CN107729804A - A kind of people flow rate statistical method and device based on garment ornament - Google Patents
A kind of people flow rate statistical method and device based on garment ornament Download PDFInfo
- Publication number
- CN107729804A CN107729804A CN201710774937.8A CN201710774937A CN107729804A CN 107729804 A CN107729804 A CN 107729804A CN 201710774937 A CN201710774937 A CN 201710774937A CN 107729804 A CN107729804 A CN 107729804A
- Authority
- CN
- China
- Prior art keywords
- image
- people
- ornament
- garment
- storehouse
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of people flow rate statistical method based on garment ornament, comprise the following steps:Model construction step:Build dress form identification storehouse;Image acquisition step:Obtain the image information in predeterminable area;Data statistics step:Identify that storehouse is compared to obtain stream of people's statistics with image information according to dress form.The invention also discloses a kind of electronic equipment, computer-readable recording medium and people flow rate statistical device based on garment ornament.When the present invention carries out statistics flow of the people, it is not necessary to analyzed, can be avoided because dispute caused by privacy infringement using the face image data of public place.
Description
Technical field
The present invention relates to image identification technical field, more particularly to a kind of people flow rate statistical method based on garment ornament and
Device.
Background technology
At present, as information system management is increasingly taken seriously, the public area such as large-scale business is super, scenic spot, airport, harbour, passenger station
Domain, the flow real-time statistics that all can targetedly conduct oneself, stream of people's flow direction and distributional analysis, degree of crowding estimation, crowd characteristic point
The demography statisticss of attributes such as analysis;And it is each to carry out commercial planning and regional development plan customization etc. according to flow of the people and demography attribute
The business demand of aspect also increases increasingly.
The simple supervision equipment and artificial judgement processing of relying on far can not meet to carry out people flow rate statistical analysis
The needs efficiently managed, how efficiently Computer Vision to be divided so as to carry out flow of the people data statistics exactly and feature
Analysis, it has also become improve the horizontal key of public domain information system management.
The content of the invention
For overcome the deficiencies in the prior art, an object of the present invention is a kind of flow of the people system based on garment ornament
Meter method, it can solve the technical problem of people's Data stream statistics.
The second object of the present invention is electronic equipment, and it can solve the technical problem of people's Data stream statistics.
The third object of the present invention is a kind of computer-readable recording medium, and it can solve the technology of people's Data stream statistics
Problem.
The fourth object of the present invention is a kind of people flow rate statistical device based on garment ornament, and it can solve people's flow data
The technical problem of statistics.
An object of the present invention adopts the following technical scheme that realization:
A kind of people flow rate statistical method based on garment ornament, comprises the following steps:
Model construction step:Build dress form identification storehouse;
Image acquisition step:Obtain the image information in predeterminable area;
Data statistics step:Identify that storehouse is compared to obtain stream of people's statistics with image information according to dress form.
Further, the model construction step specifically includes following sub-step:
Model preprocessing step:The garment image of various styles to getting pre-processes;
Characteristic extraction step:Feature extraction is carried out to obtain clothes training to the garment image of pretreated various styles
Collection;
Model establishment step:Extraction standard template identifies storehouse to establish dress form from clothes training set.
Further, image preprocessing step is also included before data statistics step after image acquisition step:To figure
As information is pre-processed.
Further, it is further comprising the steps of after image preprocessing step:
Dress ornament obtaining step:Obtain the dress ornament information in image information;
Image segmentation step:Image segmentation is carried out to dress ornament information, and is divided into the grid spaces of predetermined number;
Feature calculation step:Calculate the characteristic vector in each grid, the points in this feature vector=each grid with
The ratio between total points of dress ornament information.
Further, the data statistics step specifically includes following sub-step:
Aspect ratio is to step:The dress ornament information in image information is obtained, and by dress ornament information and dress form identification storehouse
Each characteristic vector be compared;
Judgment step:When detecting that its similarity reaches preset value, then judge it for a people;
As a result obtaining step:Storehouse is identified according to dress form to obtain stream of people's statistics.
Further, in the judgment step, the preset value is 80%.
The second object of the present invention adopts the following technical scheme that realization:
A kind of electronic equipment, including memory, processor and storage can be run on a memory and on a processor
Computer program, following steps are realized during the computing device described program:
Model construction step:Build dress form identification storehouse;
Image acquisition step:Obtain the image information in predeterminable area;
Data statistics step:Identify that storehouse is compared to obtain stream of people's statistics with image information according to dress form.
Further, the model construction step specifically includes following sub-step:
Model preprocessing step:The garment image of various styles to getting pre-processes;
Characteristic extraction step:Feature extraction is carried out to obtain clothes training to the garment image of pretreated various styles
Collection;
Model establishment step:Extraction standard template identifies storehouse to establish dress form from clothes training set.
The third object of the present invention adopts the following technical scheme that realization:
A kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that:The computer program
The as above method described by any one is realized when being executed by processor.
The fourth object of the present invention adopts the following technical scheme that realization:
A kind of people flow rate statistical device based on garment ornament, including with lower module:
Model construction module:For building dress form identification storehouse;
Image collection module:For obtaining the image information in predeterminable area;
Data statistics module:For identifying that storehouse is compared to obtain stream of people's statistical number with image information according to dress form
According to.
Compared with prior art, the beneficial effects of the present invention are:
When the present invention carries out statistics flow of the people, it is not necessary to analyzed using the face image data of public place, can be with
Avoid because dispute caused by privacy infringement.
Brief description of the drawings
Fig. 1 is the flow chart of the people flow rate statistical method based on garment ornament of the present invention;
Fig. 2 is the structure chart of the people flow rate statistical device based on garment ornament of the present invention.
Embodiment
Below, with reference to accompanying drawing and embodiment, the present invention is described further, it is necessary to which explanation is, not
Under the premise of afoul, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
Embodiment one:
As shown in figure 1, the invention provides a kind of people flow rate statistical method based on garment ornament, comprise the following steps:
S1:Build dress form identification storehouse;Step S1 specifically includes following sub-step:
S11:The garment image of various styles to getting pre-processes;To the garment image of the various styles of acquisition
Pre-processed, by removing the preprocessing process such as noise and noise spot, normalization, so that follow-up processing is preferably carried out.
S12:Feature extraction is carried out to obtain clothes training set to the garment image of pretreated various styles;To pretreatment
The garment image of each style dressing afterwards carries out feature extraction, according to the color of the clothing space density of different styles, shape etc.
Arrangement situation feature, dress ornament image is divided into 5*5 25 grid spaces, and the points calculated in each grid are always counted with clothes
The ratio between, to obtain 25 dimensional feature vectors.
S13:Extraction standard template identifies storehouse to establish dress form from clothes training set.Recognition training, from training set
Standard form is extracted in each clothes, establishes standard feature storehouse.Every kind of clothes have hundreds of standard forms, by pretreatment and
After feature extraction, need to indicate each configuration item of clothing by the characteristic vector of each configuration item of clothing of training set deposit file, during training
Right value, then complete the foundation in dress form storehouse identification storehouse.
Pass through the clothes photo that internet gathers a large amount of all ages and classes, the various styles of personage of sex are worn clothes, it is first determined
The style of clothes, the clothes in picture is selected to establish identification model by machine learning frame;Meanwhile various styles are combined
Clothes labelled, such as Women's Suits, professional men's clothing, old women's dress, girl's wear, dirndl, student's women's dress, pass through mark
The type of label can carry out statistical analysis to statistical regions crowd characteristic;
S2:Obtain the image information in predeterminable area;Multiple cameras are provided with, being separately positioned on needs to count flow of the people
Public place everywhere, for stream of people's video image in each region of real-time capture.Also include step S21 upon step s 2:
Image information is pre-processed;The regional flow of the people video image extraction key frame to be counted that camera is obtained, it is right
Image is removed the pretreatment such as noise and noise spot, normalization, so that the later stage carries out aspect ratio pair;
S22:Obtain the dress ornament information in image information;It is more personal due to including in each image information, everyone
There will be corresponding dress ornament, so when being identified, first pass through the dress ornament information in identification image information, then come again
Dress ornament information is further judged to obtain the statistics of people's stream attribute information;
S23:Image segmentation is carried out to dress ornament information, and is divided into the grid spaces of predetermined number;
S24:Calculate the characteristic vector in each grid, the points and dress ornament information in this feature vector=each grid are total
The ratio between points.
S3:Identify that storehouse is compared to obtain stream of people's statistics with image information according to dress form.The step S3
Specifically include following sub-step:
S31:The dress ornament information in image information is obtained, and dress ornament information and dress form are identified to each feature in storehouse
Vector is compared;
S32:When detecting that its similarity reaches preset value, then judge it for a people;The preset value is 80%;
S33:Storehouse is identified according to dress form to count ascribed characteristics of population feature.It is right according to clothes fashion, color characteristics of combination
Pretreated video image to be counted carries out feature extraction, by each clothes to be prestored in the characteristic vector and system of extraction
Characteristic vector compares, and when similarity reaches more than 80%, then regards as one group of clothes, you can be judged as having a people.Will
The dress ornament recognition result of video image carries out statistics calculating, obtains people flow rate statistical result.According to the combination tag of each clothes,
Count the ascribed characteristics of population feature of the region stream of people.
By camera obtain regional flow of the people video image extraction key frame to be counted, pretreatment, feature extraction,
Compared with each garment features in identification model, judge the quantity of the style combination of the clothes included in image, so as to
To the quantity of the people in the image.
Due in the modelling phase, not only having carried out model foundation to dress ornament template, also having established and aspect of model phase
Corresponding label information, more extensive stream of people's attributive character can be counted by the label information, the region can be got
The stream of people attribute type, such as, be that working clan is more in this region, or student is more, or old man is more, be boy student it is more or
Schoolgirl is more, and it can be distinguished according to the different periods so that the data got more universal, more
Comprehensively;The ascribed characteristics of population feature of more horn of plenty is provided, certain data supporting is provided for the corresponding decision of government or company.
The present invention in the gateway in the places such as the super, passenger station of large-scale business or main Shang Qu arterial highways by setting camera to obtain
The video image of pedestrian, carried out first by the image of clothing for a large amount of various dressing personages for learning to obtain from internet in advance anti-
Refreshment is practiced, and establishes identification model.When counting flow of the people, identification judge module analyzes the crowd that each camera head monitor region obtains
Video image, judge to obtain the number of combinations result of various clothes dresses by matching identification model.Statistical analysis module is final
It will identify that the clothes number of combinations judged is added up, statistics recognition result and the corresponding demography attribute for obtaining flow of the people are special
Levy statistical result.
The present invention is by video acquisition flow of the people image information, according to the different difference different peoples of everyone garment
Group, by the statistics of clothes quantity, judge the quantity of crowd, and further according to information acquisitions such as the color of clothes, styles
More demography statistics of attributes information, reliable and abundant data basis for estimation is provided for business decision and planning demand.This
During invention statistics flow of the people, it is not necessary to analyzed, can be avoided because privacy is invaded using the face image data of public place
Dispute caused by power, there is certain commercial application value.
Embodiment two
Embodiment two discloses a kind of electronic equipment, and the electronic equipment includes processor, memory and program, wherein locating
One or more can be used by managing device and memory, and program is stored in memory, and is configured to by computing device,
During the computing device program, the people flow rate statistical method based on garment ornament of embodiment one is realized.The electronic equipment can be with
It is a series of electronic equipment of mobile phone, computer, tablet personal computer etc..
Embodiment three
Embodiment three discloses a kind of readable computer-readable storage medium, and the storage medium is used for storage program, and should
When program is executed by processor, the people flow rate statistical method based on garment ornament of embodiment one is realized.
Example IV
As shown in Fig. 2 present embodiment discloses a kind of people flow rate statistical device based on garment ornament, including following mould
Block:
Model construction module:For building dress form identification storehouse;
Image collection module:For obtaining the image information in predeterminable area;
Data statistics module:For identifying that storehouse is compared to obtain stream of people's statistical number with image information according to dress form
According to.
Above-mentioned embodiment is only the preferred embodiment of the present invention, it is impossible to the scope of protection of the invention is limited with this,
The change and replacement for any unsubstantiality that those skilled in the art is done on the basis of the present invention belong to institute of the present invention
Claimed scope.
Claims (10)
- A kind of 1. people flow rate statistical method based on garment ornament, it is characterised in that comprise the following steps:Model construction step:Build dress form identification storehouse;Image acquisition step:Obtain the image information in predeterminable area;Data statistics step:Identify that storehouse is compared to obtain stream of people's statistics with image information according to dress form.
- 2. the people flow rate statistical method based on garment ornament as claimed in claim 1, it is characterised in that the model construction step Suddenly following sub-step is specifically included:Model preprocessing step:The garment image of various styles to getting pre-processes;Characteristic extraction step:Feature extraction is carried out to obtain clothes training set to the garment image of pretreated various styles;Model establishment step:Extraction standard template identifies storehouse to establish dress form from clothes training set.
- 3. the people flow rate statistical method based on garment ornament as claimed in claim 1, it is characterised in that in image acquisition step Also include image preprocessing step before data statistics step afterwards:Image information is pre-processed.
- 4. the people flow rate statistical method based on garment ornament as claimed in claim 3, it is characterised in that walked in image preprocessing It is further comprising the steps of after rapid:Dress ornament obtaining step:Obtain the dress ornament information in image information;Image segmentation step:Image segmentation is carried out to dress ornament information, and is divided into the grid spaces of predetermined number;Feature calculation step:Calculate the characteristic vector in each grid, points and dress ornament in this feature vector=each grid The ratio between total points of information.
- 5. the people flow rate statistical method based on garment ornament as described in claim 1 or 4, it is characterised in that the data system Meter step specifically includes following sub-step:Aspect ratio is to step:Obtain image information in dress ornament information, and by dress ornament information and dress form identification storehouse in it is each Individual characteristic vector is compared;Judgment step:When detecting that its similarity reaches preset value, then judge it for a people;As a result obtaining step:Storehouse is identified according to dress form to obtain stream of people's statistics.
- 6. the people flow rate statistical method based on garment ornament as claimed in claim 5, it is characterised in that the judgment step In, the preset value is 80%.
- 7. a kind of electronic equipment, including memory, processor and storage are on a memory and the meter that can run on a processor Calculation machine program, it is characterised in that realize following steps during the computing device described program:Model construction step:Build dress form identification storehouse;Image acquisition step:Obtain the image information in predeterminable area;Data statistics step:Identify that storehouse is compared to obtain stream of people's statistics with image information according to dress form.
- 8. electronic equipment as claimed in claim 7, it is characterised in that the model construction step specifically includes following sub-step Suddenly:Model preprocessing step:The garment image of various styles to getting pre-processes;Characteristic extraction step:Feature extraction is carried out to obtain clothes training set to the garment image of pretreated various styles;Model establishment step:Extraction standard template identifies storehouse to establish dress form from clothes training set.
- 9. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that:The computer program quilt Method as claimed in any one of claims 1 to 6 is realized during computing device.
- 10. a kind of people flow rate statistical device based on garment ornament, it is characterised in that including with lower module:Model construction module:For building dress form identification storehouse;Image collection module:For obtaining the image information in predeterminable area;Data statistics module:For identifying that storehouse is compared to obtain stream of people's statistics with image information according to dress form.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710774937.8A CN107729804A (en) | 2017-08-31 | 2017-08-31 | A kind of people flow rate statistical method and device based on garment ornament |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710774937.8A CN107729804A (en) | 2017-08-31 | 2017-08-31 | A kind of people flow rate statistical method and device based on garment ornament |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107729804A true CN107729804A (en) | 2018-02-23 |
Family
ID=61205604
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710774937.8A Pending CN107729804A (en) | 2017-08-31 | 2017-08-31 | A kind of people flow rate statistical method and device based on garment ornament |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107729804A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108898103A (en) * | 2018-06-29 | 2018-11-27 | 深圳市宝视达广告控股有限公司 | A kind of acquiring and processing method, device and server to shop consumer information and a kind of storage medium |
CN108985298A (en) * | 2018-06-19 | 2018-12-11 | 浙江大学 | A kind of human body clothing dividing method based on semantic consistency |
CN109165842A (en) * | 2018-08-21 | 2019-01-08 | 北京深瞐科技有限公司 | A kind of capital construction temperature index statistical method and device |
CN110262594A (en) * | 2019-04-30 | 2019-09-20 | 广州富港万嘉智能科技有限公司 | A kind of mobile focus control system, method and storage medium |
CN113076775A (en) * | 2020-01-03 | 2021-07-06 | 上海依图网络科技有限公司 | Preset clothing detection method, device, chip and computer readable storage medium |
CN113454664A (en) * | 2019-03-08 | 2021-09-28 | 本田技研工业株式会社 | Information processing system, program, and information processing method |
US11651609B2 (en) | 2020-06-10 | 2023-05-16 | Here Global B.V. | Method, apparatus, and system for mapping based on a detected pedestrian type |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101325690A (en) * | 2007-06-12 | 2008-12-17 | 上海正电科技发展有限公司 | Method and system for detecting human flow analysis and crowd accumulation process of monitoring video flow |
CN102542289A (en) * | 2011-12-16 | 2012-07-04 | 重庆邮电大学 | Pedestrian volume statistical method based on plurality of Gaussian counting models |
CN103198327A (en) * | 2013-04-25 | 2013-07-10 | 重庆师范大学 | Open type scene-oriented entrance and exit population counting method and device |
CN105631413A (en) * | 2015-12-23 | 2016-06-01 | 中通服公众信息产业股份有限公司 | Cross-scene pedestrian searching method based on depth learning |
CN106462881A (en) * | 2014-05-19 | 2017-02-22 | 霍斯顿分析有限公司 | System and method for determining demographic information |
CN106951832A (en) * | 2017-02-28 | 2017-07-14 | 广东数相智能科技有限公司 | A kind of verification method and device based on Handwritten Digits Recognition |
-
2017
- 2017-08-31 CN CN201710774937.8A patent/CN107729804A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101325690A (en) * | 2007-06-12 | 2008-12-17 | 上海正电科技发展有限公司 | Method and system for detecting human flow analysis and crowd accumulation process of monitoring video flow |
CN102542289A (en) * | 2011-12-16 | 2012-07-04 | 重庆邮电大学 | Pedestrian volume statistical method based on plurality of Gaussian counting models |
CN103198327A (en) * | 2013-04-25 | 2013-07-10 | 重庆师范大学 | Open type scene-oriented entrance and exit population counting method and device |
CN106462881A (en) * | 2014-05-19 | 2017-02-22 | 霍斯顿分析有限公司 | System and method for determining demographic information |
CN105631413A (en) * | 2015-12-23 | 2016-06-01 | 中通服公众信息产业股份有限公司 | Cross-scene pedestrian searching method based on depth learning |
CN106951832A (en) * | 2017-02-28 | 2017-07-14 | 广东数相智能科技有限公司 | A kind of verification method and device based on Handwritten Digits Recognition |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108985298A (en) * | 2018-06-19 | 2018-12-11 | 浙江大学 | A kind of human body clothing dividing method based on semantic consistency |
CN108985298B (en) * | 2018-06-19 | 2022-02-18 | 浙江大学 | Human body clothing segmentation method based on semantic consistency |
CN108898103A (en) * | 2018-06-29 | 2018-11-27 | 深圳市宝视达广告控股有限公司 | A kind of acquiring and processing method, device and server to shop consumer information and a kind of storage medium |
CN109165842A (en) * | 2018-08-21 | 2019-01-08 | 北京深瞐科技有限公司 | A kind of capital construction temperature index statistical method and device |
CN109165842B (en) * | 2018-08-21 | 2021-01-29 | 北京深瞐科技有限公司 | Capital construction heat index statistical method and device |
CN113454664A (en) * | 2019-03-08 | 2021-09-28 | 本田技研工业株式会社 | Information processing system, program, and information processing method |
CN110262594A (en) * | 2019-04-30 | 2019-09-20 | 广州富港万嘉智能科技有限公司 | A kind of mobile focus control system, method and storage medium |
CN113076775A (en) * | 2020-01-03 | 2021-07-06 | 上海依图网络科技有限公司 | Preset clothing detection method, device, chip and computer readable storage medium |
US11651609B2 (en) | 2020-06-10 | 2023-05-16 | Here Global B.V. | Method, apparatus, and system for mapping based on a detected pedestrian type |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107729804A (en) | A kind of people flow rate statistical method and device based on garment ornament | |
CN104091176B (en) | Portrait comparison application technology in video | |
CN107103279B (en) | Passenger flow counting method based on deep learning under vertical visual angle | |
CN104036236B (en) | A kind of face gender identification method based on multiparameter exponential weighting | |
CN109670591A (en) | A kind of training method and image matching method, device of neural network | |
CN103310444B (en) | A kind of method of the monitoring people counting based on overhead camera head | |
CN109978918A (en) | A kind of trajectory track method, apparatus and storage medium | |
CN106096577A (en) | Target tracking system in a kind of photographic head distribution map and method for tracing | |
CN110532970A (en) | Age-sex's property analysis method, system, equipment and the medium of face 2D image | |
CN101325690A (en) | Method and system for detecting human flow analysis and crowd accumulation process of monitoring video flow | |
CN109670430A (en) | A kind of face vivo identification method of the multiple Classifiers Combination based on deep learning | |
CN102298709A (en) | Energy-saving intelligent identification digital signage fused with multiple characteristics in complicated environment | |
CN107886507B (en) | A kind of salient region detecting method based on image background and spatial position | |
CN109740517A (en) | A kind of method and device of determining object to be identified | |
CN108764167A (en) | A kind of target of space time correlation recognition methods and system again | |
CN110110732B (en) | Intelligent inspection method for catering kitchen | |
CN103853794B (en) | Pedestrian retrieval method based on part association | |
CN104156729B (en) | A kind of classroom demographic method | |
CN107341445A (en) | The panorama of pedestrian target describes method and system under monitoring scene | |
CN109241847A (en) | The Oilfield Operation District safety monitoring system of view-based access control model image | |
CN107358163A (en) | Visitor's line trace statistical method, electronic equipment and storage medium based on recognition of face | |
Karpagavalli et al. | Estimating the density of the people and counting the number of people in a crowd environment for human safety | |
CN112183472A (en) | Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet | |
CN113436229A (en) | Multi-target cross-camera pedestrian trajectory path generation method | |
CN103020614A (en) | Human movement identification method based on spatio-temporal interest point detection |
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: 20180223 |
|
RJ01 | Rejection of invention patent application after publication |