CN111144248B - People counting method, system and medium based on ST-FHCD network model - Google Patents
People counting method, system and medium based on ST-FHCD network model Download PDFInfo
- Publication number
- CN111144248B CN111144248B CN201911293709.4A CN201911293709A CN111144248B CN 111144248 B CN111144248 B CN 111144248B CN 201911293709 A CN201911293709 A CN 201911293709A CN 111144248 B CN111144248 B CN 111144248B
- Authority
- CN
- China
- Prior art keywords
- frames
- people
- fhcd
- network model
- picture
- 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
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 37
- 230000004927 fusion Effects 0.000 claims abstract description 17
- 238000012544 monitoring process Methods 0.000 claims description 19
- 230000009466 transformation Effects 0.000 claims description 12
- 230000001629 suppression Effects 0.000 claims description 5
- 238000009432 framing Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims 2
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/97—Determining parameters from multiple pictures
-
- 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
- G06T2207/30201—Face
-
- 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
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a people counting method based on an ST-FHCD network model, which comprises the following steps: an information acquisition step: acquiring pictures in classrooms; the detection step comprises: detecting face position frames in the picture, and outputting the number of the frames; and (3) a fusion step: fusing the number of frames to obtain information of the number of people; the storage step: the information of the number of people is stored in a database. According to the method, through detecting pictures with different scales, the detection difference of an algorithm on the size of a target is made up, and the omission ratio is reduced; the detection results within a certain time are fused, so that the detection rate of the blocked target can be improved, and the omission factor is reduced; by dividing the seat areas in advance, the false detection rate of the number of people is reduced, and the algorithm efficiency is improved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a people counting method, a system and a medium based on an ST-FHCD network model.
Background
The intelligent process is developed at a high speed, the security monitoring system is gradually perfected, and the monitoring system consists of shooting, transmission, control, display, record registration and the like. The video camera transmits video images to the control host through the coaxial video cable, the control host distributes video signals to each monitor and video equipment, and the voice signals to be transmitted are synchronously recorded into the video recorder. By using a special video processing mode, the operations such as recording, playback and processing can be performed on the images, so that the video effect can be optimized.
The content of the monitoring system is required to be identified in a refined mode, and the people counting high-definition monitoring system is an advanced intelligent security system for monitoring the flow of people. Not only can the regional access ports and the people number in and out be accurately counted, but also information such as the crowd flowing direction is provided. Operators can know passenger flow information of one or more entrances and exits to be monitored as required during management, and can also know and count changes of single-direction or bidirectional crowd flow and predict the number of detained people in an area.
The pedestrian flow serves as a key monitoring index in the intelligent monitoring system, plays an increasing role, so that the acquired passenger flow information can be used for mastering real-time dynamic information of a monitoring area according to data, timely obtaining accurate data of the number of people and the crowd flow in the field, facilitating more efficient organization work of a management unit, integrating with a third-party software system and providing data support for scientific decision.
The people counting high definition monitoring system supports various dimensional data analysis, including time (day, week, month, year, period, homonymy, cyclic ratio, etc.), space (nationwide, territories, shops, etc.).
And (5) comparing and analyzing the passenger flow volume to generate the same-ratio or ring-ratio data. And various chart forms such as diversified reports, statistics and the like are provided for displaying, and passenger flow is marked in a manner such as a histogram, a graph, an EXCEL, an HTML table and the like. Because the people counting high-definition monitoring system adopts an open interface protocol, the system can be in butt joint with a third party platform.
The remote monitoring client can be a WeChat client or a pc computer end to log in, and can log in any place to enter the system, and various services such as inquiry, report form, statistics, analysis, site condition observation and the like are provided by the personnel statistics comprehensive management platform. Real-time and accurate people counting of a monitoring area is an important application direction of the intelligent monitoring system.
Through searching the existing people counting technology, the Chinese patent publication No. CN105139425A describes a people counting method, and the publication date is 2015, 12, 19. Extracting a moving foreground target by carrying out target segmentation on a current frame image detection region; detecting a head-shoulder characteristic frame in the moving foreground object; judging whether the head-shoulder characteristic frames in the motion foreground target meet the statistical triggering conditions of the number of people; and when the head-shoulder characteristic frame meets the trigger condition of the people counting, the people counting is carried out according to the head-shoulder characteristic frame. The method can shorten the feature detection time, reduce the feature false detection rate and improve the feature detection effect, thereby improving the statistics efficiency and accuracy of the number of people. The disadvantage is that the statistical method has a certain omission ratio, for example, if the target is blocked by a blocking object, people cannot be detected through head and shoulder recognition, and people cannot be counted.
The ST-FHCD network model utilizes convolutional neural network to detect the number and position of people's head in the picture, and carries on the fusion of the detection result in space and time, it is a kind of people counting method.
Patent document CN108416250a (application number: 201710074404.9) discloses a people counting method and device, and the method is applied to a server carrying a people counting model comprising an image feature extraction sub-model and an SSD classification regression sub-model constructed based on a convolutional neural network, and specifically comprises: inputting the image frames into an image feature extraction sub-model to generate an image feature map; generating a default frame for each pixel point in the image feature map based on the SSD classification regression sub-model, acquiring position coordinates and probability scores of each default frame, and taking the maximum probability score as a primary confidence coefficient; screening out the first K default frames with the highest primary confidence as target candidate frames; based on the position coordinates and probability scores of the target candidate frames, carrying out bounding box regression analysis and softxmax classification to obtain the coordinate positions and final confidence coefficients of the target candidate frames; and acquiring target frames based on a non-maximum suppression algorithm, and counting the number of people in the monitoring area based on the number of the target frames.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a people counting method and system based on an ST-FHCD network model.
The people counting method based on the ST-FHCD network model provided by the invention comprises the following steps:
an information acquisition step: acquiring pictures in classrooms;
the detection step comprises: detecting face position frames in the picture, and outputting the number of the frames;
and (3) a fusion step: fusing the number of frames to obtain information of the number of people;
the storage step: the information of the number of people is stored in a database.
Preferably, the information acquisition step includes: shooting video streams in classrooms by using monitoring equipment;
and de-framing the video stream according to the FFmpeg to obtain a picture.
Preferably, the detecting step includes:
step 1: detecting the original scale of a single picture, dividing a detection area, scaling the picture to 640 x 360 pixels, and detecting a face in the picture by using an ST-FHCD network model to obtain a face position frame and a face transverse and longitudinal coordinates;
step 2: performing space multiscale detection, cutting an original image into four blocks with the same size by 2 x 2, scaling to 640 x 360 pixels respectively, detecting by using an ST-FHCD network model, and outputting the number of frames by corresponding the positions of the frames to the original image through coordinate transformation;
step 3: and (3) performing time fusion detection, namely performing step 1 and step 2 on all video frames in one unit by taking 10s as one unit, and outputting the number of frames by corresponding the positions of the frames to the original picture through coordinate transformation.
Preferably, the fusing step includes: in the ST-FHCD network model, detecting a face position frame, detecting whether the face position frame contains a face, and obtaining confidence probability;
and performing non-maximum suppression on the face position frames according to the confidence probability, removing the repeated frames and frames with sizes not conforming to the preset, mapping the rest frames into an original image through coordinate transformation, and taking the number of the final frames as the number of people detected in the current scene.
The people counting system based on the ST-FHCD network model provided by the invention comprises:
an information acquisition module: acquiring pictures in classrooms;
and a detection module: detecting face position frames in the picture, and outputting the number of the frames;
and a fusion module: fusing the number of frames to obtain information of the number of people;
and a storage module: the information of the number of people is stored in a database.
Preferably, the information acquisition module includes: acquiring video streams shot by monitoring equipment in a classroom;
and de-framing the video stream according to the FFmpeg to obtain a picture.
Preferably, the detection module includes:
module M1: detecting the original scale of a single picture, dividing a detection area, scaling the picture to 640 x 360 pixels, and detecting a face in the picture by using an ST-FHCD network model to obtain a face position frame and a face transverse and longitudinal coordinates;
module M2: performing space multiscale detection, cutting an original image into four blocks with the same size by 2 x 2, scaling to 640 x 360 pixels respectively, detecting by using an ST-FHCD network model, and outputting the number of frames by corresponding the positions of the frames to the original image through coordinate transformation;
module M3: and (3) performing time fusion detection, calling the module M1 and the module M2 for all video frames in a unit by taking 10s as a unit, and outputting the number of frames by corresponding the positions of the frames to the original picture through coordinate transformation.
Preferably, the fusion module includes: in the ST-FHCD network model, detecting a face position frame, detecting whether the face position frame contains a face, and obtaining confidence probability;
and performing non-maximum suppression on the face position frames according to the confidence probability, removing the repeated frames and frames with sizes not conforming to the preset, mapping the rest frames into an original image through coordinate transformation, and taking the number of the final frames as the number of people detected in the current scene.
Compared with the prior art, the invention has the following beneficial effects:
1. by detecting pictures with different scales, the detection difference of an algorithm on the size of a target is made up, and the omission ratio is reduced;
2. the detection results within a certain time are fused, so that the detection rate of the blocked target can be improved, and the omission factor is reduced;
3. by dividing the seat areas in advance, the false detection rate of the number of people is reduced, and the algorithm efficiency is improved.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a structural frame diagram of a person identification system according to the present invention;
figure 2 is a diagram of a model of the structure of the ST-FHCD network.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present invention.
As shown in fig. 1, the present embodiment provides a method for detecting the number of people, and in particular relates to a method for intelligently identifying and analyzing the number of people based on an ST-FHCD network model, which includes an information acquisition step, a detection step, a fusion step, and a storage step. The detection step comprises a people counting algorithm, the fusion step comprises a time fusion process and a space fusion process, and the storage step is used for storing information detected by the camera:
specifically, the video stream shot by the monitoring camera is transmitted to a system background, the background extracts video frames at intervals according to the video stream, and an algorithm of the background takes the video frames as input detection picture information.
Specifically, the video stream is transmitted to a system detection background, frames are intercepted in the background, pretreatment modes such as cutting, filtering and the like are carried out, and the number of people who output a monomer is processed through an ST-FHCD network to count.
As shown in fig. 2, the network structure diagram of the ST-FHCD algorithm used in this example mainly includes five rounds of 3*3 filters, 1*1 filters and 4 maximized pool layers, and then the coordinates of the head prediction probability layer and the regression prediction positioning are output and converted into spatial coordinates with 640 x 480 layer dimensions by a bounding box, after which the pictures sequentially pass through a time slicing layer and a spatial slicing layer, and the results are recorded respectively, and the number of people in the current scene and the corresponding position coordinates are output in the final result fusion layer.
Those skilled in the art will appreciate that the systems, apparatus, and their respective modules provided herein may be implemented entirely by logic programming of method steps such that the systems, apparatus, and their respective modules are implemented as logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc., in addition to the systems, apparatus, and their respective modules being implemented as pure computer readable program code. Therefore, the system, the apparatus, and the respective modules thereof provided by the present invention may be regarded as one hardware component, and the modules included therein for implementing various programs may also be regarded as structures within the hardware component; modules for implementing various functions may also be regarded as being either software programs for implementing the methods or structures within hardware components.
The foregoing describes specific embodiments of the present invention. It is to be understood that the invention is not limited to the particular embodiments described above, and that various changes or modifications may be made by those skilled in the art within the scope of the appended claims without affecting the spirit of the invention. The embodiments of the present application and features in the embodiments may be combined with each other arbitrarily without conflict.
Claims (5)
1. A method for counting the number of people based on an ST-FHCD network model, comprising:
an information acquisition step: acquiring pictures in classrooms;
the detection step comprises: detecting face position frames in the picture, and outputting the number of the frames;
and (3) a fusion step: fusing the number of frames to obtain information of the number of people;
the storage step: storing the information of the number of people in a database;
the information acquisition step includes: shooting video streams in classrooms by using monitoring equipment;
according to FFmpeg, de-framing the video stream to obtain a picture;
the ST-FHCD network model comprises five rounds of 3*3 filters, 1*1 filters and 4 maximized pool layers, and then outputs the coordinates of the positioning through head prediction probability layers and regression prediction, the coordinates are converted into space coordinates under 640 x 480 layers through a boundary box, after that, the pictures sequentially pass through a time cutting layer and a space cutting layer, the results are recorded respectively, and the number of people in the current scene and the corresponding position coordinates are output in a final result fusion layer;
the detection step comprises the following steps:
step 1: detecting the original scale of a single picture, dividing a detection area, scaling the picture to 640 x 360 pixels, and detecting a face in the picture by using an ST-FHCD network model to obtain a face position frame and a face transverse and longitudinal coordinates;
step 2: performing space multiscale detection, cutting an original image into four blocks with the same size by 2 x 2, scaling to 640 x 360 pixels respectively, detecting by using an ST-FHCD network model, and outputting the number of frames by corresponding the positions of the frames to the original image through coordinate transformation;
step 3: and (3) performing time fusion detection, namely performing step 1 and step 2 on all video frames in one unit by taking 10s as one unit, and outputting the number of frames by corresponding the positions of the frames to the original picture through coordinate transformation.
2. The method of claim 1, wherein the step of fusing comprises: in the ST-FHCD network model, detecting a face position frame, detecting whether the face position frame contains a face, and obtaining confidence probability;
and performing non-maximum suppression on the face position frames according to the confidence probability, removing the repeated frames and frames with sizes not conforming to the preset, mapping the rest frames into an original image through coordinate transformation, and taking the number of the final frames as the number of people detected in the current scene.
3. A system for demographic based on an ST-FHCD network model, comprising:
an information acquisition module: acquiring pictures in classrooms;
and a detection module: detecting face position frames in the picture, and outputting the number of the frames;
and a fusion module: fusing the number of frames to obtain information of the number of people;
and a storage module: storing the information of the number of people in a database;
the information acquisition module includes: acquiring video streams shot by monitoring equipment in a classroom;
according to FFmpeg, de-framing the video stream to obtain a picture;
the detection module comprises:
module M1: detecting the original scale of a single picture, dividing a detection area, scaling the picture to 640 x 360 pixels, and detecting a face in the picture by using an ST-FHCD network model to obtain a face position frame and a face transverse and longitudinal coordinates;
module M2: performing space multiscale detection, cutting an original image into four blocks with the same size by 2 x 2, scaling to 640 x 360 pixels respectively, detecting by using an ST-FHCD network model, and outputting the number of frames by corresponding the positions of the frames to the original image through coordinate transformation;
module M3: performing time fusion detection, calling a module M1 and a module M2 for all video frames in a unit by taking 10s as a unit, and outputting the number of frames by corresponding the positions of the frames to the original picture through coordinate transformation;
the ST-FHCD network model comprises five rounds of 3*3 filters, 1*1 filters and 4 maximized pool layers, and then outputs coordinates of head prediction probability layers and regression prediction positioning, the coordinates are converted into spatial coordinates under 640 x 480 layers through a boundary box, after that, pictures sequentially pass through a time cutting layer and a spatial cutting layer, the results are recorded respectively, and the number of people in the current scene and the corresponding position coordinates are output in a final result fusion layer.
4. The ST-FHCD network model-based demographics system of claim 3, wherein the fusion module comprises: in the ST-FHCD network model, detecting a face position frame, detecting whether the face position frame contains a face, and obtaining confidence probability;
and performing non-maximum suppression on the face position frames according to the confidence probability, removing the repeated frames and frames with sizes not conforming to the preset, mapping the rest frames into an original image through coordinate transformation, and taking the number of the final frames as the number of people detected in the current scene.
5. A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911293709.4A CN111144248B (en) | 2019-12-16 | 2019-12-16 | People counting method, system and medium based on ST-FHCD network model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911293709.4A CN111144248B (en) | 2019-12-16 | 2019-12-16 | People counting method, system and medium based on ST-FHCD network model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111144248A CN111144248A (en) | 2020-05-12 |
| CN111144248B true CN111144248B (en) | 2024-02-27 |
Family
ID=70518428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911293709.4A Active CN111144248B (en) | 2019-12-16 | 2019-12-16 | People counting method, system and medium based on ST-FHCD network model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144248B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416250A (en) * | 2017-02-10 | 2018-08-17 | 浙江宇视科技有限公司 | Demographic method and device |
| CN108460403A (en) * | 2018-01-23 | 2018-08-28 | 上海交通大学 | The object detection method and system of multi-scale feature fusion in a kind of image |
| CN108520219A (en) * | 2018-03-30 | 2018-09-11 | 台州智必安科技有限责任公司 | A kind of multiple dimensioned fast face detecting method of convolutional neural networks Fusion Features |
| CN108615027A (en) * | 2018-05-11 | 2018-10-02 | 常州大学 | A method of video crowd is counted based on shot and long term memory-Weighted Neural Network |
| CN109034036A (en) * | 2018-07-19 | 2018-12-18 | 青岛伴星智能科技有限公司 | A kind of video analysis method, Method of Teaching Quality Evaluation and system, computer readable storage medium |
| CN109101914A (en) * | 2018-08-01 | 2018-12-28 | 北京飞搜科技有限公司 | It is a kind of based on multiple dimensioned pedestrian detection method and device |
| CN109376637A (en) * | 2018-10-15 | 2019-02-22 | 齐鲁工业大学 | Passenger number statistical system based on video monitoring image processing |
| CN110427839A (en) * | 2018-12-26 | 2019-11-08 | 西安电子科技大学 | Video object detection method based on multilayer feature fusion |
-
2019
- 2019-12-16 CN CN201911293709.4A patent/CN111144248B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416250A (en) * | 2017-02-10 | 2018-08-17 | 浙江宇视科技有限公司 | Demographic method and device |
| CN108460403A (en) * | 2018-01-23 | 2018-08-28 | 上海交通大学 | The object detection method and system of multi-scale feature fusion in a kind of image |
| CN108520219A (en) * | 2018-03-30 | 2018-09-11 | 台州智必安科技有限责任公司 | A kind of multiple dimensioned fast face detecting method of convolutional neural networks Fusion Features |
| CN108615027A (en) * | 2018-05-11 | 2018-10-02 | 常州大学 | A method of video crowd is counted based on shot and long term memory-Weighted Neural Network |
| CN109034036A (en) * | 2018-07-19 | 2018-12-18 | 青岛伴星智能科技有限公司 | A kind of video analysis method, Method of Teaching Quality Evaluation and system, computer readable storage medium |
| CN109101914A (en) * | 2018-08-01 | 2018-12-28 | 北京飞搜科技有限公司 | It is a kind of based on multiple dimensioned pedestrian detection method and device |
| CN109376637A (en) * | 2018-10-15 | 2019-02-22 | 齐鲁工业大学 | Passenger number statistical system based on video monitoring image processing |
| CN110427839A (en) * | 2018-12-26 | 2019-11-08 | 西安电子科技大学 | Video object detection method based on multilayer feature fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111144248A (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110738127B (en) | Helmet identification method based on unsupervised deep learning neural network algorithm | |
| CN104063883B (en) | A kind of monitor video abstraction generating method being combined based on object and key frame | |
| CN108319926A (en) | A kind of the safety cap wearing detecting system and detection method of building-site | |
| CN101778260B (en) | Method and system for monitoring and managing videos on basis of structured description | |
| CN109298785A (en) | A kind of man-machine joint control system and method for monitoring device | |
| KR102035592B1 (en) | A supporting system and method that assist partial inspections of suspicious objects in cctv video streams by using multi-level object recognition technology to reduce workload of human-eye based inspectors | |
| CN109711377B (en) | Method for positioning and counting examinees in single-frame image monitored by standardized examination room | |
| CN107229894A (en) | Intelligent video monitoring method and system based on computer vision analysis technology | |
| WO2021031954A1 (en) | Object quantity determination method and apparatus, and storage medium and electronic device | |
| WO2021139049A1 (en) | Detection method, detection apparatus, monitoring device, and computer readable storage medium | |
| CN112329691A (en) | Monitoring video analysis method and device, electronic equipment and storage medium | |
| WO2020114116A1 (en) | Pedestrian detection method based on dense crowds, and storage medium and processor | |
| US20220301317A1 (en) | Method and device for constructing object motion trajectory, and computer storage medium | |
| Kongurgsa et al. | Real-time intrusion—detecting and alert system by image processing techniques | |
| CN115223246A (en) | Personnel violation identification method, device, equipment and storage medium | |
| CN106781167B (en) | Method and device for monitoring motion state of object | |
| CN115294519A (en) | Abnormal event detection and early warning method based on lightweight network | |
| CN114067396A (en) | Vision learning-based digital management system and method for live-in project field test | |
| CN105095891A (en) | Human face capturing method, device and system | |
| CN108960165A (en) | A kind of stadiums population surveillance method based on intelligent video identification technology | |
| CN116030370A (en) | Behavior recognition method and device based on multi-target tracking and electronic equipment | |
| CN106803937B (en) | Double-camera video monitoring method, system and monitoring device with text log | |
| CN111144248B (en) | People counting method, system and medium based on ST-FHCD network model | |
| CN110855932B (en) | Alarm method and device based on video data, electronic equipment and storage medium | |
| CN111277789A (en) | Video-based community security method and device, electronic equipment and storage medium |
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 |