CN110619277A - Multi-community intelligent deployment and control method and system - Google Patents
Multi-community intelligent deployment and control method and system Download PDFInfo
- Publication number
- CN110619277A CN110619277A CN201910754919.2A CN201910754919A CN110619277A CN 110619277 A CN110619277 A CN 110619277A CN 201910754919 A CN201910754919 A CN 201910754919A CN 110619277 A CN110619277 A CN 110619277A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- license plate
- community
- face
- data
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of community security, and particularly discloses a multi-community intelligent control method and a multi-community intelligent control system. The control of people mainly comprises face recognition, pedestrian recognition and abnormal behavior analysis; the vehicle control mainly comprises license plate recognition, vehicle characteristic recognition and key area violation. The method comprises the steps of obtaining pedestrians in images through a community monitoring camera, analyzing behaviors of the pedestrians in the images, determining specific behaviors of the pedestrians, and judging whether the pedestrians belong to the category of abnormal behaviors or not. The method comprises the steps of obtaining vehicles in an image through a community monitoring camera, identifying vehicle characteristics in the image, opening a barrier gate and the like if the license plate is included, and tracking the track of the vehicles in a community by combining with vehicle characteristic identification if the license plate is not included.
Description
Technical Field
The invention relates to the technical field of community security, in particular to a multi-community intelligent control method and system.
Background
The concept of smart community is rapidly developed, and community control is the most basic and important function of smart community. The rapid development of the artificial intelligence technology provides a new idea for solving a plurality of problems of community automation control. The targets needing monitoring in the community mainly comprise people and vehicles, face recognition, pedestrian recognition, license plate recognition and vehicle feature recognition all belong to deep learning technologies in nature, and the technology is combined with a control system, so that the community monitoring system has the characteristics of visual effect, automatic monitoring and the like.
The face recognition and the license plate recognition can provide basic services for community security, such as face recognition access control and license plate recognition barrier. And the pedestrian recognition, the vehicle characteristic recognition, the face recognition and the license plate recognition are combined to realize the tracking of community personnel and vehicles, so that the safety of the community is guaranteed. However, the existing community deployment and control system is mainly a single community system, and has small data volume and blocking. The timely control of suspicious people and vehicles, blacklist people and vehicles, escaping suspects and escaping vehicles cannot be completed in time according to the requirements of government departments. The problem that the data size is too large, the data analysis is slow, the communication pressure is increased and the like can occur when multiple communities are controlled. In order to complete the deployment and control of personnel and vehicles in time in mass video data, the invention provides a multi-community intelligent deployment and control method and a multi-community intelligent deployment and control system.
Disclosure of Invention
The invention aims to provide a multi-community intelligent control method and a multi-community intelligent control system, so as to solve the problems in the background technology.
In order to achieve the above object, an embodiment of the present invention provides a multi-community intelligent deployment and control method, including the following specific steps:
s10, acquiring pictures of people or vehicles;
s20, jumping to S30 if the picture contains a person or a face, and jumping to S40 if the picture contains a vehicle or a license plate;
s30, judging the specific behavior of the person and extracting the face features, and then, carrying out S50;
and S40, recognizing the vehicle characteristics and extracting the license plate characteristics, and then step S60 is carried out.
S50, calculating the similarity of the human face features to the features of the human face in the human face library, if the similarity exceeds a set threshold value, jumping to the step S70, otherwise, jumping to the step S80;
s60, obtaining specific license plate data according to the extracted license plate features, searching a control database, if the data are found to be data in the database, further operating, and otherwise, skipping to the step S90;
s70, obtaining the similarity and the identity information of the human face;
s80, adding the human face to a strange human face library, and carrying out unique marking for tracking;
and S90, tracking the vehicle by combining the extracted vehicle type and color information of the vehicle.
As a further scheme of the invention: in step S10, the video frame of the monitoring camera is pulled by the RTSP.
As a further scheme of the invention: in step S20, a specific target to be recognized is detected using the pedestrian, human face, vehicle, and license plate detection models.
As a further scheme of the invention: in step S30, specific behaviors of the person are recognized by a behavior recognition algorithm, the specific behaviors including 5 kinds of abnormal behaviors of running, jumping, bending, falling, and holding a tool, and facial features are extracted by a face recognition algorithm.
As a further scheme of the invention: in step S40, the license plate features include characters, letters, and numbers in the license plate, and the license plate database stores the specific numerical values of the license plate and the owner information.
As a further scheme of the invention: in step S50, the face library stores face information with unique ID, including identity information, age, sex, and face characteristics.
As a further scheme of the invention: in step S90, the vehicle feature detection model can detect 8 types and 9 colors of the vehicle, combine the recognized vehicle feature information with the license plate information, and determine the vehicle uniquely according to the vehicle color and the vehicle type judgment when the license plate is blocked or has no license plate information, thereby implementing vehicle tracking.
As a further scheme of the invention: the 8 types of vehicles are cars, coaches, urban off-road vehicles, trucks, fire engines, cranes, vans and trucks respectively.
As a further scheme of the invention: the 9 colors are black, white, red, yellow, blue, brown, silver, green, gray, respectively.
The embodiment of the invention also provides a multi-community intelligent control system, which comprises:
the community monitoring camera is used for capturing pictures of people and vehicles, pulling video frames through the RTSP by the monitoring camera and identifying the people and the vehicles in the video frames;
the community control server comprises models for specifically performing face recognition, pedestrian detection, license plate recognition and vehicle characteristic detection, images acquired by the camera can enter 4 models for recognition and detection at the same time, the detection result is fed back to the community management platform in real time, and data meeting the requirements of street office are reported to the cloud in real time;
the community management platform is responsible for managing server data and maintaining basic data; the community management platform of any cell can maintain and upload a face library outside the white list of the cell, and the cloud can update the face library to all the cells after obtaining the uploaded data;
the cloud of the street office deploys a big data related platform comprising Spark, Storm and HBase clusters; the cloud end utilizes HBase to store big data, and utilizes Spark to search target tracks in the mass historical data through the target picture; the cloud end processes stranger or vehicle data to serve as a data set, a Storm parallel training updating model is utilized, and the cloud end is utilized for deployment and control display.
Compared with the prior art, the multi-community intelligent control method and system provided by the embodiment of the invention have the advantages that the control targets mainly comprise people and vehicles;
first, the embodiment of the invention can establish a plurality of face libraries or license plate libraries, and divide the face libraries into a white list face library of the community, a black list face library of the community, a strange face library and a face library which needs to be monitored in street handling. And dividing the license plates into a white list license plate library of the community, a black list license plate library of the community, and a community and strange license plate library. And recognizing the human face, the pedestrians, the license plates and the vehicles in real time, and monitoring the blacklist personnel vehicles and the monitoring personnel in real time. And automatic control alarm is realized.
Secondly, the embodiment of the invention stores the mass data by utilizing HBase, quickly queries the mass historical data by utilizing Spark, realizes inputting target personnel or vehicles, and automatically acquires the historical track of the target from the mass data.
Thirdly, stranger or vehicle data are used as a data set regularly to optimize the training of the recognition model, and the advantage of Storm flow processing is utilized to realize parallel model training, improve the updating efficiency of the model and improve the recognition accuracy of the recognition model.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 is a flowchart of a multi-community intelligent deployment and control method according to an embodiment of the present invention.
Fig. 2 is a structural diagram of a multi-community intelligent deployment and control system according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It should be noted that all the directional indicators (such as upper, lower, left, right, front, rear, inner and outer …) in the embodiment of the present invention are only used to explain the relative position relationship between the components, the motion situation, etc. in a specific posture (as shown in the figure), and if the specific posture is changed, the directional indicator is changed accordingly.
In addition, the descriptions related to "one", "two", etc. in the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "a", "an", or "two" may explicitly or implicitly include at least one of the feature.
As shown in fig. 1, in an embodiment provided by the present invention, a multi-community intelligent deployment and control method includes the following specific steps:
s10, acquiring pictures of people or vehicles; in the specific implementation, the video frame of the monitoring camera is pulled through the RTSP.
S20, jumping to S30 if the picture contains a person or a face, and jumping to S40 if the picture contains a vehicle or a license plate; specifically, a specific target to be recognized is detected by using pedestrian, human face, vehicle and license plate detection models.
S30, judging the specific behavior of the person and extracting the face features, and then, carrying out S50; specifically, the specific behaviors of the person are identified through a behavior identification algorithm, the specific behaviors mainly comprise 5 abnormal behaviors of running, jumping, bending, falling and holding a mechanical device, and meanwhile, the face features are extracted through a face identification algorithm.
S40, recognizing vehicle characteristics and extracting license plate characteristics, and then, carrying out S60;
in the specific implementation of step S40, the characters, letters, and numbers included in the license plate are accurately extracted. The license plate database stores the specific numerical value of the license plate and the information of the vehicle owner and the like.
S50, calculating the similarity of the human face features to the features of the human face in the human face library, if the similarity exceeds a set threshold value, jumping to the step S70, otherwise, jumping to the step S80;
in a specific implementation of step S50, the face repository stores face information with unique ID, including identity information, age, gender, face characteristics, and the like. According to the recognition effect of the algorithm, the recognition accuracy is guaranteed, and meanwhile the features of the target to be recognized and the features of the user in the face library can reach the threshold value, and the threshold value is set. And comparing and calculating the face features extracted in real time with the features in the face library to obtain the similarity.
S60, obtaining specific license plate data according to the extracted license plate features, searching a control database, if the data are found to be data in the database, further operating, and otherwise, skipping to the step S90;
in the specific implementation of step S60, the obtained license plate data is searched in the license plate database, and if the license plate is in the database, a basic service is provided.
S70, obtaining the similarity and the identity information of the human face; in the specific implementation manner of step S70, when the value is higher than the set threshold value, corresponding operations are performed according to the belonging face library.
S80, adding the human face to a strange human face library, and carrying out unique marking for tracking; in a specific implementation of step S80, when the value is lower than the set threshold, a high-quality face picture is screened and added to the strange face library, so as to facilitate later analysis, such as assisting in investigating the historical track of the criminal suspect.
S90, tracking the vehicle by combining the extracted vehicle type and color information of the vehicle;
in step S90 provided by the embodiment of the present invention, the vehicle characteristic detection model can detect 8 types and 9 colors of the vehicle. Wherein, 8 kinds of motorcycle types are respectively cars, passenger cars, urban off-road vehicles, trucks, fire trucks, cranes, vans and trucks. The 9 colors are black, white, red, yellow, blue, brown, silver, green, gray, respectively. And combining the recognized vehicle characteristic information with the license plate information, wherein the license plate is used as the ID of the vehicle, and when the license plate is shielded or has no license plate information, judging according to the color and the type of the vehicle, uniquely determining the vehicle, and realizing vehicle tracking.
As shown in fig. 2, an embodiment of the present invention further provides a multi-community intelligent deployment and control system, including:
the community monitoring camera is used for capturing pictures of people and vehicles, pulling video frames through the RTSP by the monitoring camera and identifying the people and the vehicles in the video frames;
the community control server comprises models for specifically performing face recognition, pedestrian detection, license plate recognition and vehicle characteristic detection, images acquired by the camera can enter 4 models for recognition and detection at the same time, the detection result is fed back to the community management platform in real time, and data meeting the requirements of street office are reported to the cloud in real time;
the community management platform is responsible for managing server data and maintaining basic data; the community management platform of any cell can maintain and upload the face library outside the white list of the cell, and the cloud can update the face library to all the cells after obtaining the uploaded data.
The cloud of the street office deploys a big data related platform comprising Spark, Storm and HBase clusters; the cloud end utilizes HBase to store big data, and utilizes Spark to search target tracks in the mass historical data through the target picture; the cloud can process stranger or vehicle data to serve as a data set, the model is updated through Storm parallel training, and the cloud can be displayed in a control mode.
The invention provides a multi-community intelligent deploying and controlling method and a system. Specifically, the control of people mainly comprises face recognition, pedestrian recognition and abnormal behavior analysis; the vehicle control mainly comprises license plate recognition, vehicle characteristic recognition and key area violation. Acquiring pedestrians in the image through a community monitoring camera, analyzing behaviors of the pedestrians in the image, determining specific behaviors of the pedestrians, and judging whether the pedestrians belong to the category of abnormal behaviors; and acquiring the vehicle in the image through the community monitoring camera, and identifying the vehicle characteristics in the image to obtain the specific vehicle type and color of the vehicle. Acquiring a face image through a community monitoring camera, extracting face features, calculating the similarity between the face features and the features of the faces in a face library, if the similarity exceeds a set threshold value, acquiring the similarity and identity information of the faces, and if the similarity between the faces to be recognized and all the faces in the face library cannot exceed the threshold value, adding the faces into a strange face library; the method comprises the steps of obtaining a license plate image through a community monitoring camera, extracting characters, letters and numbers in the license plate, calculating to obtain specific license plate data, searching for the license plate in a database, if the license plate is contained, opening a barrier gate and the like, and if the license plate is not contained, tracking the track of a vehicle in a community by combining with vehicle feature recognition.
In summary, the present invention can establish a plurality of face libraries or license plate libraries, and divide the face libraries into the face library of the white list of the community, the face library of the black list of the community, the face library of the strange person and the face library of the street needing to be monitored. And dividing the license plates into a white list license plate library of the community, a black list license plate library of the community, and a community and strange license plate library. And recognizing the human face, the pedestrians, the license plates and the vehicles in real time, and monitoring the blacklist personnel vehicles and the monitoring personnel in real time. Automatic control and alarm are realized;
the HBase is used for storing the mass data, the Spark is used for quickly inquiring the mass historical data, the input of target personnel or vehicles is realized, and the historical track of the target is automatically obtained from the mass data;
stranger or vehicle data are regularly used as data sets to optimize the training of the recognition model, the advantage of Storm flow processing is utilized, parallel model training is achieved, the model updating efficiency is improved, and the recognition accuracy of the recognition model is improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A multi-community intelligent deployment and control method is characterized by comprising the following specific steps:
s10, acquiring pictures of people or vehicles;
s20, jumping to S30 if the picture contains a person or a face, and jumping to S40 if the picture contains a vehicle or a license plate;
s30, judging the specific behavior of the person and extracting the face features, and then, carrying out S50;
s40, recognizing vehicle characteristics and extracting license plate characteristics, and then, carrying out S60;
s50, calculating the similarity of the human face features to the features of the human face in the human face library, if the similarity exceeds a set threshold value, jumping to the step S70, otherwise, jumping to the step S80;
s60, obtaining specific license plate data according to the extracted license plate features, searching a control database, if the data are found to be data in the database, further operating, and otherwise, skipping to the step S90;
s70, obtaining the similarity and the identity information of the human face;
s80, adding the human face to a strange human face library, and carrying out unique marking for tracking;
and S90, tracking the vehicle by combining the extracted vehicle type and color information of the vehicle.
2. The multi-community intelligent deployment method and system as claimed in claim 1, wherein in step S10, the video frames of the monitoring cameras are pulled through RTSP.
3. The multi-community intelligent deployment and control method and system as claimed in claim 2, wherein in step S20, the specific target to be recognized is detected by using pedestrian, human face, vehicle and license plate detection models.
4. The multi-community intelligent control method and system according to claim 3, wherein in step S30, the specific behaviors of the person are identified by a behavior recognition algorithm, the specific behaviors include 5 kinds of abnormal behaviors such as running, jumping, bending, falling and holding a tool, and the face features are extracted by a face recognition algorithm.
5. The multi-community intelligent control method and system according to claim 4, wherein in step S40, the license plate features include Chinese characters, letters and numbers in the license plate, and the license plate database stores the specific number values of the license plate and the owner information.
6. The multi-community intelligent control method and system as claimed in claim 5, wherein in step S50, the face database stores face information with unique ID, the face information includes identity information, age, gender, and face characteristics.
7. The multi-community intelligent control method and system according to claim 6, wherein in step S90, the vehicle feature detection model can detect 8 types and 9 colors of vehicles, combine the identified vehicle feature information with license plate information, the license plate is used as the ID of the vehicle, and when the license plate is blocked or has no license plate information, the vehicle is uniquely determined according to the vehicle color and type judgment, so as to realize vehicle tracking.
8. The multi-community intelligent deployment and control method and system of claim 7, wherein 8 vehicle types are car, passenger car, off-road city vehicle, truck, fire truck, crane, minibus and truck.
9. The method and system according to claim 8, wherein the 9 colors are black, white, red, yellow, blue, brown, silver, green, and gray.
10. The utility model provides a many communities' wisdom cloth accuse system which characterized in that includes:
the community monitoring camera is used for capturing pictures of people and vehicles, pulling video frames through the RTSP by the monitoring camera and identifying the people and the vehicles in the video frames;
the community control server comprises models for specifically performing face recognition, pedestrian detection, license plate recognition and vehicle characteristic detection, images acquired by the camera can enter 4 models for recognition and detection at the same time, the detection result is fed back to the community management platform in real time, and data meeting the requirements of street office are reported to the cloud in real time;
the community management platform is responsible for managing server data and maintaining basic data; the community management platform of any cell can maintain and upload a face library outside the white list of the cell, and the cloud can update the face library to all the cells after obtaining the uploaded data;
the cloud of the street office deploys a big data related platform comprising Spark, Storm and HBase clusters; the cloud end utilizes HBase to store big data, and utilizes Spark to search target tracks in the mass historical data through the target picture; the cloud end processes stranger or vehicle data to serve as a data set, a Storm parallel training updating model is utilized, and the cloud end is utilized for deployment and control display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910754919.2A CN110619277A (en) | 2019-08-15 | 2019-08-15 | Multi-community intelligent deployment and control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910754919.2A CN110619277A (en) | 2019-08-15 | 2019-08-15 | Multi-community intelligent deployment and control method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110619277A true CN110619277A (en) | 2019-12-27 |
Family
ID=68921921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910754919.2A Pending CN110619277A (en) | 2019-08-15 | 2019-08-15 | Multi-community intelligent deployment and control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110619277A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275984A (en) * | 2020-02-20 | 2020-06-12 | 三一重工股份有限公司 | Vehicle detection method and device and server |
| CN111489380A (en) * | 2020-04-14 | 2020-08-04 | 上海天诚比集科技有限公司 | Target object track analysis method |
| CN112184771A (en) * | 2020-09-30 | 2021-01-05 | 青岛聚好联科技有限公司 | Community personnel trajectory tracking method and device |
| CN113010578A (en) * | 2021-03-22 | 2021-06-22 | 华南理工大学 | Community data analysis method and device, community intelligent interaction platform and storage medium |
| CN113159472A (en) * | 2020-10-30 | 2021-07-23 | 四川天翼网络服务有限公司 | Intelligent community special information research and judgment method, system, terminal and storage medium |
| CN113269091A (en) * | 2021-05-26 | 2021-08-17 | 广州瀚信通信科技股份有限公司 | Personnel trajectory analysis method, equipment and medium for intelligent park |
| CN113688810A (en) * | 2021-10-26 | 2021-11-23 | 深圳市安软慧视科技有限公司 | Target capturing method and system of edge device and related device |
| CN114445886A (en) * | 2022-01-20 | 2022-05-06 | 北京通建泰利特智能系统工程技术有限公司 | Intelligent community access method and system based on image recognition and readable storage medium |
| CN114494998A (en) * | 2022-01-19 | 2022-05-13 | 东莞先知大数据有限公司 | Intelligent analysis method and system for vehicle data |
| CN117354469A (en) * | 2023-12-05 | 2024-01-05 | 陕西华海信息技术有限公司 | District monitoring video target tracking method and system based on security precaution |
| CN118450087A (en) * | 2024-04-07 | 2024-08-06 | 广州市平可捷信息科技有限公司 | Intelligent security monitoring method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105632001A (en) * | 2016-03-24 | 2016-06-01 | 中山大学南方学院 | Security and protection monitoring method and system based on face recognition |
| CN106603690A (en) * | 2016-12-27 | 2017-04-26 | 东华互联宜家数据服务有限公司 | Data analysis device, data analysis processing system and data analysis method |
| CN106845342A (en) * | 2016-12-15 | 2017-06-13 | 重庆凯泽科技股份有限公司 | A kind of intelligence community monitoring system and method |
| CN106981041A (en) * | 2017-05-10 | 2017-07-25 | 深圳火眼智能有限公司 | A kind of wisdom peaceful community management system based on deep learning |
| CN109271891A (en) * | 2018-08-30 | 2019-01-25 | 成都考拉悠然科技有限公司 | A kind of dynamic face supervision method and system |
| CN109271554A (en) * | 2018-09-07 | 2019-01-25 | 江西省云眼大视界科技有限公司 | A kind of intelligent video identifying system and its application |
| CN109309808A (en) * | 2017-07-26 | 2019-02-05 | 梭维智能科技（深圳）有限公司 | A kind of monitoring system and method based on recognition of face |
-
2019
- 2019-08-15 CN CN201910754919.2A patent/CN110619277A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105632001A (en) * | 2016-03-24 | 2016-06-01 | 中山大学南方学院 | Security and protection monitoring method and system based on face recognition |
| CN106845342A (en) * | 2016-12-15 | 2017-06-13 | 重庆凯泽科技股份有限公司 | A kind of intelligence community monitoring system and method |
| CN106603690A (en) * | 2016-12-27 | 2017-04-26 | 东华互联宜家数据服务有限公司 | Data analysis device, data analysis processing system and data analysis method |
| CN106981041A (en) * | 2017-05-10 | 2017-07-25 | 深圳火眼智能有限公司 | A kind of wisdom peaceful community management system based on deep learning |
| CN109309808A (en) * | 2017-07-26 | 2019-02-05 | 梭维智能科技（深圳）有限公司 | A kind of monitoring system and method based on recognition of face |
| CN109271891A (en) * | 2018-08-30 | 2019-01-25 | 成都考拉悠然科技有限公司 | A kind of dynamic face supervision method and system |
| CN109271554A (en) * | 2018-09-07 | 2019-01-25 | 江西省云眼大视界科技有限公司 | A kind of intelligent video identifying system and its application |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275984A (en) * | 2020-02-20 | 2020-06-12 | 三一重工股份有限公司 | Vehicle detection method and device and server |
| CN111489380A (en) * | 2020-04-14 | 2020-08-04 | 上海天诚比集科技有限公司 | Target object track analysis method |
| CN111489380B (en) * | 2020-04-14 | 2022-04-12 | 上海天诚比集科技有限公司 | Target object track analysis method |
| CN112184771A (en) * | 2020-09-30 | 2021-01-05 | 青岛聚好联科技有限公司 | Community personnel trajectory tracking method and device |
| CN112184771B (en) * | 2020-09-30 | 2023-08-11 | 青岛聚好联科技有限公司 | Method and device for tracking personnel track of community |
| CN113159472A (en) * | 2020-10-30 | 2021-07-23 | 四川天翼网络服务有限公司 | Intelligent community special information research and judgment method, system, terminal and storage medium |
| CN113010578B (en) * | 2021-03-22 | 2024-03-15 | 华南理工大学 | Community data analysis method and device, community intelligent interaction platform and storage medium |
| CN113010578A (en) * | 2021-03-22 | 2021-06-22 | 华南理工大学 | Community data analysis method and device, community intelligent interaction platform and storage medium |
| CN113269091A (en) * | 2021-05-26 | 2021-08-17 | 广州瀚信通信科技股份有限公司 | Personnel trajectory analysis method, equipment and medium for intelligent park |
| CN113688810A (en) * | 2021-10-26 | 2021-11-23 | 深圳市安软慧视科技有限公司 | Target capturing method and system of edge device and related device |
| CN114494998A (en) * | 2022-01-19 | 2022-05-13 | 东莞先知大数据有限公司 | Intelligent analysis method and system for vehicle data |
| CN114494998B (en) * | 2022-01-19 | 2022-12-06 | 东莞先知大数据有限公司 | Intelligent analysis method and system for vehicle data |
| CN114445886A (en) * | 2022-01-20 | 2022-05-06 | 北京通建泰利特智能系统工程技术有限公司 | Intelligent community access method and system based on image recognition and readable storage medium |
| CN117354469B (en) * | 2023-12-05 | 2024-01-30 | 陕西华海信息技术有限公司 | District monitoring video target tracking method and system based on security precaution |
| CN117354469A (en) * | 2023-12-05 | 2024-01-05 | 陕西华海信息技术有限公司 | District monitoring video target tracking method and system based on security precaution |
| CN118450087A (en) * | 2024-04-07 | 2024-08-06 | 广州市平可捷信息科技有限公司 | Intelligent security monitoring method and system |
| CN118450087B (en) * | 2024-04-07 | 2024-10-11 | 广州市平可捷信息科技有限公司 | Intelligent security monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
| CN110390262B (en) | Video analysis method, device, server and storage medium | |
| CN108596277B (en) | Vehicle identity recognition method and device and storage medium | |
| KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN108062349B (en) | Video monitoring method and system based on video structured data and deep learning | |
| CN102610102B (en) | Suspect vehicle inspection and control method and system | |
| CN110188807A (en) | Tunnel pedestrian target detection method based on cascade super-resolution network and improvement Faster R-CNN | |
| CN103294775B (en) | Police service cloud image recognition vehicle administrating system based on geographic space-time constraint | |
| US20140369566A1 (en) | Perimeter Image Capture and Recognition System | |
| US20140369567A1 (en) | Authorized Access Using Image Capture and Recognition System | |
| KR102122850B1 (en) | Solution for analysis road and recognition vehicle license plate employing deep-learning | |
| CN111783530A (en) | Safety system and method for monitoring and identifying behaviors in restricted area | |
| KR102282800B1 (en) | Method for trackig multi target employing ridar and camera | |
| CN109376577A (en) | Video synthesis analysis method and system | |
| CN111444840B (en) | Automatic detection method and system for fake-licensed vehicle | |
| CN107133563A (en) | A kind of video analytic system and method based on police field | |
| CN109615904A (en) | Parking management method, device, computer equipment and storage medium | |
| CN110674753A (en) | Theft early warning method, terminal device and storage medium | |
| CN113971821A (en) | Driver information determination method and device, terminal device and storage medium | |
| KR20190041704A (en) | A cctv divided management system and method it | |
| CN108805184B (en) | Image recognition method and system for fixed space and vehicle | |
| CN113191273A (en) | Oil field well site video target detection and identification method and system based on neural network | |
| CN109325755A (en) | Electronics charge system based on automotive hub | |
| CN103761345A (en) | Video retrieval method based on OCR character recognition technology | |
| US12100214B2 (en) | Video-based public safety incident prediction system and method therefor |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191227 |
|
| RJ01 | Rejection of invention patent application after publication |