10 and a preset angle threshold.
[0073] For example, taking the object to be unlocked as a vehicle as an example, Figure 3As shown, in one scenario, when the detection module 10 detects a person passing by a vehicle, at this time, after acquiring multiple images of the moving object, the detection module 10 will determine that the multiple images all include human face images, thereby determining that the moving object is the target person. Afterwards, the detection module 10 further obtains the moving direction OA of the target person based on the changes in the head posture information of the target person in the multiple images and the changes in the distance between the target person and the detection module 10, and determines that the angle α between the moving direction OA of the target person and the direction OB of the target person pointing to the detection module 10 is greater than the preset angle threshold, thereby determining that the moving trend of the person is not to approach the detection module 10, and will not control the face recognition module 20 to start.
[0074] In this way, the movement trend of the human body is evaluated with higher accuracy by combining the changes in the human head posture information and the changes in the distance between the target human body and the detection module 10 .
[0075] In some embodiments, the head posture information of the target person includes the Euler angles of the head of the target person. The face detection module 12 is specifically used to calculate the Euler angles of the head of the target person in each image and the difference between the Euler angles of the head of the target person in any two adjacent images, and when the difference between the Euler angles of the head of the target person in any two adjacent images is less than a preset angle threshold, and the distance between the target person and the detection module 10 gradually decreases, it is determined that the movement trend of the target person is to approach the detection module 10.
[0076] Among them, two adjacent images refer to two images with adjacent shooting times. For example, the face detection module 12 sequentially acquires three images of a moving object at a time interval of 0.5 s, that is, the first image is acquired at the start time, the second image is acquired 0.5 s after the start time, and the third image is acquired 1 s after the start time. Then the first image and the second image are two adjacent images, and the second image and the third image are also two adjacent images.
[0077] See also Figure 4 , Figure 4Schematic diagram of the Euler angles of the human head provided in the embodiment of the present application. The Euler angles are a set of angles that describe the direction of an object in three-dimensional space relative to a fixed coordinate system, and are used to represent the rotation of an object around three principal coordinate axes (usually the x, y, and z axes), including the pitch angle (rotation around the x-axis, indicating the degree of inclination of the object in the vertical direction), the yaw angle (rotation around the y-axis, indicating the rotation of the object in the horizontal plane, determining the direction of the object's advance), and the roll angle (rotation around the z-axis, indicating the rotation of the object around its own direction of advance).
[0078] Exemplarily, the face detection module 12 sequentially acquires three images of the target human body at a time interval of 0.5 s, and respectively calculates a first pitch angle, a first yaw angle, and a first roll angle of the head of the target human body in the first image, a second pitch angle, a second yaw angle, and a second roll angle of the head of the target human body in the second image, a third pitch angle, a third yaw angle, and a third roll angle of the head of the target human body in the third image, as well as a difference between the first pitch angle and the second pitch angle, a difference between the first yaw angle and the second yaw angle, a difference between the first roll angle and the second roll angle, a difference between the second pitch angle and the third pitch angle, a difference between the second yaw angle and the third yaw angle, and a difference between the second roll angle and the third roll angle. The face detection module 12 is used to determine that the target human body's movement trend is approaching the detection module 10 when the difference between the first pitch angle and the second pitch angle and the difference between the second pitch angle and the third pitch angle are both smaller than a preset pitch angle threshold, the difference between the first yaw angle and the second yaw angle and the difference between the second yaw angle and the third yaw angle are both smaller than a preset yaw angle threshold, and the difference between the first roll angle and the second roll angle and the difference between the second roll angle and the third roll angle are both smaller than a preset roll angle threshold, and when the distance between the target human body and the detection module 10 gradually becomes smaller.
[0079] It is not difficult to understand that when the user's moving intention is to approach the vehicle for facial recognition unlocking and getting on the vehicle, the amplitude of the head swing will not be too large during the process of approaching the vehicle. Therefore, according to the change of the distance between the target human body in each image and the detection module 10, it can be judged whether the user's body is gradually approaching the vehicle. Further, according to the change of the Euler angle of the head of the target human body in each image, it can be judged whether the user has the intention to approach the unlocking device 100 for facial recognition unlocking. Therefore, when the difference between the Euler angles of the head of the target human body in any two adjacent images is less than the preset angle threshold, and the distance between the target human body and the detection module 10 gradually becomes smaller, it is determined that the moving trend of the target human body is to approach the detection module 10 and control the facial recognition module 20 to start, which can more accurately distinguish whether the target human body is a user with the intention of unlocking or a passerby passing by the vehicle, which can reduce the probability of the facial recognition module 20 being mistakenly started and further reduce the power consumption of the unlocking device 100.
[0080] It is not difficult to understand that when a human body approaches the detection module 10, the area ratio of the human body's head image in each image will gradually increase. Therefore, in some embodiments, the face detection module 12 can also determine whether the target human body's moving trend is approaching the detection module 10 based on the changes in the head posture information of the target human body in the multiple images and the changes in the area ratio of the target human body's head image in each image.
[0081] In some embodiments, the detection module 10 further includes a moving object detection module 11. The moving object detection module 11 is used to detect whether there is a moving object in the preset area U when the object to be unlocked is in a locked state, and when it is determined that there is a moving object in the preset area U, detect the distance between the moving object and the detection module 10, and determine whether to control the face detection module 12 to start based on the distance between the moving object and the detection module 10.
[0082] Wherein, the distance between each position point in the preset area U and the detection module 10 is greater than the first preset distance d1 and less than the second preset distance d2. Figure 2-3 As shown, the preset area U is a fan-shaped area extending toward the outside of the vehicle with the unlocking device 100 as the center.
[0083] It is not difficult to understand that if the detection area of the moving body detection module 11 is too large, the power consumption will be very high, and the probability of detecting passers-by will also be high; if the detection area of the moving body detection module 11 is too small, the response time left for the face detection module 12 and the face recognition module 20 may not be enough, so that the user may need to wait for unlocking. According to the test statistical results, it is more appropriate to set the first preset distance d1 to 0.3m, and it is more appropriate to set the second preset distance d2 to 5m.
[0084] like Figure 2-3 As shown, in some embodiments, the moving object detection module 11 is specifically used to control the face detection module 12 to start when the distance between the moving object and the detection module 10 is less than or equal to a third preset distance d3. The third preset distance d3 is less than the second preset distance d2 and greater than the first preset distance d1.
[0085] In order to further reduce the power consumption of the face detection module 12, if the distance between the moving object and the detection module 10 is always greater than the third preset distance d3 after entering the preset area, it can be preliminarily determined that the moving object is not approaching the detection module 10, and thus the face detection module 12 may not be started.
[0086] Among them, the third preset distance d3 can be determined according to the response time of the face detection module 12 and the face recognition module 20. It is not difficult to understand that if the third preset distance d3 is set larger, the face detection module 12 will be turned on earlier and the power consumption will be higher; if the third preset distance d3 is set too small, the response time left for the face detection module 12 and the face recognition module 20 may not be enough, so the user may need to wait for unlocking. According to the test statistical results, it is more appropriate to set the third preset distance d3 to 2.5m.
[0087] like Figure 2-3 As shown, in some embodiments, the face detection module 12 is specifically used to control the face recognition module 20 to start when it is determined that the moving object is a human body approaching the detection module 10 and the distance between the human body and the detection module 10 is less than or equal to a fourth preset distance d4. The fourth preset distance d4 is less than the third preset distance d3 and greater than the first preset distance d1.
[0088] In order to further reduce the power consumption of the face recognition module 20, if the distance between the human body and the detection module 10 is always greater than the fourth preset distance d4, it can be preliminarily determined that the human body has no intention of approaching the detection module 10 to unlock the phone, and thus the face recognition module 20 may not be started.
[0089] The fourth preset distance d4 can be determined according to the response time of the face recognition module 20. It is not difficult to understand that if the fourth preset distance d4 is set larger, the face recognition module 20 will be turned on earlier and the power consumption will be higher; if the fourth preset distance d4 is set too small, the response time of the face recognition module 20 may not be enough, so the user may need to wait for unlocking. According to the test statistical results, it is more appropriate to set the fourth preset distance d4 to 1.2m.
[0090] like Figure 5 As shown, in some embodiments, the preset area U is a fan-shaped area extending toward the outside of the vehicle with the detection module 10 as the center. Then, the moving object detection module 11 has a detection blind spot. For example, when the user approaches the detection module 10 close to the vehicle body, the moving object detection module 11 will not be able to detect the user's moving trend toward the detection module 10.
[0091] In view of this, the moving object detection module 11 is also used to control the face detection module 12 to start up when it is determined that there is a moving object in the preset area U, the distance between the moving object and the detection module 10 is less than the fourth preset distance d4, and the face detection module 12 and the face recognition module 20 are both in the off state, so that the face detection module 12 detects whether the moving object is a human body. The face detection module 12 is used to control the face recognition module 20 to start up when it is determined that the moving object is a human body. The face recognition module 20 is used to perform face recognition on the human body after starting up, and output an unlocking instruction to control the unlocking of the object to be unlocked after the face recognition is passed.
[0092] In this way, when the user approaches the detection module 10 from the detection blind area, the detection module 10 can still control the face recognition module 20 to start, and the recognition success rate is higher.
[0093] In some embodiments, the moving object detection module 11 includes a radar 112 and a first processor 111. The first processor 111 is electrically connected to the radar 112, and the first processor 111 is configured to be in a dormant state when the object to be unlocked is in an unlocked state, thereby lowering energy consumption. Exemplarily, the radar 112 is a millimeter wave radar with an operating frequency of 24 GHz.
[0094] The first processor 111 is also used to control the radar 112 to emit detection waves when the object to be unlocked is in a locked state, and detect whether there is a moving object in the preset area U according to the echo of the detection wave, and when it is determined that there is a moving object in the preset area U, determine whether to output a first control instruction to the face detection module 12 based on the distance between the moving object and the detection module 10. The first control instruction is used to control the start of the face detection module 12.
[0095] After receiving the echo of the detection wave, the moving body detection module 11 will perform clutter removal on the echo signal to eliminate the influence of clutter. The moving body detection module 11 will also perform analog-to-digital conversion on the echo signal after clutter removal and output it to the first processor 111.
[0096] When working, the first processor 111 is used to control the radar 112 to emit detection waves according to a preset detection cycle, and detect whether there is an object to be detected in the preset area U according to the echo of the detection wave, and when it is determined that there is an object to be detected in the preset area U, it is judged whether the object to be detected is a moving object according to the change of the distance between the object to be detected and the radar 112 in each detection cycle. Exemplarily, the first processor 111 can determine that the object to be detected is a moving object when the distance between the object to be detected and the radar 112 changes continuously in each detection cycle, and determine that the object to be detected is a non-moving object when the distance between the object to be detected and the radar 112 remains unchanged in each detection cycle.
[0097] In some embodiments, the moving object detection module 11 may also acquire key radar signals and process the key radar signals according to a preset frequency range to detect whether there is a moving living body in the preset area U. A living body refers to an object with vital signs such as a person or an animal in any state.
[0098] Specifically, according to existing medical research results, the frequency range of human physiological signals is generally low. Through spectrum analysis, it can be known that except for the high spectrum components of sound signals (such as heart sounds), the spectrum of other electrophysiological signals is generally low; for example, the heart rate of a normal person is between 0.8 and 2 Hz, and the breathing rate is between 0.1 and 0.5 Hz. Therefore, according to the pseudo-periodic characteristics of cardiopulmonary movements such as human breathing and heartbeat, the key radar signal containing effective information can be locked within a preset frequency range, such as 0.1 to 2 Hz. The first processor 111 can determine that there is a living body within the radar detection range when there is a radar component within the preset frequency range in the above-mentioned key radar signal. Further, the first processor 111 can determine whether the living body is moving according to the change in the distance between the living body and the radar 112 in each detection cycle, and output a first control instruction to the face detection module 12 when it is determined that the living body is moving, and control the face detection module 12 to start.
[0099] In this way, the moving object detection module 11 can distinguish whether the object to be detected is a living body, and control the face detection module 12 to start only when it is determined that the object to be detected is a moving living body, which can further reduce the power consumption of the face detection module 12.
[0100] In some embodiments, the face detection module 12 includes an ultra low power camera (ULPC) 122 and a second processor 121. The second processor 121 is electrically connected to the low power camera 122, and the second processor 121 is used to control the low power camera 122 to obtain multiple images of the moving object at a preset time interval after the face detection module 12 is started, and to determine whether each image includes a face image, and when it is determined that the multiple images all include face images, determine that the moving object is a human body, and determine whether the moving trend of the human body is approaching the detection module 10 based on at least the change of the head posture information of the human body, and when it is determined that the moving trend of the human body is approaching the detection module 10, determine whether to output a second control instruction to the face recognition module 20 based on the distance between the human body and the detection module 10. The second control instruction is used to control the start of the face recognition module 20.
[0101] Exemplarily, the low power camera 122 may be an RGB camera. After receiving the image captured by the low power camera 122, the second processor 121 pre-processes the image to perform contrast correction and eliminate irrelevant image information, thereby improving the recognition of the image.
[0102] In some embodiments, the face detection module 12 further includes a first power supply (not shown), which is electrically connected to the low-power camera 122, the second processor 121, and the first processor 111. The first power supply starts to supply power to the low-power camera 122 and the second processor 121 in response to the first control instruction, thereby starting the face detection module 12.
[0103] In this way, when the face detection module 12 does not need to be started, the first power supply can be directly controlled not to supply power, the control logic is simple, and the energy-saving effect is good.
[0104] In some embodiments, the face detection module 12 may further include a fill light 123, the fill light 123 is electrically connected to the second processor 121, and the second processor 121 also obtains the ambient light intensity, and controls the fill light 123 to turn on for fill light when the ambient light intensity is lower than a preset light intensity (e.g., 50 lux). In this way, the unlocking device 100 can work normally even in a weak light environment.
[0105] In some embodiments, the face recognition module 20 includes a time of flight (TOF) camera 22 and a third processor 21. The third processor 21 is electrically connected to the TOF camera 22, and the third processor 21 is used to control the TOF camera 22 to obtain the face depth image of the human body after the face recognition module 20 is started, perform face recognition on the face depth image, and output an unlocking instruction to control the unlocking of the object to be unlocked after the face recognition is passed.
[0106] Specifically, the third processor 21 is used to extract facial feature points from the facial depth image after acquiring the facial depth image collected by the time-of-flight camera 22, and compare the extracted facial feature points with the facial feature points of the preset facial image, and determine whether the facial recognition is passed according to the comparison result. Among them, the method of performing facial recognition based on facial feature points belongs to the prior art and will not be described in detail here.
[0107] In some embodiments, before performing face recognition, the face recognition module 20 will perform detection through a combination of software and hardware to determine whether the collected face is generated by a photo, video or software simulation. In this way, the anti-counterfeiting and anti-prosthesis attack problems can be solved, and the risk of identity fraud caused by various face forgeries can be effectively avoided, with higher security.
[0108] In some embodiments, the third processor 21 is also used to record the number of face recognition failures when face recognition fails, and to re-acquire the face depth image of the human body and re-perform face recognition when the number of face recognition failures does not reach a preset number, and to control the face recognition module 20 and the face detection module 12 to be turned off when the number of face recognition failures reaches a preset number.
[0109] Exemplarily, the preset number of times is three. In this way, on the one hand, it can avoid the situation where the face recognition fails due to a single failure to successfully capture a complete face depth image, which can improve the recognition success rate; on the other hand, it can avoid the situation where the third processor 21 keeps working and continues to consume power after multiple recognition failures, which can extend the battery life of the unlocking device 100.
[0110] In some embodiments, the face recognition module 20 further includes a second power supply (not shown), which is electrically connected to the time-of-flight camera 22, the third processor 21, and the second processor 121. The second power supply starts to supply power to the time-of-flight camera 22 and the third processor 21 in response to the second control instruction, thereby starting the face recognition module 20.
[0111] In this way, when the face recognition module 20 does not need to be started, the second power supply can be directly controlled not to supply power, the control logic is simple, and the energy-saving effect is good.
[0112] In some embodiments, the face recognition module 20 also includes a display unit 23, which is electrically connected to the third processor 21 and is used to display the image acquired by the low-power camera 122 and / or display the face depth image acquired by the time-of-flight camera 22.
[0113] Exemplarily, the display unit 23 can adopt a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light emitting diode or an active-matrix organic light emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-OLed, a quantum dot light emitting diode (QLED), etc.
[0114] In some embodiments, the face recognition module 20 also includes a memory 24, which is electrically connected to the third processor 21 and is used to store a preset face image entered in advance by the user for the third processor 21 to call for comparison with the face depth image acquired by the time-of-flight camera 22.
[0115] In some embodiments, the operating frequency of the first processor 111 is lower than the operating frequency of the second processor 121, and lower than the operating frequency of the second processor 121. Exemplarily, the operating frequency of the first processor 111 is 128 MHz, and the operating frequencies of the second processor 121 and the third processor 21 are both 400 MHz.
[0116] Thus, by default, the second processor 121 and the third processor 21 with a higher operating frequency are not operated, and only the first processor 111 with a lower operating frequency is operated, which can further reduce the power consumption of the unlocking device 100.
[0117] In some embodiments, the first processor 111, the second processor 121 and the third processor 21 may also be the same processor, that is, the face recognition module 20, the face detection module 12 and the moving object detection module 11 share a processor.
[0118] See also Figure 6 Based on the same inventive concept, the present application also provides an unlocking method, which comprises the following steps:
[0119] Step S1, when the detection module 10 detects a moving object, it obtains an image of the moving object, and when it is determined based on the image that the moving object is a human body approaching the detection module 10, it determines whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10; and
[0120] Step S2, the face recognition module 20 performs face recognition on the human body after startup, and outputs an unlocking instruction to control the unlocking of the object to be unlocked after the face recognition is passed.
[0121] The unlocking method provided by the present application obtains the image of the moving object through the detection module 10 when monitoring the moving object, and when determining based on the image that the moving object is a human body approaching the detection module 10, determines whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10, and uses the face recognition module 20 to perform face recognition on the human body after startup. In this way, when the user approaches the detection module 10, the face recognition module 20 will be automatically triggered to start the face recognition function to unlock. On the one hand, the face recognition module 20 is only started when the detection module 10 monitors the moving object and determines that the moving object is a human body approaching the detection module 10, and the energy consumption is lower. On the other hand, in the entire unlocking process, the user does not need to operate or wait to achieve senseless unlocking, and the intelligence level is higher, the unlocking is more convenient and efficient, and the user experience is better.
[0122] In some embodiments, the detection module 10 includes a face detection module 12. When the detection module 10 detects a moving object, it obtains an image of the moving object, and when it is determined based on the image that the moving object is a human body approaching the detection module 10, it determines whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10, including:
[0123] The face detection module 12 acquires a plurality of images of the moving object at a preset time interval, and determines whether each image includes a face image;
[0124] When the face detection module 12 determines that the multiple images all include face images, it determines that the moving object is a human body, and judges whether the moving trend of the human body is approaching the detection module 10 based on at least the change of the head posture information of the human body in the multiple images; and
[0125] When the face detection module 12 determines that the movement trend of the human body is approaching the detection module 10 , the face detection module 12 determines whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10 .
[0126] In some embodiments, the face detection module 12 acquires multiple images of the moving object at preset time intervals, and determines whether each image includes a face image, including:
[0127] The face detection module 12 determines that the image includes a face image when the image includes image information matching a preset face template.
[0128] In some embodiments, when the face detection module 12 determines that the multiple images all include face images, it determines that the moving object is a human body, and judges whether the moving trend of the human body is approaching the detection module 10 based on at least the change of the head posture information of the human body in the multiple images, including:
[0129] When determining that the plurality of images all include face images, the face detection module 12 obtains face feature points of the face images in each image, and determines whether the face images in each image all include face images of the same person according to the face feature points of the face images in each image; and
[0130] When the face detection module 12 determines that the face images in each image include the face images of the same person, it judges whether the movement trend of the target person is approaching the detection module 10 based on at least the change of the head posture information of the target person in the multiple images.
[0131] The target human body is the human body corresponding to the face image that appears in each image.
[0132] In some embodiments, when the face detection module 12 determines that the face images in each image include the face image of the same person, judging whether the movement trend of the target person is approaching the detection module 10 based on at least the change of the head posture information of the target person in the multiple images includes:
[0133] When the face detection module 12 determines that the face images in each image include the face images of the same person, it judges whether the movement trend of the target person is approaching the detection module 10 based on the changes in the head posture information of the target person in the multiple images and the changes in the distance between the target person and the detection module 10.
[0134] In some embodiments, the head posture information of the target person includes the Euler angle of the head of the target person. When the face detection module 12 determines that the face images in each image include the face images of the same person, it determines whether the movement trend of the target person is approaching the detection module 10 based on the change of the head posture information of the target person in the multiple images and the change of the distance between the target person and the detection module 10, including:
[0135] When the face detection module 12 determines that the face images in each image include the face images of the same person, it calculates the Euler angles of the head of the target person in each image and the difference between the Euler angles of the head of the target person in any two adjacent images, and when the difference between the Euler angles of the head of the target person in any two adjacent images is less than a preset angle threshold, and the distance between the target person and the detection module 10 gradually becomes smaller, it is determined that the moving trend of the target person is approaching the detection module 10.
[0136] In some embodiments, the detection module 10 further includes a moving body detection module 11. The unlocking method further includes:
[0137] The moving object detection module 11 detects whether there is a moving object in the preset area U when the object to be unlocked is in a locked state, and when it is determined that there is a moving object in the preset area U, detects the distance between the moving object and the detection module 10; wherein the distance between each position point in the preset area U and the detection module 10 is greater than the first preset distance and less than the second preset distance; and,
[0138] The moving object detection module 11 determines whether to control the face detection module 12 to start based on the distance between the moving object and the detection module 10 .
[0139] In some embodiments, the moving object detection module 11 determines whether to control the face detection module 12 to start based on the distance between the moving object and the detection module 10, including:
[0140] The moving object detection module 11 controls the face detection module 12 to start when the distance between the moving object and the detection module 10 is less than or equal to a third preset distance, wherein the third preset distance is less than the second preset distance and greater than the first preset distance.
[0141] In some embodiments, when the face detection module 12 determines that the moving object is a human body approaching the detection module 10, the face detection module 12 determines whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10, including:
[0142] When the face detection module 12 determines that the moving object is a human body approaching the detection module 10 and the distance between the human body and the detection module 10 is less than or equal to a fourth preset distance, the face recognition module 20 is controlled to start; wherein the fourth preset distance is less than the third preset distance and greater than the first preset distance.
[0143] In some embodiments, the unlocking method further includes:
[0144] When the moving object detection module 11 determines that there is a moving object in the preset area U, and the distance between the moving object and the detection module 10 is less than the fourth preset distance d4, and when the face detection module 12 and the face recognition module 20 are both in the off state, the face detection module 12 is controlled to start;
[0145] The face detection module 12 detects whether the moving object is a human body after being started;
[0146] The face detection module 12 controls the face recognition module 20 to start when determining that the moving object is a human body; and
[0147] The face recognition module 20 performs face recognition on the human body after startup, and outputs an unlocking instruction to control the unlocking of the object to be unlocked after the face recognition is passed.
[0148] It should be noted that the unlocking method corresponds to the aforementioned unlocking device 100. For a more detailed description, please refer to the contents of the various embodiments of the unlocking device 100 in the foregoing text. The unlocking method and the contents of the aforementioned unlocking device 100 may also refer to each other.
[0149] Please also read Figure 7-Figure 8 , Figure 7 is a schematic diagram of the back structure of a vehicle pillar assembly provided in an embodiment of the present application; Figure 8The front structural diagram of the vehicle pillar assembly provided in the embodiment of the present application is based on the same inventive concept. The present application also provides a vehicle pillar assembly 1, the vehicle pillar assembly 1 comprising the unlocking device 100 described in any of the above embodiments.
[0150] In some embodiments, the vehicle pillar assembly 1 further includes a bracket 2 , and the unlocking device 100 is installed in the bracket 2 .
[0151] In some embodiments, the vehicle pillar assembly 1 further includes a sealing strip 3 , which is disposed between the unlocking device 100 and the bracket 2 , and is used to prevent water droplets and dust from entering the unlocking device 100 .
[0152] In some embodiments, the vehicle pillar assembly 1 is disposed on a side of the vehicle pillar facing outward from the vehicle, and has the function of decorating the appearance of the vehicle.
[0153] In some embodiments, the face recognition module 20 in the unlocking device 100 includes a time-of-flight camera 22 , and the time-of-flight camera 22 includes a TOF transmitting unit 221 and a TOF receiving unit 222 .
[0154] The detection module 10 in the unlocking device 100 includes a moving body detection module 11 and a face detection module 12. The face detection module 12 includes the fill light 123 and the low-power camera 122 disposed below the time-of-flight camera 22, and the moving body detection module 11 includes a radar 112 disposed below the face detection module 12.
[0155] Based on the same inventive concept, the present application also provides a vehicle, which includes the unlocking device 100 described in any of the above embodiments, and the unlocking device 100 is used to control the unlocking of the vehicle.
[0156] The vehicle pillar assembly 1 and the vehicle provided by the present application, when the detection module 10 monitors a moving object, obtains an image of the moving object, and when it is determined based on the image that the moving object is a human body approaching the detection module 10, it determines whether to control the face recognition module 20 to start based on the distance between the human body and the detection module 10, and the face recognition module 20 is used to perform face recognition on the human body after startup. In this way, when the user approaches the detection module 10, the face recognition module 20 will be automatically triggered to start the face recognition function to unlock. On the one hand, the face recognition module 20 is only started when the detection module 10 monitors the moving object and determines that the moving object is a human body approaching the detection module 10, and the energy consumption is lower; on the other hand, compared with the method in the related art that requires the driver to activate the face recognition system by touching the button on the pillar, in the entire unlocking process, there is no need for the user to operate or wait to achieve senseless unlocking, the intelligence level is higher, the unlocking is more convenient and efficient, and the user experience is better.
[0157] Based on the same inventive concept, the present application also provides a computer-readable storage medium, in which a computer program is stored. The computer program is used for being called and executed by a processor to implement the steps in the unlocking method described in any of the above embodiments.
[0158] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable media. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive lists) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing programs, which can be used by instruction execution systems, devices or devices or used in combination with them.
[0159] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0160] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0161] Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer or may be connected to an external computer (e.g., via the Internet using an Internet service provider) through any type of network, including a local area network (LAN) or a wide area network (WAN).
[0162] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.
Claims
1. An unlocking device, characterized in that: The unlocking device includes a detection module and a face recognition module; The detection module is used to acquire an image of the moving object when a moving object is detected, and when it is determined based on the image that the moving object is a human body approaching the detection module, determine whether to control the face recognition module to start based on the distance between the human body and the detection module; The face recognition module is used to perform face recognition on the human body after startup, and output an unlocking instruction to control the unlocking of the object to be unlocked after the face recognition is passed.
2. The unlocking device according to claim 1, characterized in that: The detection module includes a face detection module; the face detection module is used to obtain multiple images of the moving object at preset time intervals, determine whether each image includes a face image, and when it is determined that the multiple images all include face images, determine that the moving object is a human body, and at least based on the change of the head posture information of the human body in the multiple images, determine whether the movement trend of the human body is approaching the detection module, and when it is determined that the movement trend of the human body is approaching the detection module, determine whether to control the face recognition module to start based on the distance between the human body and the detection module.
3. The unlocking device according to claim 2, characterized in that: The face detection module is specifically used to determine that the image includes a face image when the image includes image information matching a preset face template.
4. The unlocking device according to claim 2, characterized in that: The face detection module is specifically used to obtain facial feature points of the facial images in each image when it is determined that the multiple images all include facial images, and judge whether the facial images in each image all include facial images of the same person based on the facial feature points of the facial images in each image, and when it is determined that the facial images in each image all include facial images of the same person, judge whether the movement trend of the target person is approaching the detection module based at least on the change of the head posture information of the target person in the multiple images; wherein the target person is the person corresponding to the facial images that appear in each image.
5. The unlocking device according to claim 4, characterized in that: The face detection module is specifically used to determine whether the target person's movement trend is approaching the detection module based on changes in the head posture information of the target person in the multiple images and changes in the distance between the target person and the detection module.
6. The unlocking device according to claim 5, characterized in that: The head posture information of the target person includes the Euler angles of the head of the target person; the face detection module is specifically used to calculate the Euler angles of the head of the target person in each image and the difference between the Euler angles of the head of the target person in any two adjacent images, and when the difference between the Euler angles of the head of the target person in any two adjacent images is less than a preset angle threshold, and the distance between the target person and the detection module gradually becomes smaller, it is determined that the moving trend of the target person is approaching the detection module.
7. The unlocking device according to claim 2, characterized in that: The detection module also includes a moving object detection module; the moving object detection module is used to detect whether there is a moving object in a preset area when the object to be unlocked is in a locked state, and when it is determined that there is a moving object in the preset area, detect the distance between the moving object and the detection module, and determine whether to control the face detection module to start based on the distance between the moving object and the detection module; wherein the distance between each position point in the preset area and the detection module is greater than the first preset distance and less than the second preset distance.
8. The unlocking device according to claim 7, characterized in that: The moving object detection module is specifically used to control the face detection module to start when the distance between the moving object and the detection module is less than or equal to a third preset distance; wherein the third preset distance is less than the second preset distance and greater than the first preset distance.
9. The unlocking device according to claim 8, characterized in that: The face detection module is specifically used to control the face recognition module to start when it is determined that the moving object is a human body approaching the detection module and the distance between the human body and the detection module is less than or equal to a fourth preset distance; wherein the fourth preset distance is less than the third preset distance and greater than the first preset distance.
10. The unlocking device according to claim 7, characterized in that: The moving object detection module comprises: Radar; and The first processor is electrically connected to the radar, and is used to control the radar to emit a detection wave when the object to be unlocked is in a locked state, and detect whether there is a moving object in the preset area according to the echo of the detection wave, and when it is determined that there is a moving object in the preset area, determine whether to output a first control instruction to the face detection module based on the distance between the moving object and the detection module; wherein the first control instruction is used to control the start of the face detection module.
11. The unlocking device according to claim 10, characterized in that: The face detection module comprises: Low-power camera; and The second processor is electrically connected to the low-power camera, and is used to control the low-power camera to obtain multiple images of the moving object at preset time intervals after the face detection module is started, and determine whether each image includes a face image, and when it is determined that the multiple images all include face images, determine that the moving object is a human body, and determine whether the moving trend of the human body is approaching the detection module based on at least the change of the head posture information of the human body, and when it is determined that the moving trend of the human body is approaching the detection module, determine whether to output a second control instruction to the face recognition module based on the distance between the human body and the detection module; wherein the second control instruction is used to control the start of the face recognition module.
12. The unlocking device according to claim 11, characterized in that: The face detection module also includes a first power supply, which is electrically connected to the low-power camera, the second processor and the first processor; the first power supply starts to supply power to the low-power camera and the second processor in response to the first control instruction, thereby starting the face detection module.
13. The unlocking device according to claim 11, characterized in that: The face recognition module comprises: Time-of-flight cameras; and The third processor is electrically connected to the time-of-flight camera, and is used to control the time-of-flight camera to obtain the face depth image of the human body after the face recognition module is started, and to perform face recognition on the face depth image, and to output an unlocking instruction to control the unlocking of the object to be unlocked after the face recognition is passed.
14. The unlocking device according to claim 13, characterized in that: The face recognition module also includes a second power supply, which is electrically connected to the time-of-flight camera, the third processor and the second processor; the second power supply starts to supply power to the time-of-flight camera and the third processor in response to the second control instruction, thereby starting the face recognition module.
15. An unlocking method, characterized in that: The unlocking method comprises: When the detection module detects a moving object, it acquires an image of the moving object, and when it is determined based on the image that the moving object is a human body approaching the detection module, it determines whether to control the face recognition module to start based on the distance between the human body and the detection module; and The face recognition module performs face recognition on the human body after startup, and outputs an unlocking instruction to control the unlocking of the object to be unlocked after the face recognition is passed.
16. The unlocking method according to claim 15, characterized in that: The detection module includes a face detection module; When the detection module detects a moving object, it obtains an image of the moving object, and when it is determined based on the image that the moving object is a human body approaching the detection module, it determines whether to control the face recognition module to start based on the distance between the human body and the detection module, including: The face detection module acquires a plurality of images of the moving object at a preset time interval and determines whether each image includes a face image; When the face detection module determines that the multiple images all include face images, it determines that the moving object is a human body, and judges whether the moving trend of the human body is approaching the detection module based on at least the change of the head posture information of the human body in the multiple images; and When the face detection module determines that the movement trend of the human body is approaching the detection module, the face detection module determines whether to control the face recognition module to start based on the distance between the human body and the detection module.
17. The unlocking method according to claim 16, characterized in that: The face detection module acquires a plurality of images of the moving object at a preset time interval and determines whether each image includes a face image, including: The face detection module determines that the image includes a face image when the image includes image information matching a preset face template.
18. The unlocking method according to claim 16, characterized in that: When the face detection module determines that the multiple images all include face images, determining that the moving object is a human body, and judging whether the moving trend of the human body is approaching the detection module based on at least the change of the head posture information of the human body in the multiple images, includes: When the face detection module determines that the multiple images all include face images, it obtains face feature points of the face images in each image, and determines whether the face images in each image all include face images of the same person according to the face feature points of the face images in each image; and When the face detection module determines that the face images in each image include face images of the same person, it judges whether the movement trend of the target person is approaching the detection module based on at least the change of the head posture information of the target person in the multiple images; wherein the target person is the person corresponding to the face image that appears in each image.
19. The unlocking method according to claim 18, characterized in that: When the face detection module determines that the face images in each image include the face image of the same person, judging whether the movement trend of the target person is approaching the detection module based on at least the change of the head posture information of the target person in the multiple images, includes: When the face detection module determines that the face images in each image include the face images of the same person, it judges whether the movement trend of the target person is approaching the detection module based on the changes in the head posture information of the target person in the multiple images and the changes in the distance between the target person and the detection module.
20. The unlocking method according to claim 19, characterized in that: The head posture information of the target person includes the Euler angle of the head of the target person; when the face detection module determines that the face images in each image include the face image of the same person, judging whether the movement trend of the target person is approaching the detection module based on the change of the head posture information of the target person in the multiple images and the change of the distance between the target person and the detection module, including: When the face detection module determines that the face images in each image include the face image of the same person, the Euler angles of the head of the target person in each image and the difference between the Euler angles of the head of the target person in any two adjacent images are calculated, and when the difference between the Euler angles of the head of the target person in any two adjacent images is less than a preset angle threshold, and the distance between the target person and the detection module gradually becomes smaller, it is determined that the moving trend of the target person is approaching the detection module.
21. The unlocking method according to claim 17, characterized in that: The detection module further includes a moving body detection module; and the unlocking method further includes: The moving object detection module detects whether there is a moving object in a preset area when the object to be unlocked is in a locked state, and when it is determined that there is a moving object in the preset area, detects the distance between the moving object and the detection module; wherein the distance between each position point in the preset area and the detection module is greater than a first preset distance and less than a second preset distance; and The moving object detection module determines whether to control the face detection module to start based on the distance between the moving object and the detection module.
22. The unlocking method according to claim 21, characterized in that: The moving object detection module determines whether to control the face detection module to start based on the distance between the moving object and the detection module, including: The moving object detection module controls the face detection module to start when the distance between the moving object and the detection module is less than or equal to a third preset distance; wherein the third preset distance is less than the second preset distance and greater than the first preset distance.
23. The unlocking method according to claim 22, characterized in that: When the face detection module determines that the moving object is a human body approaching the detection module, the face detection module determines whether to control the face recognition module to start based on the distance between the human body and the detection module, including: When the face detection module determines that the moving object is a human body approaching the detection module and the distance between the human body and the detection module is less than or equal to a fourth preset distance, the face recognition module is controlled to start; wherein the fourth preset distance is less than the third preset distance and greater than the first preset distance.
24. A vehicle pillar assembly, characterized in that: Comprising an unlocking device as described in any one of claims 1-14.
25. A vehicle, characterized in that: It comprises the unlocking device as described in any one of claims 1 to 14, and the unlocking device is used to control the unlocking of the vehicle.
