CN104063253A - Method for automatic statistics of passenger flow, all-in-one machines and distributed system for automatic statistics of passenger flow - Google Patents
Method for automatic statistics of passenger flow, all-in-one machines and distributed system for automatic statistics of passenger flow Download PDFInfo
- Publication number
- CN104063253A CN104063253A CN201410321218.7A CN201410321218A CN104063253A CN 104063253 A CN104063253 A CN 104063253A CN 201410321218 A CN201410321218 A CN 201410321218A CN 104063253 A CN104063253 A CN 104063253A
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- data
- region
- automatically
- image
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method for automatic statistics of passenger flow, all-in-one machines and a distributed system for automatic statistics of the passenger flow. The method for automatic statistics of the passenger flow, the all-in-one machines and the distributed system for automatic statistics of the passenger flow have the advantages that accurate statistics is achieved, color information is not needed, and the influence of the factors such as the hair condition and color are avoided; the all-in-one machines can be installed conveniently and can be used flexibly; data of all the all-in-one machines of the distributed system are transmitted to a center server through a network, and thus data can be managed, inquired and mined more effectively; meanwhile, due to the fact that the caching type transmission mechanism is used, independent operation of each all-in-one machine can not be influenced.
Description
Technical field
The present invention relates to passenger flow statistics technical field, relate in particular to a kind of passenger flow method for automatically counting, all-in-one and distributed system thereof.
Background technology
The volume of the flow of passengers is the indispensable data in management and decision aspect, place, public place such as megastore, shopping center, chain store, airport, station, museum, exhibition center, also be an important commercial market research means, can provide the reference of data accurately and timely for the Operation Decision of large scale business system and integrated management.Significant for depending on the industry of the volume of the flow of passengers, research volume of the flow of passengers rule, can increase sales opportunnities, changes beholder into shopper, excavates to greatest extent the sales potential in market, increases profit.The volume of the flow of passengers is important measurement instrument, by this quantized data accurately, not only can help businessman to grasp the situation that market, shopping center, museum etc. are moving, but also can utilize these high-precision data, effectively organize operation work.But also there is many deficiencies in traditional passenger flow statistical method: the situation that when one, the passenger flow statistics based on infrared electronic technology cannot be distinguished many people and passes in and out, mutual is blocked.Two, the existing passenger flow statistical method precision based on video is low, uses hair color as statistical nature, causes being branded as, the miscount such as bald head, hair dyeing.And other passenger flow statistical system all needs to be connected with computer debugging at present substantially, install, dispose, safeguard all inconvenient.
Summary of the invention
The object of the invention is to, by a kind of passenger flow method for automatically counting, all-in-one and distributed system thereof, solve the problem that above background technology part is mentioned.
For reaching this object, the present invention by the following technical solutions:
A kind of passenger flow method for automatically counting, it comprises the steps:
S101, video sensor collection are by the video image of statistical regions;
S102, image pre-service: first described video image is carried out to gray processing, then use Gaussian smoothing, remove noise, regeneration image pyramid;
S103, background subtraction: by the background subtraction algorithm VIBE algorithm based on statistics, obtain foreground image; Meanwhile, by opening operation, remove the noise prospect that does not meet human body condition in image;
S104, recognition and tracking based on block: the foreground area of automatic analysis image, and judge which region and belong to human body, simultaneously, sequence frame is carried out to the tracking judgement based on sequential, and according to the human body motion track of following the tracks of, judge that people is by the turnover state of statistical regions, and upgrade the total number of persons data of turnover;
S105, carry out human body quantity statistics based on human experience data, obtain final passenger flow statistics result.
Especially, described step S104 specifically comprises:
S1041, according to connectivity, foreground segmentation is become to several regions, and filters the region falling into outside predeterminable area magnitude range;
The center B of S1042, the center of gravity A that asks for each region and boundary rectangle, the center C that the center of getting A and B is region;
S1043, for t frame region, in the time of t+1 frame, ask in each region V in t frame with the t frame of its overlapping region maximum in regional ensemble S, set a threshold value D, will be less than in the regional ensemble S of D, obtain the set T of several elements;
S1044, use Kalman filtering find the region U that meets the characteristics of motion most in set T, and U is the region that region V traces in the time of the t moment.
Especially, described step S105 specifically comprises:
S1051, according to human experience data, foundation characteristics of human body's including shoulder breadth, nose shape database, wherein, the data content in database is determined by camera heights and focal length, record under differing heights, focal length camera the pixel size scope of characteristics of human body in image;
S1052, analyze time, according to concrete camera situation, the pixel size scope of inquirer's body characteristics;
S1053, according to the data that inquire, estimate passenger flow quantity by the provincial characteristics including width, highly, area, circle rate.
The invention also discloses a kind of passenger flow and automatically add up all-in-one, it comprises video sensor and single-chip microcomputer; Described video sensor is installed on by statistical regions top, for gathering by the video image of statistical regions; Described single-chip microcomputer and video sensor communication connection, for the data processing including above-mentioned steps S102 to S105, complete passenger flow statistics.
Especially, described single-chip microcomputer adopts POE mode to power.
The automatic statistical distribution formula of a kind of passenger flow system, it comprises that several above-mentioned passenger flows add up all-in-one and central server automatically; Described passenger flow is added up all-in-one automatically for obtaining the passenger flow data of present position separately, and is cached in this locality, and timing sends to central server by the mode of PUSH; Described central server and passenger flow are added up all-in-one communication connection automatically, for receiving after passenger flow data, return to a receipt and automatically add up all-in-one to passenger flow, correspondence data cached carried out to set, and described passenger flow data is carried out to analyzing and processing, for management, inquiry and the excavation of data.
Passenger flow method for automatically counting, all-in-one and distributed system tool thereof that the present invention proposes have the following advantages: one, statistics accurately: do not use colouring information, be not subject to that hair has or not, the impact of color etc.Two, the form of all-in-one is easy for installation, uses flexibly.Three, distributed system: the data of each all-in-one arrive central server by Internet Transmission, makes the management, inquiry, excavation etc. of data more effective, meanwhile, uses buffer memory transmission mechanism, can not affect each all-in-one working condition alone.
Brief description of the drawings
The passenger flow method for automatically counting process flow diagram that Fig. 1 provides for the embodiment of the present invention;
Fig. 2 adds up all-in-one block diagram automatically for the passenger flow that the embodiment of the present invention provides;
The automatic statistical distribution formula of the passenger flow system schematic that Fig. 3 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the invention will be further described.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, in accompanying drawing, only show part related to the present invention but not full content.
Please refer to shown in Fig. 1 the passenger flow method for automatically counting process flow diagram that Fig. 1 provides for the embodiment of the present invention.
In the present embodiment, passenger flow method for automatically counting specifically comprises the steps:
S101, video sensor collection are by the video image of statistical regions.
S102, image pre-service: first described video image is carried out to gray processing, then use Gaussian smoothing, remove noise, regeneration image pyramid, is convenient to speed-up computation.
S103, background subtraction: by the background subtraction algorithm VIBE algorithm based on statistics, obtain foreground image; Meanwhile, by opening operation, remove the noise prospect that does not meet human body condition in image.
By the background subtraction algorithm VIBE algorithm based on statistics, can, under the impact of the conditions such as opposing illumination, shade, obtain good foreground image.
S104, recognition and tracking based on block: the foreground area of automatic analysis image, and judge which region and belong to human body, simultaneously, sequence frame is carried out to the tracking judgement based on sequential, and according to the human body motion track of following the tracks of, judge that people is by the turnover state of statistical regions, and upgrade the total number of persons data of turnover.
Specific implementation process is as follows: S1041, according to connectivity, becomes several regions by foreground segmentation, and filter the region falling into outside predeterminable area magnitude range.The center B of S1042, the center of gravity A that asks for each region and boundary rectangle, the center C that the center of getting A and B is region.S1043, for t frame region, in the time of t+1 frame, ask in each region V in t frame with the t frame of its overlapping region maximum in regional ensemble S, set a threshold value D, will be less than in the regional ensemble S of D, obtain the set T of several elements.S1044, use Kalman filtering find the region U that meets the characteristics of motion most in set T, and U is the region that region V traces in the time of the t moment.According to above track algorithm, can be that a movement locus is estimated in each region, one in this track and predefined video sensor or two lines are judged to Intersection, can judge the behaviors such as, enter, hover in this region.
S105, carry out human body quantity statistics based on human experience data, obtain final passenger flow statistics result.
Because human body recognition and tracking algorithm can only be judged isolated crowd's exercise data.For some complex situations, for example: the connected state of setting about as handle in region between Different Individual, recognition and tracking algorithm will be failed to judge, therefore, need to be according to some human body empirical datas, such as shoulder breadth, nose shape etc., cut apart connected human region, thereby reduce the situation of failing to judge, improve accuracy of identification.Specific implementation process is as follows: S1051, according to human experience data, foundation characteristics of human body's including shoulder breadth, nose shape database, wherein, data content in database is determined by camera heights and focal length, record under differing heights, focal length camera the pixel size scope of characteristics of human body in image.S1052, analyze time, according to concrete camera situation, the pixel size scope of inquirer's body characteristics.S1053, according to the data that inquire, estimate passenger flow quantity by the provincial characteristics including width, highly, area, circle rate.
As shown in Figure 2, install for convenient, use flexibly, a kind of passenger flow that the present embodiment provides is added up all-in-one 201 automatically, passenger flow statistics algorithm solidifies in single-chip microcomputer 2012, uses netting twine or USB line to carry out data communication between single-chip microcomputer 2012 and video sensor 2011.
In the present embodiment, passenger flow is automatically added up all-in-one 201 and is specifically comprised video sensor 2011 and single-chip microcomputer 2012.Described video sensor 2011 is installed on by statistical regions top, for gathering by the video image of statistical regions.Video sensor 2011 is installed on by statistical regions top, with the visual angle of looking down, turnover statistical regions is observed.The benefit that video sensor 2011 is loaded on to top is: overlook visual angle and can farthest remove the interference of human body between mutually, and be conducive to the tracking of human body.Described single-chip microcomputer 2012 communicates to connect with video sensor 2011, for the data processing including above-mentioned steps S102 to S105, completes passenger flow statistics.The data processing method of described step S102 to S105 is encapsulated as passenger flow statistics algorithm and solidifies in single-chip microcomputer 2012.It should be noted that, video sensor 2011 and single-chip microcomputer 2012 are adopted POE mode or are passed through any power supply of 5V line mode by power supply 2013 in the present embodiment.
As shown in Figure 3, in order more effectively passenger flow statistics data to be managed, inquire about, to be excavated, the present embodiment provides the automatic statistical distribution formula of a kind of passenger flow system.
In the present embodiment, the automatic statistical distribution formula of passenger flow system specifically comprises that several above-mentioned passenger flows add up all-in-one 201 and central server 301 automatically.
Described passenger flow is added up all-in-one 201 automatically for obtaining the passenger flow data of present position separately, and is cached in this locality, and timing sends to central server 301 by the mode of PUSH.Automatically add up the isolated operation of all-in-one 201 in order not affect passenger flow, first passenger flow data will be cached in this locality, and timing sends to central server 301 by passenger flow data by the form of PUSH.
Described central server 301 is automatically added up all-in-one 201 with passenger flow and is communicated to connect, for receiving after passenger flow data, return to a receipt and automatically add up all-in-one 201 to passenger flow, correspondence data cached carried out to set, and described passenger flow data is carried out to analyzing and processing, for management, inquiry and the excavation of data.Wherein, passenger flow is automatically added up between all-in-one 201 and central server 301 and can be carried out data transmission by language such as json/xml.
In actual applications, camera is connected with the computing machine that is loaded with video analysis software by netting twine, use RTSP agreement that video image is sent to computing machine in real time, computing machine is analyzed video image: on real-time video, virtual tag goes out for the mobile region of computational activity impact; Draw personnel's quantity according to the shape analysis of movable image, and the barycentric coordinates of corresponding each mobile personnel, and implement to follow the tracks of and upgrade; The scope in region and the barycentric coordinates of mobile personnel of contrast virtual tag, to judge movable direction, speed and whether to count statistics; Thereby acquisitor flows to out movable data.Computing machine can, by the mode of network communication, be delivered to data the central server 301 on backstage, for the automatic generation of visual form with browse; Or by interface, send the data to other ERP, POS, CRM or mis system, process for them, generate the information of serving productive life.
Technical scheme tool of the present invention has the following advantages: one, statistics accurately: do not use colouring information, be not subject to that hair has or not, the impact of color etc.Two, the form of all-in-one is easy for installation, uses flexibly.Three, distributed system: the data of each all-in-one arrive central server by Internet Transmission, makes the management, inquiry, excavation etc. of data more effective, meanwhile, uses buffer memory transmission mechanism, can not affect each all-in-one working condition alone.
Note, above are only preferred embodiment of the present invention and institute's application technology principle.Skilled person in the art will appreciate that and the invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious variations, readjust and substitute and can not depart from protection scope of the present invention.Therefore, although the present invention is described in further detail by above embodiment, the present invention is not limited only to above embodiment, in the situation that not departing from the present invention's design, can also comprise more other equivalent embodiment, and scope of the present invention is determined by appended claim scope.
Claims (6)
1. a passenger flow method for automatically counting, is characterized in that, comprises the steps:
S101, video sensor collection are by the video image of statistical regions;
S102, image pre-service: first described video image is carried out to gray processing, then use Gaussian smoothing, remove noise, regeneration image pyramid;
S103, background subtraction: by the background subtraction algorithm VIBE algorithm based on statistics, obtain foreground image; Meanwhile, by opening operation, remove the noise prospect that does not meet human body condition in image;
S104, recognition and tracking based on block: the foreground area of automatic analysis image, and judge which region and belong to human body, simultaneously, sequence frame is carried out to the tracking judgement based on sequential, and according to the human body motion track of following the tracks of, judge that people is by the turnover state of statistical regions, and upgrade the total number of persons data of turnover;
S105, carry out human body quantity statistics based on human experience data, obtain final passenger flow statistics result.
2. passenger flow method for automatically counting according to claim 1, is characterized in that, described step S104 specifically comprises:
S1041, according to connectivity, foreground segmentation is become to several regions, and filters the region falling into outside predeterminable area magnitude range;
The center B of S1042, the center of gravity A that asks for each region and boundary rectangle, the center C that the center of getting A and B is region;
S1043, for t frame region, in the time of t+1 frame, ask in each region V in t frame with the t frame of its overlapping region maximum in regional ensemble S, set a threshold value D, will be less than in the regional ensemble S of D, obtain the set T of several elements;
S1044, use Kalman filtering find the region U that meets the characteristics of motion most in set T, and U is the region that region V traces in the time of the t moment.
3. according to the passenger flow method for automatically counting described in claim 1 or 2 any one, it is characterized in that, described step S105 specifically comprises:
S1051, according to human experience data, foundation characteristics of human body's including shoulder breadth, nose shape database, wherein, the data content in database is determined by camera heights and focal length, record under differing heights, focal length camera the pixel size scope of characteristics of human body in image;
S1052, analyze time, according to concrete camera situation, the pixel size scope of inquirer's body characteristics;
S1053, according to the data that inquire, estimate passenger flow quantity by the provincial characteristics including width, highly, area, circle rate.
4. passenger flow is added up an all-in-one automatically, it is characterized in that, comprises video sensor and single-chip microcomputer; Described video sensor is installed on by statistical regions top, for gathering by the video image of statistical regions; Described single-chip microcomputer and video sensor communication connection, for the data processing including claim 1 step S102 to S105, complete passenger flow statistics.
5. passenger flow according to claim 4 is added up all-in-one automatically, it is characterized in that, described single-chip microcomputer adopts POE mode to power.
6. the automatic statistical distribution formula of a passenger flow system, is characterized in that, comprises that the passenger flow described in several claims 4 adds up all-in-one and central server automatically; Described passenger flow is added up all-in-one automatically for obtaining the passenger flow data of present position separately, and is cached in this locality, and timing sends to central server by the mode of PUSH; Described central server and passenger flow are added up all-in-one communication connection automatically, for receiving after passenger flow data, return to a receipt and automatically add up all-in-one to passenger flow, correspondence data cached carried out to set, and described passenger flow data is carried out to analyzing and processing, for management, inquiry and the excavation of data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410321218.7A CN104063253A (en) | 2014-07-07 | 2014-07-07 | Method for automatic statistics of passenger flow, all-in-one machines and distributed system for automatic statistics of passenger flow |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410321218.7A CN104063253A (en) | 2014-07-07 | 2014-07-07 | Method for automatic statistics of passenger flow, all-in-one machines and distributed system for automatic statistics of passenger flow |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104063253A true CN104063253A (en) | 2014-09-24 |
Family
ID=51550977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410321218.7A Pending CN104063253A (en) | 2014-07-07 | 2014-07-07 | Method for automatic statistics of passenger flow, all-in-one machines and distributed system for automatic statistics of passenger flow |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104063253A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106850722A (en) * | 2015-12-04 | 2017-06-13 | 上海杰轩智能科技有限公司 | A kind of method that passenger flow counting information is transmitted by HTTP |
| CN109064457A (en) * | 2018-07-25 | 2018-12-21 | 哈工大机器人（合肥）国际创新研究院 | A kind of method and system that the quantity of view-based access control model is accumulative |
| CN110414361A (en) * | 2019-07-02 | 2019-11-05 | 青岛海洋科学与技术国家实验室发展中心 | Distributed machines vision data acquisition analysis method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1574986A1 (en) * | 2004-03-17 | 2005-09-14 | Norbert Prof. Dr. Link | Apparatus and method to detect persons in a zone of interest |
| 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 |
| CN101872431A (en) * | 2010-02-10 | 2010-10-27 | 杭州海康威视软件有限公司 | People flow rate statistical method and system applicable to multi-angle application scenes |
| CN102184409A (en) * | 2011-04-22 | 2011-09-14 | 北京文安科技发展有限公司 | Machine-vision-based passenger flow statistics method and system |
| US20120182390A1 (en) * | 2011-01-18 | 2012-07-19 | Disney Enterprises, Inc. | Counting system for vehicle riders |
| CN102799935A (en) * | 2012-06-21 | 2012-11-28 | 武汉烽火众智数字技术有限责任公司 | Human flow counting method based on video analysis technology |
| CN102902971A (en) * | 2012-08-31 | 2013-01-30 | 电子科技大学 | Method and system for conducting statistics on elevator visitor flow based on intelligent visual perception |
| CN103021059A (en) * | 2012-12-12 | 2013-04-03 | 天津大学 | Video-monitoring-based public transport passenger flow counting method |
| US20130182904A1 (en) * | 2012-01-17 | 2013-07-18 | Objectvideo, Inc. | System and method for video content analysis using depth sensing |
| CN103646250A (en) * | 2013-09-13 | 2014-03-19 | 魏运 | Pedestrian monitoring method and device based on distance image head and shoulder features |
-
2014
- 2014-07-07 CN CN201410321218.7A patent/CN104063253A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1574986A1 (en) * | 2004-03-17 | 2005-09-14 | Norbert Prof. Dr. Link | Apparatus and method to detect persons in a zone of interest |
| 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 |
| CN101872431A (en) * | 2010-02-10 | 2010-10-27 | 杭州海康威视软件有限公司 | People flow rate statistical method and system applicable to multi-angle application scenes |
| US20120182390A1 (en) * | 2011-01-18 | 2012-07-19 | Disney Enterprises, Inc. | Counting system for vehicle riders |
| CN102184409A (en) * | 2011-04-22 | 2011-09-14 | 北京文安科技发展有限公司 | Machine-vision-based passenger flow statistics method and system |
| US20130182904A1 (en) * | 2012-01-17 | 2013-07-18 | Objectvideo, Inc. | System and method for video content analysis using depth sensing |
| CN102799935A (en) * | 2012-06-21 | 2012-11-28 | 武汉烽火众智数字技术有限责任公司 | Human flow counting method based on video analysis technology |
| CN102902971A (en) * | 2012-08-31 | 2013-01-30 | 电子科技大学 | Method and system for conducting statistics on elevator visitor flow based on intelligent visual perception |
| CN103021059A (en) * | 2012-12-12 | 2013-04-03 | 天津大学 | Video-monitoring-based public transport passenger flow counting method |
| CN103646250A (en) * | 2013-09-13 | 2014-03-19 | 魏运 | Pedestrian monitoring method and device based on distance image head and shoulder features |
Non-Patent Citations (1)
| Title |
|---|
| 孙统义: "《实时视频监控人数统计关键技术研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106850722A (en) * | 2015-12-04 | 2017-06-13 | 上海杰轩智能科技有限公司 | A kind of method that passenger flow counting information is transmitted by HTTP |
| CN109064457A (en) * | 2018-07-25 | 2018-12-21 | 哈工大机器人（合肥）国际创新研究院 | A kind of method and system that the quantity of view-based access control model is accumulative |
| CN109064457B (en) * | 2018-07-25 | 2021-09-14 | 哈工大机器人（合肥）国际创新研究院 | Quantity accumulation method and system based on vision |
| CN110414361A (en) * | 2019-07-02 | 2019-11-05 | 青岛海洋科学与技术国家实验室发展中心 | Distributed machines vision data acquisition analysis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Paneru et al. | Computer vision applications in construction: Current state, opportunities & challenges | |
| Khallaf et al. | Classification and analysis of deep learning applications in construction: A systematic literature review | |
| US20220309835A1 (en) | Multi-target detection and tracking method, system, storage medium and application | |
| US10997428B2 (en) | Automated detection of building entrances | |
| JP4972491B2 (en) | Customer movement judgment system | |
| CN110532978A (en) | Storage management method, device, equipment and storage medium | |
| US20190080274A1 (en) | Tracking and/or analyzing facility-related activities | |
| CN103971082A (en) | Video object detecting system and method based on area conversion | |
| CN108369419A (en) | Generating a spatiotemporal object manifest using object observations of a mobile robot and using the manifest to determine monitoring parameters for the mobile robot | |
| CN103971433B (en) | A kind of bus passenger flow volume number system based on RFID and method | |
| CN103455657B (en) | A kind of site work emulation mode based on Kinect and system thereof | |
| CN104036139B (en) | A kind of mobile object track monitoring method | |
| Luo et al. | Construction machine pose prediction considering historical motions and activity attributes using gated recurrent unit (GRU) | |
| CN107403464A (en) | A kind of three-dimensional Mine Modeling system and method | |
| CN105892423A (en) | Intelligent-terminal-based intelligent work ticket system for digital workshop | |
| CN104933710A (en) | Intelligent analysis method of store people stream track on the basis of surveillance video | |
| Assadzadeh et al. | Vision-based excavator pose estimation using synthetically generated datasets with domain randomization | |
| CN1996357A (en) | Dynamic production line modeling system integrated with information system based on real-time data acquisition | |
| CN109409238A (en) | A kind of obstacle detection method, device and terminal device | |
| CN104063253A (en) | Method for automatic statistics of passenger flow, all-in-one machines and distributed system for automatic statistics of passenger flow | |
| CN106570055A (en) | Information early-warning platform based on financial big data | |
| CN102096408A (en) | Motor assembly line data collecting and processing system and data collecting method | |
| Bian et al. | Machine learning-based real-time monitoring system for smart connected worker to improve energy efficiency | |
| GB2495193A (en) | Method and system for counting and tracking defined and anonymous objects | |
| CN110363137A (en) | Face datection Optimized model, method, system and its electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140924 |
|
| RJ01 | Rejection of invention patent application after publication |