CN110321857A - Accurate objective group analysis method based on edge calculations technology - Google Patents
Accurate objective group analysis method based on edge calculations technology Download PDFInfo
- Publication number
- CN110321857A CN110321857A CN201910609505.0A CN201910609505A CN110321857A CN 110321857 A CN110321857 A CN 110321857A CN 201910609505 A CN201910609505 A CN 201910609505A CN 110321857 A CN110321857 A CN 110321857A
- Authority
- CN
- China
- Prior art keywords
- face
- analysis method
- edge calculations
- group analysis
- code stream
- 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
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
Abstract
The accurate objective group analysis method that the invention discloses a kind of based on edge calculations technology.A kind of accurate objective group analysis method based on edge calculations technology of the present invention, comprising: after extraneous light passes through camera lens, be irradiated on sensor cover, the light conducted from camera lens is converted to electric signal by sensor, then the AD conversion for passing through inside is digital signal;Picture signal exports the data of color difference components format by video input module after handling using video processing subsystem.Beneficial effects of the present invention: the present invention realizes video image parsing, target detection tracking (an equipment same picture could support up 10 Face datection tracking), adjustable, the face characteristic extraction of luminance compensation etc. in hardware end first, so that network bandwidth consumption is reduced, traffic efficiency significantly improves, energy support is higher concurrent, and batch passenger flow biggish industry higher to requirement of real-time has obvious help.
Description
Technical field
The present invention relates to field of face identification, and in particular to a kind of accurate objective cluster analysis side based on edge calculations technology
Method.
Background technique
Current business message ten thousand becomes, how within the shortest time the anti-of fast accurate is made in variation faint to market
It answers, and saves commercial operation cost to greatest extent, to realize that efficient commercial operation management has become commercial operation
The key element of success or failure.Such as:
Acquisition passenger flow information in real time, provides scientific basis for operation management.
It prevents passenger flow from unnecessary accident excessively occurs, establishes safe public place.
By counting the passenger flow of each entrance and the direction of passenger flow disengaging, the conjunction of each entrance setting can be precisely judged
Rationality.
By counting each main region passenger flow, so that the reasonable layout to whole region provides scientific basis.
It, can objective decision sales counter, retail shop's rent price level by passenger flow statistics.
However, in the prior art, often use infrared induction mode statistical passenger flow, this mode cost ratio haggle over it is moderate,
But it is highly prone to extraneous factor interference due to infrared, its statistical data is made to generate large error;For than wider doorway, more people
Simultaneously by being also easy to produce leakage number phenomenon.
There are following technical problems for traditional technology:
And pass through the passenger flow statistics mode of cloud Face datection and comparison, larger to the consumption of network bandwidth, more people at present
The response speed into shop will be by shadow simultaneously.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of accurate objective group analysis method based on edge calculations technology, use
In statistics, analysis passenger flow.
The accurate objective cluster analysis side that in order to solve the above-mentioned technical problems, the present invention provides a kind of based on edge calculations technology
Method, comprising: after extraneous light passes through camera lens, be irradiated on sensor cover, sensor turns the light conducted from camera lens
It is changed to electric signal, then the AD conversion for passing through inside is digital signal;Picture signal is by video input module, at video
The data of color difference components format are exported after reason subsystem processes;
The producer is responsible for receiving the reception and distribution of color difference components formatted data:
The producer fills frame number (cumulative) in color difference components data and issues Video Output Modules, transfers to recognition of face
Algorithm is handled;
The producer fills frame number (cumulative) in color difference components data and is stored in image buffer storage queue;It is regarded for synchronous
The processing result of frequency frame and face recognition algorithms;
Color difference components data are sent MJPEG encoder by the producer, and the frame number that adds up in MJPEG receiving thread, with
This synchronizes color difference components data and MJPEG frame number;
Consumer is responsible for receiving and handling the result of face recognition algorithms:
Consumer receives the result (including corresponding frame number) of face recognition algorithms, and is matched by image buffer storage queue
Face location is plotted in color difference components image by corresponding video frame, is then sent to encoder, is received code stream and is provided out
Code stream plays service;
The result of face recognition algorithms is sent to face tracking thread;
Face tracking thread at the appointed time, preferably conforms to desired human face target, is sent to candid photograph thread.Capture line
Journey receives candid photograph task, corresponding picture in JPEG queue is matched by the frame number in face information, further according to face information
In face location intercept face picture.
It is irradiated on sensor cover after optical filter filters in one of the embodiments,.
In one of the embodiments, video processing subsystem processing include automatically track white balance, camera lens shade,
Gray scale, acutance, automatic exposure and noise reduction.
The encoder is H264 encoder in one of the embodiments,.
In " receiving code stream in one of the embodiments, and be provided out code stream broadcasting service ", the code stream is H264 code
Stream.
Flv server and rtsp server reception H264 code stream is provided out code stream and broadcasts in one of the embodiments,
The service of putting.
It uploads onto the server and is further processed after the entire candid photograph process of completion in one of the embodiments,.
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
The step of computer program, the processor realizes any one the method when executing described program.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
The step of any one the method.
A kind of processor, the processor is for running program, wherein described program executes described in any item when running
Method.
Beneficial effects of the present invention:
The present invention first hardware end realize video image parsing, target detection tracking (an equipment same picture is most
It is support 10 Face datections tracking more), luminance compensation is adjustable, face characteristic extracts etc. so that network bandwidth consumption is reduced, lead to
Line efficiency significantly improves, and can support higher concurrent, and batch passenger flow biggish industry higher to requirement of real-time has obvious side
It helps.Meanwhile video camera and algorithm chip become integral type from split type by the present invention, more compact, very good solution complexity
The installation question of environment.
Detailed description of the invention
Fig. 1 is in the accurate objective group analysis method the present invention is based on edge calculations technology " at edge calculations integral type hardware
The schematic diagram of reason part "
Fig. 2 is the schematic diagram of " back partition " in the accurate objective group analysis method the present invention is based on edge calculations technology.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings and specific examples, so that those skilled in the art can be with
It more fully understands the present invention and can be practiced, but illustrated embodiment is not as a limitation of the invention.
A kind of accurate objective group analysis method based on edge calculations technology, comprising: after extraneous light passes through camera lens, be irradiated to
On sensor cover, the light conducted from camera lens is converted to electric signal by sensor, then the AD conversion for passing through inside is number
Word signal;Picture signal exports color difference components format by video input module after handling using video processing subsystem
Data;
The producer is responsible for receiving the reception and distribution of color difference components formatted data:
The producer fills frame number (cumulative) in color difference components data and issues Video Output Modules, transfers to recognition of face
Algorithm is handled;
The producer fills frame number (cumulative) in color difference components data and is stored in image buffer storage queue;It is regarded for synchronous
The processing result of frequency frame and face recognition algorithms;
Color difference components data are sent MJPEG encoder by the producer, and the frame number that adds up in MJPEG receiving thread, with
This synchronizes color difference components data and MJPEG frame number;
Consumer is responsible for receiving and handling the result of face recognition algorithms:
Consumer receives the result (including corresponding frame number) of face recognition algorithms, and is matched by image buffer storage queue
Face location is plotted in color difference components image by corresponding video frame, is then sent to encoder, is received code stream and is provided out
Code stream plays service;
The result of face recognition algorithms is sent to face tracking thread;
Face tracking thread at the appointed time, preferably conforms to desired human face target, is sent to candid photograph thread.Capture line
Journey receives candid photograph task, corresponding picture in JPEG queue is matched by the frame number in face information, further according to face information
In face location intercept face picture.
It is irradiated on sensor cover after optical filter filters in one of the embodiments,.
In one of the embodiments, video processing subsystem processing include automatically track white balance, camera lens shade,
Gray scale, acutance, automatic exposure and noise reduction.
The encoder is H264 encoder in one of the embodiments,.
In " receiving code stream in one of the embodiments, and be provided out code stream broadcasting service ", the code stream is H264 code
Stream.
Flv server and rtsp server reception H264 code stream is provided out code stream and broadcasts in one of the embodiments,
The service of putting.
It uploads onto the server and is further processed after the entire candid photograph process of completion in one of the embodiments,.
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
The step of computer program, the processor realizes any one the method when executing described program.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
The step of any one the method.
A kind of processor, the processor is for running program, wherein described program executes described in any item when running
Method.
Beneficial effects of the present invention:
The present invention first hardware end realize video image parsing, target detection tracking (an equipment same picture is most
It is support 10 Face datections tracking more), luminance compensation is adjustable, face characteristic extracts etc. so that network bandwidth consumption is reduced, lead to
Line efficiency significantly improves, and can support higher concurrent, and batch passenger flow biggish industry higher to requirement of real-time has obvious side
It helps.Meanwhile video camera and algorithm chip become integral type from split type by the present invention, more compact, very good solution complexity
The installation question of environment.
Refering to a concrete application scene of the invention is described below:
Hardware:
If Fig. 1 is irradiated on Sensor (sensor) face after extraneous light passes through camera lens after optical filter filters,
The light conducted from camera lens is converted to electric signal by Sensor, then the AD conversion for passing through inside is digital signal.Image
Signal passes through VI (video input module), handled using VPSS (video processing subsystem) (AWB (automatically tracking white balance),
Lens shading (camera lens shade), gamma (gray scale), sharpness (acutance), AE (automatic exposure), de-noise (drop
Make an uproar)) afterwards export YUV (color difference components) format data.
FrameProducer (producer) is responsible for receiving the reception and distribution of yuv data:
1, FrameProducer fills frame number (cumulative) in yuv data and issues VO (Video Output Modules), transfers to
Face recognition algorithms are handled.
2, FrameProducer fills frame number (cumulative) in yuv data and is stored in YUVFrameList (image is slow
Deposit queue).Processing result for synchronized video frames and face recognition algorithms.
3, yuv data is sent MJPEG encoder by FrameProducer, and the frame sequence that adds up in MJPEG receiving thread
Number, yuv data and MJPEG frame number are synchronized with this.
FrameConsumer (consumer) is responsible for receiving and handling the result of face recognition algorithms:
1, FrameConsumer receives the result (including corresponding frame number) of face recognition algorithms, and passes through
YUVFrameList matches corresponding video frame, and face location is plotted in YUV image, H264 encoder is then sent to,
Flv server and rtsp server receive H264 code stream and are provided out code stream broadcasting service.
2, the result of face recognition algorithms is sent to TrackingThead (face tracking thread) by FrameConsumer.
TrackingThead (face tracking thread) at the appointed time, preferably conforms to desired human face target, is sent to
Capture thread.It captures thread and receives candid photograph task, by right in frame number matching JPEGRQ (JPEG queue) in face information
The picture answered intercepts face picture further according to the face location in face information.It is uploaded to after completing entire candid photograph process in this way
Server is further processed.
Software:
1, preprocessing rule is configured according to various usage scenarios from the background, to reduce the resource consumption that interface calls frequency.
2, carrying out face character detection again (can define face character requirement for every equipment, in the good field of condition
It improves and requires under scape, otherwise suitably lower the requirement).It detects underproof photo to keep records of, does not do business processing;Detection is qualified
Photo carry out face alignment again.
3, faceid is determined according to comparison result, while is compared with the time in faceid last time to the shop, if
Time phase difference is no more than the duplicate removal time, it is believed that is not record passenger flow again with primary visiting;Otherwise by satisfactory data
(faceid, gender, age, mood etc.) is updated into passenger flow table, is realized passenger flow duplicate removal, is reached accurate statistics.
Embodiment described above is only to absolutely prove preferred embodiment that is of the invention and being lifted, protection model of the invention
It encloses without being limited thereto.Those skilled in the art's made equivalent substitute or transformation on the basis of the present invention, in the present invention
Protection scope within.Protection scope of the present invention is subject to claims.
Claims (10)
1. a kind of accurate objective group analysis method based on edge calculations technology characterized by comprising extraneous light passes through camera lens
Afterwards, it is irradiated on sensor cover, the light conducted from camera lens is converted to electric signal by sensor, then passes through internal AD
Be converted to digital signal;Picture signal exports color difference point by video input module after handling using video processing subsystem
Measure the data of format;
The producer is responsible for receiving the reception and distribution of color difference components formatted data:
The producer fills frame number (cumulative) in color difference components data and issues Video Output Modules, transfers to face recognition algorithms
It is handled;
The producer fills frame number (cumulative) in color difference components data and is stored in image buffer storage queue;For synchronized video frames
With the processing result of face recognition algorithms;
Color difference components data are sent MJPEG encoder by the producer, and the frame number that adds up in MJPEG receiving thread, same with this
Walk color difference components data and MJPEG frame number;
Consumer is responsible for receiving and handling the result of face recognition algorithms:
Consumer receives the result (including corresponding frame number) of face recognition algorithms, and is corresponded to by image buffer storage queue matching
Video frame, face location is plotted in color difference components image, is then sent to encoder, code stream is received and is provided out code stream
Play service;
The result of face recognition algorithms is sent to face tracking thread.
Face tracking thread at the appointed time, preferably conforms to desired human face target, is sent to candid photograph thread.Thread is captured to receive
To the task of candid photograph, corresponding picture in JPEG queue is matched by the frame number in face information, further according in face information
Face location intercepts face picture.
2. the accurate objective group analysis method based on edge calculations technology as described in claim 1, which is characterized in that by filtering
It is irradiated on sensor cover after piece filtering.
3. the accurate objective group analysis method based on edge calculations technology as described in claim 1, which is characterized in that the video
Processing subsystem processing includes automatically tracking white balance, camera lens shade, gray scale, acutance, automatic exposure and noise reduction.
4. the accurate objective group analysis method based on edge calculations technology as described in claim 1, which is characterized in that the coding
Device is H264 encoder.
5. the accurate objective group analysis method based on edge calculations technology as described in claim 1, which is characterized in that " receive code
Stream is provided out code stream and plays service " in, the code stream is H264 code stream.
6. the accurate objective group analysis method based on edge calculations technology as described in claim 1, which is characterized in that flv
Server and rtsp server receives H264 code stream and is provided out code stream broadcasting service.
7. the accurate objective group analysis method based on edge calculations technology as described in claim 1, which is characterized in that complete entire
It uploads onto the server and is further processed after candid photograph process.
8. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any one of claims 1 to 7 the method when executing described program
Step.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claims 1 to 7 the method is realized when row.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit requires 1 to 7 described in any item methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910609505.0A CN110321857B (en) | 2019-07-08 | 2019-07-08 | Accurate passenger group analysis method based on edge calculation technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910609505.0A CN110321857B (en) | 2019-07-08 | 2019-07-08 | Accurate passenger group analysis method based on edge calculation technology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110321857A true CN110321857A (en) | 2019-10-11 |
CN110321857B CN110321857B (en) | 2021-08-17 |
Family
ID=68123081
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910609505.0A Active CN110321857B (en) | 2019-07-08 | 2019-07-08 | Accurate passenger group analysis method based on edge calculation technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110321857B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110766474A (en) * | 2019-10-30 | 2020-02-07 | 浙江易时科技股份有限公司 | Sales exhibition room passenger flow batch statistics based on face recognition technology |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7665113B1 (en) * | 2007-05-24 | 2010-02-16 | TrueSentry, Inc. | Rate adaptive video transmission and synchronization system |
CN103034841A (en) * | 2012-12-03 | 2013-04-10 | Tcl集团股份有限公司 | Face tracking method and face tracking system |
US20140241426A1 (en) * | 2012-02-22 | 2014-08-28 | Adobe Systems Incorporated | Interleaved video streams |
CN105488478A (en) * | 2015-12-02 | 2016-04-13 | 深圳市商汤科技有限公司 | Face recognition system and method |
EP3098755A1 (en) * | 2015-05-29 | 2016-11-30 | Accenture Global Services Limited | Local caching for object recognition |
CN107645673A (en) * | 2017-08-29 | 2018-01-30 | 湖北航天技术研究院总体设计所 | A kind of remote measurement image real-time decoding unit |
CN108491822A (en) * | 2018-04-02 | 2018-09-04 | 杭州高创电子科技有限公司 | A kind of Face datection De-weight method based on the limited caching of embedded device |
CN108710856A (en) * | 2018-05-22 | 2018-10-26 | 河南亚视软件技术有限公司 | A kind of face identification method based on video flowing |
CN109086919A (en) * | 2018-07-17 | 2018-12-25 | 新华三云计算技术有限公司 | A kind of sight spot route planning method, device, system and electronic equipment |
CN109218731A (en) * | 2017-06-30 | 2019-01-15 | 腾讯科技(深圳)有限公司 | The throwing screen method, apparatus and system of mobile device |
CN109492536A (en) * | 2018-10-12 | 2019-03-19 | 大唐高鸿信息通信研究院(义乌)有限公司 | A kind of face identification method and system based on 5G framework |
CN109522853A (en) * | 2018-11-22 | 2019-03-26 | 湖南众智君赢科技有限公司 | Face datection and searching method towards monitor video |
CN109657588A (en) * | 2018-12-11 | 2019-04-19 | 上海工业自动化仪表研究院有限公司 | Intelligent edge calculations built-in terminal based on video identification |
CN109672751A (en) * | 2019-01-15 | 2019-04-23 | 特斯联(北京)科技有限公司 | A kind of wisdom population statistical method and system based on edge calculations |
-
2019
- 2019-07-08 CN CN201910609505.0A patent/CN110321857B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7665113B1 (en) * | 2007-05-24 | 2010-02-16 | TrueSentry, Inc. | Rate adaptive video transmission and synchronization system |
US20140241426A1 (en) * | 2012-02-22 | 2014-08-28 | Adobe Systems Incorporated | Interleaved video streams |
CN103034841A (en) * | 2012-12-03 | 2013-04-10 | Tcl集团股份有限公司 | Face tracking method and face tracking system |
EP3098755A1 (en) * | 2015-05-29 | 2016-11-30 | Accenture Global Services Limited | Local caching for object recognition |
CN105488478A (en) * | 2015-12-02 | 2016-04-13 | 深圳市商汤科技有限公司 | Face recognition system and method |
CN109218731A (en) * | 2017-06-30 | 2019-01-15 | 腾讯科技(深圳)有限公司 | The throwing screen method, apparatus and system of mobile device |
CN107645673A (en) * | 2017-08-29 | 2018-01-30 | 湖北航天技术研究院总体设计所 | A kind of remote measurement image real-time decoding unit |
CN108491822A (en) * | 2018-04-02 | 2018-09-04 | 杭州高创电子科技有限公司 | A kind of Face datection De-weight method based on the limited caching of embedded device |
CN108710856A (en) * | 2018-05-22 | 2018-10-26 | 河南亚视软件技术有限公司 | A kind of face identification method based on video flowing |
CN109086919A (en) * | 2018-07-17 | 2018-12-25 | 新华三云计算技术有限公司 | A kind of sight spot route planning method, device, system and electronic equipment |
CN109492536A (en) * | 2018-10-12 | 2019-03-19 | 大唐高鸿信息通信研究院(义乌)有限公司 | A kind of face identification method and system based on 5G framework |
CN109522853A (en) * | 2018-11-22 | 2019-03-26 | 湖南众智君赢科技有限公司 | Face datection and searching method towards monitor video |
CN109657588A (en) * | 2018-12-11 | 2019-04-19 | 上海工业自动化仪表研究院有限公司 | Intelligent edge calculations built-in terminal based on video identification |
CN109672751A (en) * | 2019-01-15 | 2019-04-23 | 特斯联(北京)科技有限公司 | A kind of wisdom population statistical method and system based on edge calculations |
Non-Patent Citations (5)
Title |
---|
XUAN QI 等: "IoT Edge Device Based Key Frame Extraction for Face in Video Recognition", 《2018 18TH IEEE/ACM INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND GRID COMPUTING》 * |
YUEJUN CHEN 等: "design and implementation of video analytics system based on edge computing", 《2018 INTERNATIONAL CONFERENCE ON CYBER-ENABLED DISTRIBUTED COMPUTING AND KNOWLEDGE DISCOVERY》 * |
史天运 等: "铁路智能客运车站系统总体设计及评价", 《铁路计算机应用》 * |
王浩先 : "边缘计算助力大数据侦查", 《中国公共安全》 * |
蔡成飞: "基于人脸识别技术和边缘计算技术的智能系统研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110766474A (en) * | 2019-10-30 | 2020-02-07 | 浙江易时科技股份有限公司 | Sales exhibition room passenger flow batch statistics based on face recognition technology |
Also Published As
Publication number | Publication date |
---|---|
CN110321857B (en) | 2021-08-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TW202011263A (en) | System and method for performing image processing based on a damage assessment image judgement model | |
US20240106973A1 (en) | Optimized video review using motion recap images | |
US20230334890A1 (en) | Pedestrian re-identification method and device | |
CN111160202B (en) | Identity verification method, device, equipment and storage medium based on AR equipment | |
CN102547301A (en) | System and method for processing image data using an image signal processor | |
CN111325051A (en) | Face recognition method and device based on face image ROI selection | |
CN108369651A (en) | Information extraction is carried out using image data | |
WO2022213540A1 (en) | Object detecting, attribute identifying and tracking method and system | |
CN113469920B (en) | Image processing method and system for intelligent equipment management | |
CN113784171A (en) | Video data processing method, device, computer system and readable storage medium | |
CN110321857A (en) | Accurate objective group analysis method based on edge calculations technology | |
CN110617670A (en) | Unmanned refrigerator based on image recognition and recognition method thereof | |
CN112417989A (en) | Invigilator violation identification method and system | |
CN113807327B (en) | Deep learning side face image processing method and system based on light compensation | |
WO2023029559A1 (en) | Data processing method and apparatus | |
CN110321782A (en) | A kind of system detecting characteristics of human body's signal | |
CN115631402A (en) | AI algorithm service platform construction method suitable for intelligent breeding | |
CN110148074A (en) | A kind of method, apparatus and system for picking children for campus | |
CN106908455A (en) | IMAQ terminal, glass surface defects on-line detecting system and method | |
KR102567823B1 (en) | Youtube upload time analysis system | |
CN112488933A (en) | Video detail enhancement method and device, mobile terminal and storage medium | |
CN112215174A (en) | Sanitation vehicle state analysis method based on computer vision | |
CN112101331B (en) | Security video fusion scheduling method and device | |
CN113762156B (en) | Video data processing method, device and storage medium | |
CN114898410B (en) | Cross-resolution pedestrian re-identification method based on wavelet transformation |
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 | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Accurate customer group analysis method based on edge computing technology Effective date of registration: 20220715 Granted publication date: 20210817 Pledgee: Bank of Suzhou Co.,Ltd. Shishan road sub branch Pledgor: SUZHOU WANDIANZHANG NETWORK TECHNOLOGY Co.,Ltd. Registration number: Y2022320010387 |