CN109446946A - A kind of multi-cam real-time detection method based on multithreading - Google Patents
A kind of multi-cam real-time detection method based on multithreading Download PDFInfo
- Publication number
- CN109446946A CN109446946A CN201811197765.3A CN201811197765A CN109446946A CN 109446946 A CN109446946 A CN 109446946A CN 201811197765 A CN201811197765 A CN 201811197765A CN 109446946 A CN109446946 A CN 109446946A
- Authority
- CN
- China
- Prior art keywords
- face
- pedestrian
- network
- picture
- yolo3
- 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.)
- Granted
Links
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
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- 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
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
Abstract
Multi-cam real-time detection method based on multithreading, pedestrian of the load based on ResNet50 and triple loss functions identifies network again first, building detection face database, the feature vector of face database is extracted using the library face_recognition, start to construct multi-threaded system later, queue is constructed using the Queue in the library multiprocess, and use daemon finger daemon, later by Yolo3 by personage position and with Opencv cut out come, it is identified later using the identification module in the library face_recognition, pedestrian is used to identify that network identifies again if no face, finally by multi-threading parallel process, the target in multiple cameras can be measured in real time in monitor video.
Description
Technical field
The present invention relates to the methods being measured in real time to camera shooting video.
Background technique
Since safety-security area is quickly grown, camera function is become stronger day by day, and existing camera generally has communication
Agreement may be implemented wired and wireless long-distance video and read.Simultaneously as the increase in demand of safety, more and more to image
Head is installed in building, and monitoring is played the role of in the places such as street.Thus police etc. can carry out personage's by camera
Monitoring, and handle multiple cameras in real time and improve efficiency.
Recognition of face and pedestrian identify it is the key technology for identifying specific pedestrian again.But due to current effective side
Fado uses deep learning neural network, its committed memory is big, while calculation amount is also more, and the scene of real time monitoring is difficult
It is handled.So using multithreading, parallel processing carried out using multiple threads for multiple cameras, it is so can be with
Guarantee does not have successive influence for the video of multi-source camera, while can guarantee a higher real-time yet.
Summary of the invention
The present invention will overcome the disadvantages mentioned above of the prior art, provide a kind of multi-cam real-time detection side based on multithreading
Method.
For real-time purpose to be realized, the present invention devises a kind of multi-cam real-time detection side based on multithreading
Method can effectively improve the requirement of real-time, the precision that reduction recognition of face and pedestrian identify again.This is for real-time mesh
Mark detection, is a very big promotion in efficiency, utilizable because the quantity of same time-triggered protocol camera increases
Information is also more with time-varying, and it is accurate that user also can judge to detect whether from more information.
The present invention realizes technical solution used by foregoing invention purpose are as follows:
A kind of multi-cam method of real-time of multithreading, comprising the following steps:
Step 1. load pedestrian identifies network again: using the ResNet50 network of pre-training, will connect entirely in ResNet50
Output before layer uses triple loss function tectonic networks as pedestrian's feature, and passes through the training of Market1501 data set.
Step 2. establishes face database, loads recognition of face network: selecting the third party library dlib of Python, and face_
Recognition carries out the judgement of recognition of face, and the face picture that will test target is added to local library and carries out feature extraction.
Step 3. reads monitoring camera video: monitoring camera mostly uses greatly wired form to be configured, and usually takes
It is loaded with Rstp agreement, carries out video reading using the VideoCapture function in Opencv.
Step 4. personage cuts step: the Yolo3 weight of pre-download is put under specified directory, Yolo3 network is loaded, it will
The picture read from camera is put into Yolo3, obtains the coordinate of pedestrian, and cut out pedestrian's picture and identify.
Step 5. constructs the step of multithreading frame: the multithreading library multiprocess for selecting Python included, and sets
Set the picture that multiple queues are used to store multiple cameras (quantity depends on camera quantity).And by main program
Process.start () function starts multithreading service.And daemon finger daemon is used, guarantee that it, in running background, is more
Thread comes with being environmentally isolated before operation, guarantees the operation of parent process.
Step 6. person detecting step: in single subprocess, the knowledge of personage is carried out using the target detection network of Yolo3
Not, the picture cut is put into the face detection module of face_recoginition and has detected whether clear face, such as
Fruit can carry out recognition of face if having face, in the case where no face, if someone in pedestrian library, and progress
Match, if there is being matched to people (Euclidean distance is less than threshold value), then identifies successfully and outline personage to add label, if do not had
The people being matched to can not then judge；If the nobody of pedestrian library, it can not judge
Compared with prior art, have the advantages of technical solution of the present invention:
(1) present invention makes full use of computer memory space, can handle multiple cameras as far as possible, promotes work effect
Rate, and reduce cost.
(2) third party library carried using Python itself has transplanting convenient, the advantages of should be readily appreciated that.
Detailed description of the invention
Fig. 1: the flow chart of the method for the present invention；
Fig. 2: multithreading setting procedure figure of the invention；
Fig. 3: face characteristic saves flow chart.
Specific embodiment
Understand for the ease of those of ordinary skill in the art and implement the present invention, with reference to the accompanying drawings and examples to this hair
It is bright to be described in further detail.
A kind of multi-cam real-time detection method based on multithreading contains step:
(1) pedestrian that load was trained identifies network again
Step 11: selecting existing pedestrian to identify network again, have on current some open source websites in Market1501 data
The accuracy for having reached 94% on collection, is substantially able to satisfy demand.The structure of the network of selection is as described below, ResNet50 conduct
Last full articulamentum is removed, and handled 3 block once by backbone network, and res5a, res5b do pondization processing,
And the feature vector of one 1024 dimension is obtained by exporting the full articulamentum tieed up for 1024 after the splicing of left and right, while doing to res5c
Pondization processing, is directly launched into the feature vector of 2048 dimensions.The two are superimposed and is used as final feature vector.
Step 12: add triple loss functions, be added hard_triplet loss function, softmax loss function and
Ring loss function is built into last pedestrian and identifies network again.The data set of oneself can be finely adjusted, be had reached more preferable
Effect.
(2) face database is established, and loads human face recognition model
Step 21: each 2-3 positive face photos of taking one's hat off of example storage, wherein photo is preferably without any processing, otherwise
It will affect precision.It is stored in a file then according to naming rule, if Li Ming reference numeral is 0003, then photo is named
For the photo sequence that 0003_*.jpg, * are this example face.
Step 22: dlib and face_recognition third party library being installed in the environment, and can be first by face database
Face picture pass through feature vector save.
(3) camera head monitor picture step is read
Step 31: the reading of camera video is carried out using the VideoCapture class in Opencv.It will be assisted with RTSP
The user name of camera is discussed, password and IP address define respectively, and are filled according to specified format, and each company is taken the photograph
As head is all different.
Step 32: the picture in VideoCapture class being read out using read () function in Opencv, is provided
We are handled.
(4) person detecting step
Step 41: the Yolo3 weight of pre-download being put under specified directory, Yolo3 is a kind of mesh that occupied space is less
Mark detection neural network, accuracy rate is low compared to Faster-Rcnn, but uses enough.
Step 42: the picture read from camera is put into Yolo3, obtains the coordinate of pedestrian by load Yolo3 network,
And it cuts out pedestrian's picture and identifies.
(5) the step of constructing multithreading frame
Step 51: the load Python included library Multiprocess, and multiple queues are set, number and desired reading
The quantity of camera video is identical, and capacity is set as 2.
Step 52: camera picture is read and is pressed into queue by two queue operations of setting, operation of bringing up the rear, dequeue operation
Picture is extruded from queue, and is handled.
Step 53: each sub thread identifies the pedestrian loaded before again and Yolo3 network reads and carries out independent point
Analysis carrys out parallel work-flow with this, promotes processing speed.
(6) person detecting step:
Step 61: after the picture of camera is read by RSTP protocol remote first, in single subprocess, using
The target detection network of Yolo3 carries out the identification of personage, and is cut personage by the coordinate that Yolo3 is exported.
Step 62: the picture cut being put into the face detection module of face_recoginition and is detected whether
There is clear face, recognition of face can be carried out if there is face, step 3 is jumped into if without face.Carry out face knowledge
If capableing of the information (reaching under threshold value) of very determining pedestrian when other, current information is charged in pedestrian library.
Step 63: in the case where no face, be first the case where seeing pedestrian library, if someone in pedestrian library,
It is then matched, if there is being matched to people (Euclidean distance be less than threshold value), then identifies successfully and outline personage to add label,
If the people being not matched to can not judge.If the nobody of pedestrian library, it can not judge.
Content described in this specification embodiment is only enumerating to the way of realization of inventive concept, protection of the invention
Range should not be construed as being limited to the specific forms stated in the embodiments, and protection scope of the present invention is also and in art technology
Personnel conceive according to the present invention it is conceivable that equivalent technologies mean.
Claims (1)
1. a kind of multi-cam real-time detection method based on multithreading, includes the following steps；
(1) pedestrian that load was trained identifies network again；
It selects existing pedestrian to identify network again, the back-page structure of ResNet50 network is converted into the block of 3 difference,
And respectively convert its output to the feature of 3072 last dimensions；3 weight loss function of finally addition identifies net as pedestrian again
The step of network；
(2) face database is established, and loads human face recognition model；
Step 21, each 2-3 positive face photos of taking one's hat off of example storage, and picture is named with number+arrangement serial number, it is stored in specified
Step under catalogue；
Step 22, picture name file corresponding with name is established under specified directory；
(3) camera head monitor picture step is read；
Step 31, the reading of camera video is carried out using the VideoCapture class in Opencv；
Step 32, the picture figure area in VideoCapture class is come out using read () function in Opencv and is added to team
In column；
(4) personage cuts step；
Step 41, the Yolo3 weight of pre-download is put under specified directory, loads Yolo3 network；
Step 42, the picture read from camera is put into Yolo3, obtains the coordinate of pedestrian, and cut out pedestrian's picture into
The step of row identification；
(5) the step of constructing multithreading frame；
Step 51, the load Python included library Multiprocess, sets two queue operations；
Step 52, each sub thread identifies the pedestrian loaded before again and Yolo3 network reads and carries out independent analysis；
(6) person detecting step；
Step 61, in single subprocess, the identification of personage is carried out using the target detection network of Yolo3, by what is cut
Picture, which is put into the face detection module of face_recoginition, has detected whether clear face；
Step 62, recognition of face can be carried out if there is face, in the case where no face, if someone in pedestrian library
If, then it is matched, if there is being matched to people (Euclidean distance is less than threshold value), then identifies successfully and outline personage to add
Label can not judge if the people being not matched to；If the nobody of pedestrian library, it can not judge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811197765.3A CN109446946B (en) | 2018-10-15 | 2018-10-15 | Multi-camera real-time detection method based on multithreading |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811197765.3A CN109446946B (en) | 2018-10-15 | 2018-10-15 | Multi-camera real-time detection method based on multithreading |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109446946A true CN109446946A (en) | 2019-03-08 |
| CN109446946B CN109446946B (en) | 2022-03-18 |
Family
ID=65546376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811197765.3A Active CN109446946B (en) | 2018-10-15 | 2018-10-15 | Multi-camera real-time detection method based on multithreading |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446946B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948490A (en) * | 2019-03-11 | 2019-06-28 | 浙江工业大学 | A kind of employee's specific behavior recording method identified again based on pedestrian |
| CN110457991A (en) * | 2019-06-24 | 2019-11-15 | 平安科技（深圳）有限公司 | Picture feature value file optimization method, device, terminal and storage medium |
| CN111027462A (en) * | 2019-12-06 | 2020-04-17 | 长沙海格北斗信息技术有限公司 | Pedestrian track identification method across multiple cameras |
| CN112818917A (en) * | 2021-02-24 | 2021-05-18 | 复旦大学 | Real-time pedestrian detection and re-identification method and device |
| CN113095199A (en) * | 2021-04-06 | 2021-07-09 | 复旦大学 | High-speed pedestrian identification method and device |
| CN113591809A (en) * | 2021-09-28 | 2021-11-02 | 广州思林杰科技股份有限公司 | Method and device for determining action track of client in website |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016341A (en) * | 2017-03-03 | 2017-08-04 | 西安交通大学 | A kind of embedded real-time face recognition methods |
| US20180005343A1 (en) * | 2016-07-01 | 2018-01-04 | Digimarc Corporation | Image-based pose determination |
| CN108038462A (en) * | 2017-12-22 | 2018-05-15 | 深圳英飞拓科技股份有限公司 | A kind of method and device that Face datection is carried out to real-time video and is identified |
| CN108564052A (en) * | 2018-04-24 | 2018-09-21 | 南京邮电大学 | Multi-cam dynamic human face recognition system based on MTCNN and method |
| CN108596010A (en) * | 2017-12-31 | 2018-09-28 | 厦门大学 | The implementation method of pedestrian's weight identifying system |
-
2018
- 2018-10-15 CN CN201811197765.3A patent/CN109446946B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180005343A1 (en) * | 2016-07-01 | 2018-01-04 | Digimarc Corporation | Image-based pose determination |
| CN107016341A (en) * | 2017-03-03 | 2017-08-04 | 西安交通大学 | A kind of embedded real-time face recognition methods |
| CN108038462A (en) * | 2017-12-22 | 2018-05-15 | 深圳英飞拓科技股份有限公司 | A kind of method and device that Face datection is carried out to real-time video and is identified |
| CN108596010A (en) * | 2017-12-31 | 2018-09-28 | 厦门大学 | The implementation method of pedestrian's weight identifying system |
| CN108564052A (en) * | 2018-04-24 | 2018-09-21 | 南京邮电大学 | Multi-cam dynamic human face recognition system based on MTCNN and method |
Non-Patent Citations (1)
| Title |
|---|
| JUN XIANG 等: "Person Re-identification Based on Feature Fusion and Triplet Loss Function", 《2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948490A (en) * | 2019-03-11 | 2019-06-28 | 浙江工业大学 | A kind of employee's specific behavior recording method identified again based on pedestrian |
| CN110457991A (en) * | 2019-06-24 | 2019-11-15 | 平安科技（深圳）有限公司 | Picture feature value file optimization method, device, terminal and storage medium |
| CN111027462A (en) * | 2019-12-06 | 2020-04-17 | 长沙海格北斗信息技术有限公司 | Pedestrian track identification method across multiple cameras |
| CN112818917A (en) * | 2021-02-24 | 2021-05-18 | 复旦大学 | Real-time pedestrian detection and re-identification method and device |
| CN112818917B (en) * | 2021-02-24 | 2022-03-22 | 复旦大学 | Real-time pedestrian detection and re-identification method and device |
| CN113095199A (en) * | 2021-04-06 | 2021-07-09 | 复旦大学 | High-speed pedestrian identification method and device |
| CN113095199B (en) * | 2021-04-06 | 2022-06-14 | 复旦大学 | High-speed pedestrian identification method and device |
| CN113591809A (en) * | 2021-09-28 | 2021-11-02 | 广州思林杰科技股份有限公司 | Method and device for determining action track of client in website |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109446946B (en) | 2022-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446946A (en) | A kind of multi-cam real-time detection method based on multithreading | |
| US20230063920A1 (en) | Content navigation with automated curation | |
| US10242250B2 (en) | Picture ranking method, and terminal | |
| CN107481327B (en) | About the processing method of augmented reality scene, device, terminal device and system | |
| CN103207870B (en) | Photo classification management method, server, device and system | |
| CN104331509A (en) | Picture managing method and device | |
| US20150055879A1 (en) | Method, Server and System for Setting Background Image | |
| CN102880634B (en) | Intelligent human-face recognition and retrieval method based on cloud | |
| CN108256439A (en) | A kind of pedestrian image generation method and system based on cycle production confrontation network | |
| CN103617432A (en) | Method and device for recognizing scenes | |
| CN113365147B (en) | Video editing method, device, equipment and storage medium based on music card point | |
| CN110163041A (en) | Video pedestrian recognition methods, device and storage medium again | |
| CN101300588A (en) | Determining a particular person from a collection | |
| WO2016145844A1 (en) | Picture sorting method and corresponding picture storage and display device | |
| CN110765134A (en) | File establishing method, equipment and storage medium | |
| CN109670517A (en) | Object detection method, device, electronic equipment and target detection model | |
| CN105224913A (en) | A kind of number of articles detection method and device | |
| CN103428537A (en) | Video processing method and video processing device | |
| CN103501410B (en) | The based reminding method of shooting, the generation method of device and detection pattern, device | |
| CN106250396B (en) | Automatic image label generation system and method | |
| CN105631404A (en) | Method and device for clustering pictures | |
| CN110324589A (en) | A kind of monitoring system and method for tourist attraction | |
| CN105787131A (en) | Information processing method and device and mobile terminal | |
| Presa-Reyes et al. | Deep learning with weak supervision for disaster scene description in low-altitude imagery | |
| CN112101387A (en) | Salient element identification method and device |
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 |