CN110782568B - Access control system based on video photography - Google Patents
Access control system based on video photography Download PDFInfo
- Publication number
- CN110782568B CN110782568B CN201810769667.6A CN201810769667A CN110782568B CN 110782568 B CN110782568 B CN 110782568B CN 201810769667 A CN201810769667 A CN 201810769667A CN 110782568 B CN110782568 B CN 110782568B
- Authority
- CN
- China
- Prior art keywords
- module
- face
- matching
- entrance guard
- video
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
- H04N7/186—Video door telephones
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention discloses an access control system based on video photography, which comprises a camera module, a video acquisition module and a video processing module, wherein the camera module is used for acquiring video pictures; the invention effectively integrates face recognition and artificial compounding, can automatically open the entrance guard for the face in a video area after the face is recognized, and decides whether to open the entrance guard for the face according to a monitoring picture transmitted in real time, is more accurate in face recognition, can also realize that a user acquires the condition of an equipment end and updates own information, is anti-interference, has better pattern recognition effect, improves the speed of face matching, reduces the consumption of network bandwidth resources, can also improve the network service quality even if the number of monitoring devices is increased or reduced, and meets the requirement of real-time monitoring.
Description
Technical Field
The invention belongs to the technical field of photographic security. In particular to an access control system based on video photography.
Background
The entrance guard system is in the intelligent building field, and the entrance guard safety management system is a novel modern safety management system, integrates the microcomputer automatic identification technology and the modern safety management measures into a whole, and relates to a plurality of new technologies such as electronics, machinery, optics, computer technology, communication technology, biotechnology and the like. The method is an effective measure for realizing safety precaution management at the entrance and exit of important departments. The system is suitable for various essential departments, such as banks, hotels, parking lot management, machine rooms, ordnance depots, key rooms, office rooms, intelligent districts, factories and the like. However, the existing access control system has the defects of single function, passive monitoring and the like, the traditional access control system cannot send out alarm information in time when an emergency happens, and the face recognition access control system on the market only achieves the function of opening the access control after recognizing a specific person, and cannot check and manually verify in real time.
Disclosure of Invention
The invention aims to overcome the defects and provides an access control system based on video photography, which comprises a camera module, a camera module and a control module, wherein the camera module is used for acquiring video pictures;
the control center is used for prestoring a face with access control authority, comparing the captured face image with the face prestored in the database, and sending an unlocking control signal to the access control lock switch module, an error prompt signal to the access control prompt module or a warning signal to the warning module;
the door control lock switch module is used for receiving signals and controlling the door control to be opened or locked;
the voice module is used for judging whether the operator in the control center has the access control authority or not through conversation with the person entering the door;
the entrance guard prompting module is used for prompting an error signal when the face matching is unsuccessful and prompting an operator to perform voice and video manual identification;
and the warning module is used for finding a person who does not have access control authority, and the control center sends a warning signal to the warning module.
The invention has the following advantages and effects:
the face recognition and the artificial compounding are effectively integrated, the entrance guard can be automatically opened for the face after the face in the video region is recognized, whether the entrance guard is opened for the face is determined according to a monitoring picture transmitted in real time, the face recognition is more accurate, the situation of a user obtaining equipment end can be further achieved, the information of the user can be updated, the face recognition is anti-interference, the pattern recognition effect is better, the face matching speed is improved, the consumption of network bandwidth resources is reduced, even if the number of monitoring devices is increased or reduced, the network service quality can also be improved, and the requirement of real-time monitoring is met.
Drawings
FIG. 1 is a schematic view of a communication structure of an access control system
Detailed Description
The invention is further illustrated by the following specific examples:
an access control system based on video photography comprises a camera module, a video acquisition module and a video processing module, wherein the camera module is used for acquiring video pictures;
the control center is used for prestoring a face with access control authority, comparing the captured face image with the face prestored in the database, and sending an unlocking control signal to the access control lock switch module, an error prompt signal to the access control prompt module or a warning signal to the warning module;
the door control lock switch module is used for receiving signals and controlling the door control to be opened or locked;
the voice module is used for judging whether the operator in the control center has the access control authority or not through conversation with the person entering the door;
the entrance guard prompting module is used for prompting an error signal when the face matching is unsuccessful, and prompting an operator to perform voice and video manual identification;
and the warning module is used for finding a person who does not have access control authority, and the control center sends a warning signal to the warning module.
Camera module, voice module and entrance guard lock switch module install at entrance guard's operation end, control center, entrance guard's suggestion module and warning module are located the control operation end, camera module, voice module, entrance guard's lock switch module, entrance guard's suggestion module and warning module are equallyd divide and are do not improve wireless network connection with control center, and the control operation end has the gateway through wireless network connection, and the gateway passes through wireless network connection route node, and route node connection entrance guard's operation end.
The inquiry module is used for inputting a user number and an inquiry password by a user; opening inquiry authority to the user according to the user number; the user inquires video playback and sound recording playback in the authority, if the information needs to be reset, a command for resetting the password and the authority is input to the resetting module, the resetting module is initialized, the password and the authority of the user are reset, and then the password and the authority are sent to the control center for updating.
The control center also comprises a confirmation module which is used for separating each frame of the target face monitoring video input by the camera module to obtain the reliability and the frame information of the target face, when the reliability of the target face is greater than a set threshold value, the target face in the database is confirmed, the redundant frame is removed, and the target frame is reserved;
the fusion module is used for calling a human face candidate frame prestored in the database, extracting shallow features and deep features of a region corresponding to the candidate frame, and combining the shallow features and the deep features to serve as an integral appearance feature model;
the region selection module is used for calculating the credibility scores of all parts of the target face through the filtering module, and the region with the highest score is the matching position region of the target face;
the integral appearance comparison module is used for updating the position of the target face in the current frame and comparing the position with the integral appearance characteristic model to obtain an integral appearance credibility score of the target face;
and the automatic matching module is used for judging whether the currently matched target face is shielded or not, continuously updating the matching state of each face candidate frame prestored in the database, thereby realizing the automatic matching of the target face and storing a newly matched face image into the database.
The control center also comprises a continuous matching module which is used for continuing to match the next target face and judging whether the matching fails when the target face which is matched to be successful before is matched again;
the pooling module is used for calling the last frame of image with failed matching as input when the matching of the matched target face fails again, obtaining a shallow feature map, extracting the significance of the image, eliminating redundant information in the background, outputting a deep feature map, fusing the shallow feature map and the deep feature map, performing global pooling on the fused feature map to obtain a global feature vector, and performing horizontal pooling to obtain a local feature vector;
the distance module is used for calculating the distance of the global characteristic vector between the face image with failed matching and the stored face image and the distance of the local characteristic vector between the face image with failed matching and the stored face image;
the sequencing module is used for calculating the final distance between the face image with failed matching and the stored face image, wherein the final distance is equal to the global feature vector distance plus the local feature vector distance, and the initial similarity sequencing of the stored face image and the face image with failed matching is obtained according to the final distance;
and the pre-stored updating module is used for selecting the stored image with the highest similarity as a first candidate pre-stored image and updating the image.
A door control method based on video shooting comprises the following steps:
001. prestoring the face with access control authority into a database of a control center;
002. collecting video pictures through a camera module;
003. after the camera module captures the face, comparing the captured face image with the face prestored in the database;
004. if the captured face image is successfully matched with the face prestored in the database, the control center sends an unlocking control signal to the access lock switch module to open the access;
005. if the captured face image is unsuccessfully matched with the face prestored in the database, the control center sends an error prompt signal to the entrance guard prompt module;
006. an operator of the control center judges whether the person has access control authority or not through the voice module and the camera module; if the person is a person with access control authority, the control center sends an unlocking control signal to the access control lock switch module to open the access control; and if the person does not have the access control authority, the control center sends a warning signal to the warning module.
After the step 006, the following steps are also included:
061. the user inputs a user number and a query password to the query module;
062. the query module opens a query authority to the user according to the user number;
063. the user inquires about the video playback and the audio playback in the authority, and if the information needs to be reset, the next step is carried out; if the information does not need to be reset, finishing the query;
064. the user inputs a command of resetting the password and the authority to the resetting module through the query module, the resetting module is initialized, the password and the authority of the user are reset, and then the password and the authority are sent to the control center for updating.
The step 003 is specifically:
031. separating each frame of a target face monitoring video input by a camera module to obtain the reliability and frame information of a target face, confirming the target face in a database when the reliability of the target face is greater than a set threshold value, removing a redundant frame, and keeping a target frame;
032. calling a face candidate frame prestored in a database, extracting shallow features and deep features of a region corresponding to the candidate frame, and combining the shallow features and the deep features to serve as an integral appearance feature model;
033. calculating the credibility scores of all parts of the target face through a filtering module, wherein the region with the highest score is the matching position region of the target face;
034. updating the position of the target face in the current frame, and comparing the position with the integral appearance characteristic model to obtain an integral appearance credibility score of the target face;
035. and judging whether the currently matched target face is shielded or not, continuously updating the matching state of each face candidate frame prestored in the database, thereby realizing the automatic matching of the target face, and storing a newly matched face image into the database.
After step 006, the following steps are included:
036. continuing to match the next target face, judging whether the previous matched target face fails to be matched again, if so, turning to the next step, and if not, continuing to match the next target face;
037. calling an image with failed matching of the last frame as input to obtain a shallow feature map, extracting the significance of the image to eliminate redundant information in a background, outputting a deep feature map, fusing the shallow feature map and the deep feature map, performing global pooling on the fused feature map to obtain a global feature vector, and performing horizontal pooling to obtain a local feature vector;
038. calculating the distance of the global characteristic vector between the face image with failed matching and the stored face image and the distance of the local characteristic vector between the face image with failed matching and the stored face image;
039. calculating the final distance between the face image with failed matching and the stored face image, wherein the final distance is equal to the global feature vector distance plus the local feature vector distance, and the initial similarity sequence of the stored face image and the face image with failed matching is obtained according to the final distance;
040. and selecting the stored image with the highest similarity as a first candidate pre-stored image and updating.
When the credibility scores of the parts of the target face are calculated by the filtering module in the step 033, the features of the face image are extracted first, and the method specifically comprises the following steps:
taking a pixel point on the face image as a center, and taking a neighborhood around the pixel point as a block with the size of 3 x 3;
calculating the average value of all gray values in the block, comparing each gray value in the block with the average value, if the gray value is smaller than the average value, calculating 0, otherwise calculating 1, and then forming a local binary pattern of the block;
weighting the local binary pattern of the block by taking a Gaussian function with the size of 3 x 3 as a weight;
and by analogy, each pixel point on the face image is taken as a central pixel, and the steps are repeated until the characteristics of the whole face image are extracted.
In the step 004, the control center sends unlocking control signals to the access lock switch module, and the method comprises the following steps:
061. judging whether a wireless link between the control center and the access lock switch module is stable or not, and if so, turning to the next step;
062. detecting whether a route reaching the lock forbidding switch module exists in a routing table of the control center, if so, establishing the route successfully, and if not, turning to the next step;
063. the control center sends a routing request message;
064. the module receiving the routing request message judges whether to lock the switch module according to the routing request message information, and if so, the next step is carried out;
065. judging whether a route reaching the lock forbidding switch module exists in the routing table or not, and performing step 067;
066. if the route does not reach the locking switch module or the locking switch module, continuing to forward the route request message, repeating the step 064, and if the hop count information exceeds the specified hop count, failing to establish;
067. sending the routing request to the lock forbidding switch module according to the routing path reaching the lock forbidding switch module in the routing table;
068. and the lock forbidding switch module receives the routing request and records the routing information according to the routing request, and the routing is successfully established.
Claims (1)
1. An access control system based on video photography comprises a camera module, a video acquisition module and a video processing module, wherein the camera module is used for acquiring video pictures; the control center is used for prestoring a face with access control authority, comparing the captured face image with the face prestored in the database, and sending an unlocking control signal to the access control lock switch module, an error prompt signal to the access control prompt module or a warning signal to the warning module;
the entrance guard lock switch module is used for receiving signals and controlling entrance guard to open or lock;
the voice module is used for judging whether the operator in the control center has the access control authority or not through conversation with the person entering the door;
the entrance guard prompting module is used for prompting an error signal when the face matching is unsuccessful and prompting an operator to perform voice and video manual identification;
the warning module is used for sending a warning signal to the warning module by the control center when finding a person who does not have access control authority; the system comprises a camera module, a voice module and an entrance guard lock switch module, wherein the camera module, the voice module and the entrance guard lock switch module are installed at an entrance guard operation end, a control center, an entrance guard prompting module and a warning module are located at a monitoring operation end, the camera module, the voice module, the entrance guard lock switch module, the entrance guard prompting module and the warning module are respectively connected with the control center in a wireless network mode, the monitoring operation end is connected with a gateway through a wireless network, the gateway is connected with a routing node through the wireless network, and the routing node is connected with the entrance guard operation end; the inquiry module is used for inputting a user number and an inquiry password by a user; opening inquiry authority to the user according to the user number; a user inquires video playback and audio playback in the authority, if information needs to be reset, a command for resetting a password and the authority is input to a resetting module, the resetting module is initialized, the password and the authority of the user are reset, and then the password and the authority of the user are sent to a control center for updating; the control center also comprises a confirmation module which is used for separating each frame of the target face monitoring video input by the camera module to obtain the reliability and the frame information of the target face and comparing the reliability and the frame information with the face information in the database, when the reliability of the target face is greater than a set threshold value, the target face in the database is confirmed, a redundant frame is removed, and the target frame is reserved;
the fusion module is used for calling a human face candidate frame prestored in the database, extracting shallow features and deep features of a region corresponding to the candidate frame, and combining the shallow features and the deep features to serve as an integral appearance feature model;
the region selection module is used for calculating the credibility scores of all parts of the target face through the filtering module, and the region with the highest score is the matching position region of the target face;
the integral appearance comparison module is used for updating the position of the target face in the current frame and comparing the position with the integral appearance characteristic model to obtain an integral appearance credibility score of the target face;
the automatic matching module is used for judging whether the currently matched target face is shielded or not, continuously updating the matching state of each face candidate frame prestored in the database, thereby realizing the automatic matching of the target face and storing a newly matched face image into the database; the control center also comprises a continuous matching module which is used for continuing to match the next target face and judging whether the matching fails when the target face which is matched to be successful before is matched again;
the pooling module is used for calling the image with the last frame failed in matching as input when the target face fails to be matched again, obtaining a shallow feature map, extracting the significance of the image, eliminating redundant information in the background, outputting a deep feature map, fusing the shallow feature map and the deep feature map, performing global pooling on the fused feature map to obtain a global feature vector, and performing horizontal pooling to obtain a local feature vector;
the distance module is used for calculating the distance of the global characteristic vector between the face image with failed matching and the stored face image and the distance of the local characteristic vector between the face image with failed matching and the stored face image;
the sequencing module is used for calculating the final distance between the face image with failed matching and the stored face image, wherein the final distance is equal to the global feature vector distance plus the local feature vector distance, and the initial similarity sequencing of the stored face image and the face image with failed matching is obtained according to the final distance;
and the pre-stored updating module is used for selecting the stored image with the highest similarity as a first candidate pre-stored image and updating the image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810769667.6A CN110782568B (en) | 2018-07-13 | 2018-07-13 | Access control system based on video photography |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810769667.6A CN110782568B (en) | 2018-07-13 | 2018-07-13 | Access control system based on video photography |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110782568A CN110782568A (en) | 2020-02-11 |
| CN110782568B true CN110782568B (en) | 2022-05-31 |
Family
ID=69377077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810769667.6A Active CN110782568B (en) | 2018-07-13 | 2018-07-13 | Access control system based on video photography |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110782568B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113129492A (en) * | 2021-04-16 | 2021-07-16 | 腾讯科技（深圳）有限公司 | Intelligent access control method and system |
| CN113644747A (en) * | 2021-10-18 | 2021-11-12 | 深圳市鑫道为科技有限公司 | A disguised switchgear monitored control system for intelligent monitoring warning |
| CN114253612A (en) * | 2021-11-25 | 2022-03-29 | 上海齐感电子信息科技有限公司 | Control method and control system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6853739B2 (en) * | 2002-05-15 | 2005-02-08 | Bio Com, Llc | Identity verification system |
| EP1472870A4 (en) * | 2002-02-06 | 2006-11-29 | Nice Systems Ltd | Method and apparatus for video frame sequence-based object tracking |
| CN103093216B (en) * | 2013-02-04 | 2014-08-20 | 北京航空航天大学 | Gender classification method and system thereof based on facial images |
| WO2014203026A1 (en) * | 2013-06-17 | 2014-12-24 | Aselsan Elektronik Sanayi Ve Ticaret Anonim Sirketi | A method for object tracking |
| CN104966344A (en) * | 2015-07-17 | 2015-10-07 | 江西洪都航空工业集团有限责任公司 | Security entrance guard system based on video |
| CN106295678A (en) * | 2016-07-27 | 2017-01-04 | 北京旷视科技有限公司 | Neural metwork training and construction method and device and object detection method and device |
| CN106803924A (en) * | 2015-11-25 | 2017-06-06 | 哈尔滨格泰科技有限公司 | A kind of network video monitor and control system |
| CN106951912A (en) * | 2017-02-15 | 2017-07-14 | 海尔优家智能科技（北京）有限公司 | A kind of method for building up of fruits and vegetables cosmetic variation identification model and recognition methods |
| CN107564034A (en) * | 2017-07-27 | 2018-01-09 | 华南理工大学 | The pedestrian detection and tracking of multiple target in a kind of monitor video |
| CN107909026A (en) * | 2016-11-30 | 2018-04-13 | 深圳奥瞳科技有限责任公司 | Age and gender assessment based on the small-scale convolutional neural networks of embedded system |
| CN108073929A (en) * | 2016-11-15 | 2018-05-25 | 北京三星通信技术研究有限公司 | Object detecting method and equipment based on dynamic visual sensor |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295714B (en) * | 2016-08-22 | 2020-01-21 | 中国科学院电子学研究所 | Multi-source remote sensing image fusion method based on deep learning |
| CN107742099A (en) * | 2017-09-30 | 2018-02-27 | 四川云图睿视科技有限公司 | A kind of crowd density estimation based on full convolutional network, the method for demographics |
-
2018
- 2018-07-13 CN CN201810769667.6A patent/CN110782568B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1472870A4 (en) * | 2002-02-06 | 2006-11-29 | Nice Systems Ltd | Method and apparatus for video frame sequence-based object tracking |
| US6853739B2 (en) * | 2002-05-15 | 2005-02-08 | Bio Com, Llc | Identity verification system |
| CN103093216B (en) * | 2013-02-04 | 2014-08-20 | 北京航空航天大学 | Gender classification method and system thereof based on facial images |
| WO2014203026A1 (en) * | 2013-06-17 | 2014-12-24 | Aselsan Elektronik Sanayi Ve Ticaret Anonim Sirketi | A method for object tracking |
| CN104966344A (en) * | 2015-07-17 | 2015-10-07 | 江西洪都航空工业集团有限责任公司 | Security entrance guard system based on video |
| CN106803924A (en) * | 2015-11-25 | 2017-06-06 | 哈尔滨格泰科技有限公司 | A kind of network video monitor and control system |
| CN106295678A (en) * | 2016-07-27 | 2017-01-04 | 北京旷视科技有限公司 | Neural metwork training and construction method and device and object detection method and device |
| CN108073929A (en) * | 2016-11-15 | 2018-05-25 | 北京三星通信技术研究有限公司 | Object detecting method and equipment based on dynamic visual sensor |
| CN107909026A (en) * | 2016-11-30 | 2018-04-13 | 深圳奥瞳科技有限责任公司 | Age and gender assessment based on the small-scale convolutional neural networks of embedded system |
| CN106951912A (en) * | 2017-02-15 | 2017-07-14 | 海尔优家智能科技（北京）有限公司 | A kind of method for building up of fruits and vegetables cosmetic variation identification model and recognition methods |
| CN107564034A (en) * | 2017-07-27 | 2018-01-09 | 华南理工大学 | The pedestrian detection and tracking of multiple target in a kind of monitor video |
Non-Patent Citations (4)
| Title |
|---|
| high -speed tracking-by-detection without using image information;Bochinski E;《IEEE International Conference on Advanced Video and Signal Based SueVeillance》;20171231;全文 * |
| 基于深度学习的行人再识别技术研究;焦旭辉;《中国优秀硕士学位论文全文数据库 信息科技辑》;20171231;全文 * |
| 基于视频的行人检测与跟踪算法研究;罗招材;《中国优秀硕士学位论文全文数据库 信息科技辑》;20171231;全文 * |
| 多源影像下的目标运动分析及应用;房建武;《中国博士学位论文全文数据库 信息科技辑》;20160531;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110782568A (en) | 2020-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110782554B (en) | Access control method based on video photography | |
| CN110782568B (en) | Access control system based on video photography | |
| JP3999561B2 (en) | Surveillance system and surveillance camera | |
| CN206515931U (en) | A kind of face identification system | |
| JP6607266B2 (en) | Face recognition device | |
| JP5123037B2 (en) | Face authentication apparatus and face authentication method | |
| CN107195036A (en) | A kind of method and its system of the improper unlocking of identification intelligent door lock | |
| CN104966344A (en) | Security entrance guard system based on video | |
| CN110807888A (en) | Intelligent security method, system and storage medium for park | |
| US20200126337A1 (en) | Access control system for radio and facial recognition | |
| CN104318654A (en) | Building intercom system and method | |
| CN109255863A (en) | The intelligent door lock and its operation method verified based on user's face and two dimensional code | |
| KR20140122322A (en) | Security System for Monitoring Facilities | |
| CN111800617A (en) | Intelligent security system based on Internet of things | |
| CN110096974A (en) | A kind of sight spot tourist based on recognition of face enters the method and system of garden veritification | |
| CN109118617A (en) | A kind of access control system and its recognition methods applied to substation | |
| KR102467814B1 (en) | Integrated security system for apartment complexes based on artificial intelligence image analysis | |
| KR20160072386A (en) | Home network system using face recognition based features and method using the same | |
| CN110599657A (en) | Access control monitoring system and method based on image recognition technology | |
| CN111429638B (en) | Access control method based on voice recognition and face recognition | |
| CN108320359A (en) | A kind of city Internet of Things wisdom gate inhibition and safety-protection system | |
| CN110781704A (en) | Verification method for video monitoring | |
| WO2020213384A1 (en) | Courier authentication method, courier authentication system, server device, and control device | |
| CN109147108A (en) | A kind of method and apparatus of entrance guard management | |
| KR102108391B1 (en) | Moving Object Linkage Tracking System and Method Using Multiple Cameras |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220512 Address after: 518000 1701, building A1, building A1A2, Guangming Science Park, China Merchants Group, sightseeing Road, Fenghuang community, Fenghuang street, Guangming District, Shenzhen, Guangdong Applicant after: Shenzhen Yuanrui Urban Intelligent Development Co.,Ltd. Address before: 315000 3-1-330, No. 2, Yangfan Plaza, high tech Zone, Ningbo, Zhejiang Applicant before: Ningbo Qilan Culture Development Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |