CN113641415B - Unlocking method and device based on face recognition - Google Patents
Unlocking method and device based on face recognition Download PDFInfo
- Publication number
- CN113641415B CN113641415B CN202111195272.8A CN202111195272A CN113641415B CN 113641415 B CN113641415 B CN 113641415B CN 202111195272 A CN202111195272 A CN 202111195272A CN 113641415 B CN113641415 B CN 113641415B
- Authority
- CN
- China
- Prior art keywords
- pixel points
- depth
- full
- time
- distance measuring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/4401—Bootstrapping
- G06F9/4418—Suspend and resume; Hibernate and awake
Abstract
The invention relates to an unlocking method and device based on face recognition, wherein the method comprises the following steps: a. enabling a part of pixel points in the distance measuring sensor to detect the brightness change of the environment in real time; b. judging whether an object approaches when the brightness change meets the triggering condition; c. if an object approaches, awakening the rest pixel points in the distance measuring sensor; d. and identifying the approaching object, and selecting whether to unlock according to the identification result. The invention can reduce power consumption to realize long-time standby, can meet the requirement of large-angle monitoring, and does not need to increase more elements.
Description
Technical Field
The invention relates to an unlocking method and device based on face recognition.
Background
The door locks generally include mechanical door locks, electronic door locks, combination door locks, fingerprint door locks, and face recognition door locks. The types of the face recognition door lock mainly comprise a monocular face door lock, a binocular face door lock, a face recognition door lock based on structured light and a face recognition door lock based on TOF depth measurement. The principle of tof (time of Light flight) is to measure the distance by using the time of flight of Light, so that 3D data of a human face can be measured. Therefore, the 3D point cloud formed by the TOF camera is utilized, and the face recognition can be realized based on the three-dimensional space information; and a TOF camera can be additionally arranged on the basis of an RGB or IR camera, so that the living body detection work in the face recognition is realized by using 3D data measured by the TOF.
In the existing face recognition door lock based on TOF depth measurement, a TOF camera and VCSEL illumination are usually combined for use. The main energy consumption components comprise power consumption generated by calculation force of the TOF sensor, the VCSEL illuminator and the depth calculation module, and the power consumption of the whole door lock is higher after superposition, so that the requirement of standby for a very long time cannot be met. Therefore, some technologies need to provide an independent battery to supply power, which also highlights the strong demand of the door lock for low power consumption and ultra-long standby time, so that reducing the power consumption becomes an important part for the practicability of the door lock.
In order to achieve the purpose of reducing power consumption, some technologies set a standby mode in the door lock, so that the door lock is in a standby state most of the time after being started, and only when a certain trigger condition is reached, the door lock is waken up to exit from the low power consumption mode and be converted into a full-speed working state. The existing standby wake-up mode generally detects the change of environment through an external switch or other sensors, so that when the change of environment is found, the whole door lock is woken up. In these technologies, the environment detection is usually realized by using a touch-sensitive switch or an infrared-sensitive switch, however, the additional external detection component increases the volume of the door lock, and the reliability of the system is also reduced due to the addition of components.
Of course, there are also techniques that employ single-point TOF sensors to achieve ranging. These techniques typically incorporate a single point TOF sensor that measures range during standby mode. When the door lock is detected to be approached by a person, the whole door lock is powered on again, and the door lock is awakened. Although the power consumption of the single-point TOF is low, the detection range is extremely limited, and the requirement of large FOV monitoring cannot be met.
Disclosure of Invention
The invention aims to provide an unlocking method and device based on face recognition.
In order to achieve the above object, the present invention provides an unlocking method and device based on face recognition, the method includes the following steps:
a. enabling a part of pixel points in the distance measuring sensor to detect the brightness change of the environment in real time;
b. judging whether an object approaches when the brightness change meets the triggering condition;
c. if an object approaches, awakening the rest pixel points in the distance measuring sensor;
d. and identifying the approaching object, and selecting whether to unlock according to the identification result.
According to an aspect of the present invention, in the step (a), the ranging sensor detects the environmental change using brightness information.
According to an aspect of the present invention, in the step (b), if the variation value of the brightness of the single pixel point between two frames is larger than the brightness threshold ThNumber of pixel points NiGreater than a first set natural number threshold NaJudging that the ambient brightness change meets the triggering condition;
when the environmental brightness change meets the triggering condition, depth calculation is carried out on the full-time working pixel points, and if the current depth D is reachedtLess than the previous depth Dt-1Number of pixel points NtGreater than a second natural number threshold NbAnd judging that an object approaches.
According to an aspect of the present invention, in the step (c), if it is determined that no object is currently close according to the depth value of the full-time working point, continuing to perform the next depth statistical determination;
and if no object approaches within a certain depth statistics judgment time Tc, returning to the step of judging the brightness change again.
According to one aspect of the present invention, in the step (c), after the rest of the pixel points in the distance measuring sensor are awakened, phase images of all the pixel points are output and complete depth calculation is performed;
judging whether the approaching object is a human face or not according to the depth information obtained by calculation in the step (d);
after the face is judged, the phase image is compared with the face ID stored in the database, or the characteristics of the phase image or the phase image are uploaded to a network server for face recognition, and unlocking is carried out when the unlocking condition is met.
Unlocking device based on face identification includes: the device comprises a lens, a distance measuring sensor used for detecting brightness and depth, a light source used for providing illumination, a processor used for face recognition and an unlocking mechanism used for executing unlocking operation according to a face recognition result.
According to one aspect of the invention, a built-in single chip microcomputer is arranged in the distance measuring sensor.
According to one aspect of the invention, the distance measuring sensor is a TOF sensor, and comprises full-time pixel points working in real time and common pixel points working after being awakened;
signals are output through an ROI control and reading circuit when only full-time pixel points in the TOF sensor work, and signals are output through a full-array control and reading circuit when all the pixel points in the TOF sensor work;
the light source is a VCSEL, and the processor is a DSP.
According to one aspect of the present invention, a part of the light emitting units in the VCSEL emit light in real time, and another part of the light emitting units emit light after the common pixel is awakened.
According to one aspect of the invention, a diffraction plate is used to cause the light emitted by the VCSEL to cover the field of view of the full-time pixel.
According to the concept of the invention, the pixel points on the pixel array of the TOF sensor are divided into full-time pixel points and common pixel points, the full-time pixel points work and output signals when in standby and full-speed, and the common pixel points work and output signals only in a full-speed mode. Therefore, the brightness change and the depth change of the image can be detected by utilizing the full-time pixel points, and the common pixel points with the largest occupation ratio are all in a non-power consumption state without power supply, so that the power consumption of the TOF sensor during standby is reduced.
According to one scheme of the invention, the light-emitting units of the VCSEL are separately arranged, so that the light-emitting units can concentrate energy to illuminate pixel points in a region of interest (ROI), and the power consumption of the VCSEL is reduced in standby.
According to one scheme of the invention, the detection of the brightness and the depth is completed in a low power consumption mode, so that the power consumption of the detection module during standby is reduced, the door lock can be in standby for a long time, the requirement of large-angle monitoring can be met, and new elements do not need to be added.
Drawings
FIG. 1 schematically illustrates a flow chart of a TOF sensor wake-up procedure for an unlocking method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a pixel array of a TOF sensor in a low power consumption standby state in an unlocking apparatus according to an embodiment of the present invention (black is a full time pixel; white is a normal pixel);
fig. 3 is a block diagram schematically showing the structure of a TOF sensor in the unlocking apparatus according to an embodiment of the present invention;
fig. 4 is a block diagram schematically showing the structure of an unlocking apparatus according to an embodiment of the present invention;
FIG. 5 is a schematic diagram showing the illumination mode of VCSELs in an unlocking device according to an embodiment of the present invention (black is the full-speed operating point; white is the full-speed operating point, and is not operated during standby);
fig. 6 is a view schematically showing an illumination mode of a VCSEL in an unlocking apparatus according to another embodiment of the present invention.
Detailed Description
To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made
The drawings that are required to be used in the embodiments will be briefly described. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
The present invention is described in detail below with reference to the drawings and the specific embodiments, which are not repeated herein, but the embodiments of the present invention are not limited to the following embodiments.
Referring to fig. 1, the unlocking method based on face recognition of the invention is suitable for a face recognition door lock. In the method, firstly, a part of pixel points in the distance measuring sensor detect the brightness change of the environment in real time, when the brightness change meets the triggering condition, whether an object approaches is judged, if so, the rest pixel points in the distance measuring sensor are awakened, the approaching object is identified (human face), and whether unlocking is carried out is selected according to the identification result.
In the present invention, the ranging sensor detects environmental changes using luminance information.
In the invention, if the change value of the brightness of a single pixel point between two frames is larger than the brightness threshold value ThNumber of pixel points NiGreater than a first set natural number threshold NaAnd judging that the ambient brightness change meets the trigger condition, namely the ambient brightness changes. At this time, depth calculation is performed on the working pixels (i.e. full-time working pixels), and if the current depth D is larger than the preset depth DtLess than the previous depth Dt-1Number of pixel points NtGreater than a second natural number threshold NbAnd judging that an object approaches. If the depth value of the full-time working point is judged that no object approaches the current time T, the depth counting judgment of the next time T +1 is continued, the process is circulated, and if no object approaches the current time T within a certain depth counting judgment time Tc (such as 100 times), the process of judging the brightness change is returned again.
In the invention, after other pixel points in the distance measuring sensor are awakened, phase images of all the pixel points are output, complete depth calculation is carried out, and whether an approaching object is a human face or not is judged according to depth information obtained by calculation. After the face is judged, the phase image can be compared with the face ID stored in the database, or the characteristics of the phase image or the phase image can be uploaded to a network server for face recognition, and unlocking is carried out when the unlocking condition is met.
The invention relates to an unlocking device (door lock) based on face recognition, which comprises: the system comprises a lens, a distance measuring sensor used for detecting brightness and depth (or distance) changes, a light source used for providing illumination, a processor used for face recognition and an unlocking mechanism used for executing unlocking operation according to a face recognition result.
Referring to fig. 2, the distance measuring sensor in the present invention is a TOF sensor (chip) on which pixels (pixels) arranged in a dot matrix are disposed, and includes a plurality of full-time pixels working in real time and arranged according to a certain rule and a common Pixel that works after being awakened. When the lock is in standby state, TOF sensor is also in standby state, but these full-time pixel points are in operating condition, are detecting and output the sensitization signal external environment luminance promptly all the time. The device firstly checks whether the brightness of the full-time pixel points changes or not, and if the brightness does change and meets corresponding conditions, the depth value change detection of the full-time pixel points is started. If the depth change of the corresponding positions of the full-time pixel points also meets the corresponding conditions (namely, objects are close), the common pixel points are awakened to carry out full-signal output, so that the whole door lock enters a full-speed working mode, and complete face recognition and door lock unlocking control are carried out. Of course, the distribution of these full-time pixels and normal pixels can be in other patterns. Therefore, in the standby state, except the full-time pixel points, other parts are in the state of no power supply or low power consumption, and the effect of reducing the power consumption is achieved.
Referring to fig. 3, in the present invention, a built-in low power consumption single chip Microcomputer (MCU) integrated in the TOF sensor is further provided, and is configured to receive the photosensitive signals transmitted by the full-time pixels to detect changes in the external environment, and when the external environment changes (i.e., brightness changes) are found, the whole TOF sensor is awakened, and a complete phase image is output through the image output interface. Like this, realized concentrating on inside the TOF sensor with the awakening function of device to reduced the peripheral circuit of lock, not only reduced the consumption, still improved the stability of lock. Of course, in other embodiments, the module for implementing TOF depth detection may also be placed in an external low-power-consumption single chip microcomputer.
As shown in fig. 4, in the present invention, the light source is a VCSEL (vertical cavity surface emitting laser) and the processor is a DSP (digital signal processor). From this, TOF sensor, camera lens, VCSEL and corresponding drive circuit have constituteed a TOF camera, and it accomplishes the detection function whether to external environment change through the hierarchical mode of different consumption for this device forms a low-power consumption face unblock module based on TOF camera. Therefore, when the MCU wakes up the common pixel point, the MCU also wakes up the DSP with the rear end as the identity ID identification part. At this time, the DSP starts to take over the depth calculation work in the whole TOF view field, and whether the object is a living human face can be judged based on the TOF depth information obtained through calculation. According to the method, if the living human face is judged to be the living human face, the living human face can be compared with the human face ID stored in the database, or the phase image or the characteristic data thereof is uploaded to the network server for recognition in a wireless WIFI mode, and after the recognition result is obtained from the network server, whether the door lock meets the opening condition is judged, and the door lock is opened by the unlocking mechanism serving as the door lock action control part.
In the invention, in order to further reduce power consumption, the illumination light path of the VCESL is also optimally designed. Specifically, the illumination light emitted by the VCSEL in the standby state mainly covers the range of the full-time pixel point for receiving the reflected light, so that the invalid illumination interval is reduced, the luminous power requirement is reduced, and the illumination utilization rate is improved. To achieve this, the present invention provides the following two ways:
as shown in fig. 5, the first way is to divide the light emitting units of the VCSEL into two groups, so that some of the light emitting units in the VCSEL emit VSCEL light in real time, i.e., operate at both standby and full speed; the other part of the light-emitting units do not emit light when in standby, and only emit light and generate output signals under the full-speed working state after the common pixel points are awakened, so that the power consumption is low when in standby.
A second way is to use a diffraction element (DOE) to concentrate the light emitted by the VCSEL more in certain directions, thereby concentrating the higher intensity of the light, as shown in fig. 6. Specifically, the diffracted light passing through the DOE can be formed into lines, dots, matrices or other arbitrary patterns, so that the diffracted light can just cover the direction reached by the field of view of the full-time pixel points.
Therefore, the VSCEL lighting mode enables the light rays to have a certain mode, such as a point mode or a strip mode, so that the light ray energy is more concentrated, the distance measurement function at a longer distance can be realized, the longer environmental change can be monitored, the standby state can be quitted in time, the arrival information of a vehicle owner can be better responded, the unlocking delay time is shortened, and better human-computer interaction experience is provided.
Therefore, the device has three operation states, namely a low power consumption mode, a wake-up function and full-speed operation. One of the working states can be selected according to the field condition through real-time detection. And the whole door lock system is in a low power consumption state most of the time, so the average power consumption is very low.
In the low power consumption mode, the depth is not directly calculated, but the MCU judges the brightness change by utilizing the gray scale information to detect whether the environment changes, so that a large amount of calculation can be reduced to reduce the power consumption, therefore, the calculation can be completed by a low-speed MCU, and the phase can also be called as an extremely low power consumption mode. In addition, in the standby state, the MCU only performs deep calculation on a few standby points, and the power consumption is still low, so that a low-speed MCU can still complete the calculation, which may also be referred to as a low-power mode. The depth information of the full-time working point is used as a trigger signal for the whole door lock to exit the standby mode, so that the stability of the system is improved, and the false triggering caused by the brightness change of the image, particularly the false triggering caused by the gray scale change of the point caused by the shaking of the tree, is reduced. Therefore, the door lock is ensured to be in a stable standby state, and the power consumption of the system is further reduced.
In conclusion, the average power consumption of the device is reduced from 5W to 0.1W through the design of low power consumption, and the service life of the battery is prolonged by 50 times.
The above description is only one embodiment of the present invention, and is not intended to limit the present invention, and it is apparent to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. An unlocking method based on face recognition comprises the following steps:
a. enabling a part of pixel points in the distance measuring sensor to detect the brightness change of the environment in real time;
b. judging whether an object approaches when the brightness change meets the triggering condition;
c. if an object approaches, awakening the rest pixel points in the distance measuring sensor;
d. identifying an approaching object, and selecting whether to unlock according to an identification result;
if the change value of the brightness of a single pixel point between two frames is larger than the brightness threshold value ThNumber of pixel points NiGreater than a first set natural number threshold NaJudging that the ambient brightness change meets the triggering condition;
when the environmental brightness change meets the triggering condition, depth calculation is carried out on the full-time working pixel points, and if the current depth D is reachedtLess than the previous depth Dt-1Number of pixel points NtGreater than a second natural number threshold NbJudging that an object approaches;
and (c) outputting phase images of all pixel points after other pixel points in the distance measuring sensor are awakened and performing complete depth calculation.
2. The method of claim 1, wherein in step (a), the ranging sensor detects an environmental change using brightness information.
3. The method according to claim 1, wherein in the step (c), if it is determined that no object is approaching at present according to the depth value of the full-time working point, the next depth statistical determination is continued;
and if no object approaches within a certain depth statistics judgment time Tc, returning to the step of judging the brightness change again.
4. The method of claim 1,
judging whether the approaching object is a human face or not according to the depth information obtained by calculation in the step (d);
after the face is judged, the phase image is compared with the face ID stored in the database, or the characteristics of the phase image or the phase image are uploaded to a network server for face recognition, and unlocking is carried out when the unlocking condition is met.
5. An apparatus for carrying out the method of any one of claims 1 to 4, comprising: the device comprises a lens, a distance measuring sensor used for detecting brightness and depth, a light source used for providing illumination, a processor used for face recognition and an unlocking mechanism used for executing unlocking operation according to a face recognition result.
6. The device of claim 5, wherein a built-in single chip microcomputer is arranged in the distance measuring sensor.
7. The device of claim 5, wherein the distance measuring sensor is a TOF sensor, and comprises full-time pixels working in real time and common pixels working after being awakened;
signals are output through an ROI control and reading circuit when only full-time pixel points in the TOF sensor work, and signals are output through a full-array control and reading circuit when all the pixel points in the TOF sensor work;
the light source is a VCSEL, and the processor is a DSP.
8. The apparatus of claim 7, wherein a portion of the light emitting units in the VCSEL emit light in real time, and another portion of the light emitting units emit light after the common pixel is awakened.
9. The apparatus of claim 7, wherein a diffraction plate is used to cause the light emitted from the VCSEL to cover the field of view of the full-time pixels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111195272.8A CN113641415B (en) | 2021-10-14 | 2021-10-14 | Unlocking method and device based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111195272.8A CN113641415B (en) | 2021-10-14 | 2021-10-14 | Unlocking method and device based on face recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113641415A CN113641415A (en) | 2021-11-12 |
| CN113641415B true CN113641415B (en) | 2022-02-11 |
Family
ID=78426803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111195272.8A Active CN113641415B (en) | 2021-10-14 | 2021-10-14 | Unlocking method and device based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113641415B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109150152A (en) * | 2017-06-27 | 2019-01-04 | 原相科技股份有限公司 | Optical profile type control key and its operation method and imaging sensor |
| CN209064053U (en) * | 2018-10-31 | 2019-07-05 | 信利光电股份有限公司 | A kind of arrangements for automotive doors |
| CN110456379A (en) * | 2019-07-12 | 2019-11-15 | 深圳奥比中光科技有限公司 | The depth measurement device and distance measurement method of fusion |
| WO2020019760A1 (en) * | 2018-07-27 | 2020-01-30 | 北京市商汤科技开发有限公司 | Living body detection method, apparatus and system, and electronic device and storage medium |
| CN110930556A (en) * | 2019-12-04 | 2020-03-27 | 浙江凯迪仕实业有限公司 | 3D face identification intelligence lock |
| CN210402486U (en) * | 2019-11-20 | 2020-04-24 | 辽宁丽景科技有限公司 | Induction self-powered face recognition intelligent door lock based on TOF technology |
| CN111332252A (en) * | 2020-02-19 | 2020-06-26 | 上海商汤临港智能科技有限公司 | Vehicle door unlocking method, device, system, electronic equipment and storage medium |
| WO2020196087A1 (en) * | 2019-03-27 | 2020-10-01 | パナソニックＩｐマネジメント株式会社 | Distance measurement device and image generation method |
| CN213365014U (en) * | 2020-07-31 | 2021-06-04 | 深圳市光微科技有限公司 | Miniature TOF single-point range finding module and miniature TOF single-point range finding equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101861765B1 (en) * | 2011-03-03 | 2018-05-29 | 삼성전자주식회사 | Depth pixel including microlens and depth sensor including the depth pixel |
| TW201743074A (en) * | 2016-06-01 | 2017-12-16 | 原相科技股份有限公司 | Measurement device and operation method thereof |
| US11681025B2 (en) * | 2019-03-21 | 2023-06-20 | Infineon Technologies Ag | Simultaneous data transmission and depth image recording with time-of-flight cameras |
-
2021
- 2021-10-14 CN CN202111195272.8A patent/CN113641415B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109150152A (en) * | 2017-06-27 | 2019-01-04 | 原相科技股份有限公司 | Optical profile type control key and its operation method and imaging sensor |
| WO2020019760A1 (en) * | 2018-07-27 | 2020-01-30 | 北京市商汤科技开发有限公司 | Living body detection method, apparatus and system, and electronic device and storage medium |
| CN209064053U (en) * | 2018-10-31 | 2019-07-05 | 信利光电股份有限公司 | A kind of arrangements for automotive doors |
| WO2020196087A1 (en) * | 2019-03-27 | 2020-10-01 | パナソニックＩｐマネジメント株式会社 | Distance measurement device and image generation method |
| CN110456379A (en) * | 2019-07-12 | 2019-11-15 | 深圳奥比中光科技有限公司 | The depth measurement device and distance measurement method of fusion |
| CN210402486U (en) * | 2019-11-20 | 2020-04-24 | 辽宁丽景科技有限公司 | Induction self-powered face recognition intelligent door lock based on TOF technology |
| CN110930556A (en) * | 2019-12-04 | 2020-03-27 | 浙江凯迪仕实业有限公司 | 3D face identification intelligence lock |
| CN111332252A (en) * | 2020-02-19 | 2020-06-26 | 上海商汤临港智能科技有限公司 | Vehicle door unlocking method, device, system, electronic equipment and storage medium |
| CN213365014U (en) * | 2020-07-31 | 2021-06-04 | 深圳市光微科技有限公司 | Miniature TOF single-point range finding module and miniature TOF single-point range finding equipment |
Non-Patent Citations (3)
| Title |
|---|
| Registration method between ToF and color cameras for face recognition;Joongrock Kim ET AL;《2011 6th IEEE Conference on Industrial Electronics and Applications》;20110804;全文 * |
| 基于深度传感的人脸识别算法研究与实现;陈振浚等;《自动化应用》;20200825(第08期);全文 * |
| 适用于远程动态测距，兼低功耗与高像素的3D深度传感器（tof）芯片分析;陈飞霞等;《中国集成电路》;20201031(第257期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113641415A (en) | 2021-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10922395B2 (en) | Facial authentication systems and methods utilizing time of flight sensing | |
| EP3301476B1 (en) | Apparatus having a camera and a time of flight single photon avalanche diode based range detecting module for controlling the camera and corresponding method | |
| KR20220016184A (en) | Vehicle door unlocking method and device, system, vehicle, electronic device and storage medium | |
| WO2020173155A1 (en) | Vehicle door unlocking method and apparatus, system, vehicle, electronic device and storage medium | |
| US20170009509A1 (en) | Device and method for opening trunk of vehicle, and recording medium for recording program for executing method | |
| WO2022184147A1 (en) | Monitoring component control method and apparatus, and vehicle, device and computer storage medium | |
| CN109792510B (en) | Parcel theft prevention for wireless audio/video recording and communication devices | |
| US20120326959A1 (en) | Region of interest segmentation | |
| CN104102323A (en) | Navigation device and power saving method thereof | |
| CN107358175B (en) | Iris collection method and electronic device | |
| CN111759212A (en) | Intelligent toilet seat control method | |
| WO2020125773A1 (en) | Identity confirmation method and system | |
| CN111798488A (en) | System for performing eye detection and/or tracking | |
| CN109963046A (en) | Movement detection device and related mobile detection method | |
| US20150009140A1 (en) | Navigation device including thermal sensor | |
| CN110334665A (en) | A kind of face identification system and method for 3D identification | |
| KR20210064123A (en) | Method and apparatus for recognizing wearing state of safety belt, electronic device, and storage medium | |
| CN113641415B (en) | Unlocking method and device based on face recognition | |
| CN112101186A (en) | Device and method for identifying a vehicle driver and use thereof | |
| US10475309B1 (en) | Operation method of smart warning device for security | |
| TWI578186B (en) | Identification system and identification device for identification with solar panels | |
| Khalil et al. | Licanext: Incorporating sequential range residuals for additional advancement in joint perception and motion prediction | |
| US11870952B2 (en) | Presence detection in time of flight sensing systems | |
| CN106990859B (en) | Optical touch system, optical touch device and touch detection method thereof | |
| CN114495328A (en) | Door lock device and control method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |