CN106503632A - A kind of escalator intelligent and safe monitoring method based on video analysis - Google Patents
A kind of escalator intelligent and safe monitoring method based on video analysis Download PDFInfo
- Publication number
- CN106503632A CN106503632A CN201610885329.XA CN201610885329A CN106503632A CN 106503632 A CN106503632 A CN 106503632A CN 201610885329 A CN201610885329 A CN 201610885329A CN 106503632 A CN106503632 A CN 106503632A
- Authority
- CN
- China
- Prior art keywords
- escalator
- human object
- angle point
- human
- video
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
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)
- Escalators And Moving Walkways (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of escalator intelligent and safe monitoring method based on video analysis, step is as follows：Real time video image sequence installed in the video camera of monitor area in is obtained first；Next sets up mixture Gaussian background model, and to video image in shade suppressed to extract prospect；Then human object identification is carried out by grader to the prospect that extracts, and calculates human object angle point light stream, so as to determine whether that the abnormal behaviours such as passenger is retrograde or falls, to take the measures such as Escalator jerk in time, ensure the personal safety for taking advantage of staircase personnel.The present invention is high to human object accuracy of detection, and detection speed is fast, the abnormal behaviour for judging human object by angle point light stream, can effectively prevent personnel, from because driving in the wrong direction or falling, the probability of tread event occurring, dramatically protect the personal safety of passenger.
Description
Technical field
The present invention relates to technical field of video monitoring, particularly a kind of escalator intelligent and safe prison based on video analysis
Survey method.
Background technology
Automatic escalator is played an important role in public arenas such as market, subway, railway station import and export, and high in the stream of people
Tend to the uncivil behavior phenomenons such as personnel are crowded, push and shove occur during peak, cause the emergency situations such as personnel's tumble.For preventing people
The serious accident that member's tumble causes, need to carry out jerk to Escalator immediately when generation personnel fall.
With the development of intelligent video technology, whether existing part research is applied to detection pedestrian with regard to intelligent video technology
There are the abnormal behaviours such as tumble.Chinese invention patent 1 (application number CN200910154420) discloses a kind of based on comprehensive calculating
The escalator energy-conservation of machine vision and installation monitoring system, which proposes and solves elevator energy-saving and security monitoring using video technique
Method, but the abnormal behaviour for failing to illustrate how testing staff；Chinese invention patent 2 (publication number CN10607668) is disclosed
A kind of device of Escalator monitoring, does not specify how to detect abnormal behaviour of the personnel on Escalator yet.It is thus impossible to avoid
Above escalator there is tread event because driving in the wrong direction or falling in personnel, and the personal safety of passenger is caused a hidden trouble.
Content of the invention
It is an object of the invention to provide a kind of escalator intelligent and safe monitoring method based on video analysis, to reduce
There is the probability of tread event because driving in the wrong direction or falling in personnel, dramatically protect the personal safety of passenger.
The technical solution for realizing the object of the invention is：A kind of escalator intelligent and safe based on video analysis is monitored
Method, comprises the following steps：
Step 1, obtains installed in sequence of video images in the video camera of monitor area；
Step 2, sets up mixture Gaussian background model, extracts prospect in conjunction with cast shadow suppressing method；
Step 3, in foreground area, recognizes human object using SVM+HOG graders；
Step 4, human body target tracking and optical flow computation；
Step 5, judges to take advantage of whether Escalator personnel have abnormal behaviour according to movement objective orbit and light stream size and Orientation,
Emergent stopping Escalator audible alarm is carried out if having；
Step 6, shows video image in real time, judges whether abnormal behaviour terminates, and if terminating restarts Escalator.
Further, described in step 3 in foreground area, human object, concrete steps are recognized using SVM+HOG graders
As follows：
(1) the above body training sample database of shoulders of human body is set up, and including positive sample storehouse and negative example base, positive sample storehouse includes
The above body image of the shoulders of human body of various attitudes, negative example base refer to that pedestrian takes advantage of the chaff interference that carries with during Escalator, including
Chest, handbag, school bag, go-cart, the object image of bucket；
(2) Sample Storehouse is trained using SVM+HOG graders, and by the foreground area that extracts with training after people
Body characteristicses are mated, so as to obtain human object.
Further, human body target tracking described in step 4 and optical flow computation, comprise the following steps that：
(1) human object detected in step 3 is tracked using pyramid Lucas-Kanade optical flow methods, and handle
Each human body Object tracking tracing point is stored in array tracei[j], i=1 ..., n, j=1 ..., in m, wherein, n represents inspection
The human object number for measuring, m are represented from t1Moment is to t2The totalframes that moment video camera is photographed；
(2) gradient and curvature of each pixel in i-th human object for detecting are calculated, to obtain i-th human body
The angle point C of objectik, i=1 ..., n, k=1 ..., K, wherein, K represents the angle point number of i-th human object, using pyramid
Corresponding angle point C in Lucas-Kanade optical flow methods tracking video sequence in two continuous frames imageik, obtain each angle point current
VelocityThat is the size and Orientation of angle point light stream.
Further, judge to take advantage of Escalator personnel according to movement objective orbit and light stream size and Orientation described in step 5
Whether there is abnormal behaviour, emergent stopping Escalator audible alarm is carried out if having, comprised the following steps that：
(1) judge whether pedestrian drives in the wrong direction：The pursuit path point trace of human object is obtained in step 4i[j], and obtain
Current Escalator traffic direction d, if same human object is in continuous 12 frame video sequence, has the pursuit path point of 8 frames
traceiThe direction of [j] is inconsistent with Escalator traffic direction d, then judge that pedestrian drives in the wrong direction；
(2) judge whether pedestrian falls：Obtain human object angle point light stream size and Orientation in step 4, judge human body
The angle point of the upper part of the bodyAngle point light stream with the human body lower part of the bodyIf size meets following formula, judge that pedestrian falls：
Wherein, T represents the threshold value that upper half of human body is differed with lower part of the body light stream size；
(3) if there is the abnormal behaviour that pedestrian drives in the wrong direction or falls, Escalator operation is automatically stopped.
The present invention compared with prior art, its remarkable advantage：(1) using SVM+HOG graders to the foreground zone extracted
Domain carries out human testing, and accuracy of detection is high, and detection speed is fast；(2) abnormal behaviour of human object is judged by angle point light stream,
Can remain to judge whether the passenger on Escalator occurs abnormal behaviour in the case where passenger is more, so as to effectively prevent people
There is tread event because driving in the wrong direction or falling in member, dramatically protect the personal safety of passenger.
Below in conjunction with the accompanying drawings the present invention is described in further detail.
Description of the drawings
Fig. 1 is escalator intelligent and safe monitoring method flow chart of the present invention based on video analysis.
Fig. 2 is to extract the video background figure for obtaining.
Fig. 3 is human object recognition result mark figure.
Fig. 4 is human body angle point light stream size and Orientation mark figure.
Fig. 5 is Escalator traffic direction mark figure.
Specific embodiment
In conjunction with Fig. 1, escalator intelligent and safe monitoring method of the present invention based on video analysis, comprise the following steps：
Step 1, obtains installed in sequence of video images in the video camera of monitor area.
Step 2, sets up mixture Gaussian background model, extracts prospect in conjunction with cast shadow suppressing method.
Step 3, in foreground area, using SVM (Support Vector Machine, SVMs)+HOG
(Histogram of Oriented Gradient, histograms of oriented gradients) grader recognizes human object, and concrete steps are such as
Under：
(1) the above body training sample database of shoulders of human body is set up, and including positive sample storehouse and negative example base, positive sample storehouse includes
The above body image of the shoulders of human body of various attitudes, negative example base refer to that pedestrian takes advantage of all kinds of chaff interferences that carries with during Escalator,
Including the object image such as chest, handbag, school bag, go-cart, bucket；
(2) Sample Storehouse is trained using SVM+HOG, and by the foreground area that extracts with training after characteristics of human body
Mated, so as to obtain human object.
Step 4, human body target tracking and optical flow computation, comprise the following steps that：
(1) human object detected in step 3 is tracked using pyramid Lucas-Kanade optical flow methods, and handle
Each human body Object tracking tracing point is stored in array tracei[j], i=1 ..., n, j=1 ..., in m, wherein, n represents inspection
The human object number for measuring, m are represented from t1Moment is to t2The totalframes that moment video camera is photographed；
(2) gradient and curvature of each pixel in i-th human object for detecting are calculated, to obtain i-th human body
The angle point C of objectik, i=1 ..., n, k=1 ..., K, wherein, K represents the angle point number of i-th human object, using pyramid
Corresponding angle point C in Lucas-Kanade optical flow methods tracking video sequence in two continuous frames imageik, obtain each angle point current
VelocityThat is the size and Orientation of angle point light stream.
Step 5, judges to take advantage of whether Escalator personnel have abnormal behaviour according to movement objective orbit and light stream size and Orientation,
If having, emergent stopping Escalator simultaneously carries out audible alarm, comprises the following steps that：
(1) judge whether pedestrian drives in the wrong direction：The pursuit path point trace of human object is obtained in step 4i[j], and obtain
Current Escalator traffic direction d, if same human object is in continuous 12 frame video sequence, has the pursuit path point of 8 frames
traceiThe direction of [j] is inconsistent with Escalator traffic direction d, then judge that pedestrian drives in the wrong direction；
(2) judge whether pedestrian falls：Obtain human object angle point light stream size and Orientation in step 4, judge human body
The angle point of the upper part of the bodyAngle point light stream with the human body lower part of the bodyIf size meets following formula, judge that pedestrian falls：
Wherein, T represents the threshold value that upper half of human body is differed with lower part of the body light stream size；
(3) if there is the abnormal behaviour that pedestrian drives in the wrong direction or falls, carry out sound prompting and be automatically stopped Escalator operation
Etc. stringent effort.
Step 6, shows video image in real time, judges whether abnormal behaviour terminates, and if terminating restarts Escalator.
The present invention is described in further detail with reference to specific embodiment.
Embodiment 1
Escalator intelligent and safe monitoring method of the present embodiment based on video analysis, step are as follows：
Step 1, extracts sequence of video images from the video camera of monitor area；
Step 2, according to the video sequence for extracting, in conjunction with video text message, sets up mixture Gaussian background model, extracts
The current background for arriving is as shown in Figure 2.
Step 3, in foreground area, recognizes human object using SVM+HOG graders, and human object is entered rower
Note, recognition result are as shown in Figure 3；
Step 4, is detected and is calculated its light stream size and Orientation using optical flow method to the angle point of human object, angle point
Light stream size and Orientation is marked in video image, as shown in Figure 4；
Step 5, due to Escalator traffic direction as shown in figure 5, human body angle point light stream direction and Escalator traffic direction exist
It is contrary in continuous 12 frame, therefore, the pedestrian in Fig. 5 is retrograde；
Step 6, carries out sound prompting, and takes related intervening measure to pedestrian.
To sum up, the present invention is fast to human object accuracy of detection height, speed, the exception for judging human object by angle point light stream
Behavior, can effectively prevent personnel, from because driving in the wrong direction or falling, tread event occurring, dramatically protect the personal safety of passenger.
Claims (4)
1. a kind of escalator intelligent and safe monitoring method based on video analysis, it is characterised in that comprise the following steps：
Step 1, obtains installed in sequence of video images in the video camera of monitor area；
Step 2, sets up mixture Gaussian background model, extracts prospect in conjunction with cast shadow suppressing method；
Step 3, in foreground area, recognizes human object using SVM+HOG graders；
Step 4, human body target tracking and optical flow computation；
Step 5, judges to take advantage of whether Escalator personnel have abnormal behaviour according to movement objective orbit and light stream size and Orientation, if having
Then emergent stopping Escalator audible alarm is carried out；
Step 6, shows video image in real time, judges whether abnormal behaviour terminates, and if terminating restarts Escalator.
2. the escalator intelligent and safe monitoring method based on video analysis according to claim 1, it is characterised in that step
Described in rapid 3 in foreground area, human object is recognized using SVM+HOG graders, comprised the following steps that：
(1) the above body training sample database of shoulders of human body is set up, and including positive sample storehouse and negative example base, positive sample storehouse includes various
The above body image of the shoulders of human body of attitude, negative example base refer to that pedestrian takes advantage of the chaff interference that carries with during Escalator, including chest,
Handbag, school bag, go-cart, the object image of bucket；
(2) Sample Storehouse is trained using SVM+HOG graders, and will be special with the human body after training for the foreground area that extracts
Levy and mated, so as to obtain human object.
3. the escalator intelligent and safe monitoring method based on video analysis according to claim 1, it is characterised in that step
Described in rapid 4, human body target tracking and optical flow computation, comprise the following steps that：
(1) human object detected in step 3 is tracked using pyramid Lucas-Kanade optical flow methods, and each
Human object pursuit path point is stored in array tracei[j], i=1 ..., n, j=1 ..., in m, wherein, n is represented and is detected
Human object number, m represented from t1Moment is to t2The totalframes that moment video camera is photographed；
(2) gradient and curvature of each pixel in i-th human object for detecting are calculated, to obtain i-th human object
Angle point Cik, i=1 ..., n, k=1 ..., K, wherein, K represents the angle point number of i-th human object, using pyramid
Corresponding angle point C in Lucas-Kanade optical flow methods tracking video sequence in two continuous frames imageik, obtain each angle point current
VelocityThat is the size and Orientation of angle point light stream.
4. the escalator intelligent and safe monitoring method based on video analysis according to claim 3, it is characterised in that step
Judge to take advantage of whether Escalator personnel have abnormal behaviour according to movement objective orbit and light stream size and Orientation described in rapid 5, if having
Then emergent stopping Escalator audible alarm is carried out, comprised the following steps that：
(1) judge whether pedestrian drives in the wrong direction：The pursuit path point trace of human object is obtained in step 4i[j], and obtain current
Escalator traffic direction d, if same human object is in continuous 12 frame video sequence, has the pursuit path point trace of 8 framesi
The direction of [j] is inconsistent with Escalator traffic direction d, then judge that pedestrian drives in the wrong direction；
(2) judge whether pedestrian falls：Obtain human object angle point light stream size and Orientation in step 4, judge human body upper half
The angle point of bodyAngle point light stream with the human body lower part of the bodyIf size meets following formula, judge that pedestrian falls：
Wherein, T represents the threshold value that upper half of human body is differed with lower part of the body light stream size；
(3) if there is the abnormal behaviour that pedestrian drives in the wrong direction or falls, Escalator operation is automatically stopped.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610885329.XA CN106503632A (en) | 2016-10-10 | 2016-10-10 | A kind of escalator intelligent and safe monitoring method based on video analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610885329.XA CN106503632A (en) | 2016-10-10 | 2016-10-10 | A kind of escalator intelligent and safe monitoring method based on video analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106503632A true CN106503632A (en) | 2017-03-15 |
Family
ID=58293862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610885329.XA Pending CN106503632A (en) | 2016-10-10 | 2016-10-10 | A kind of escalator intelligent and safe monitoring method based on video analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106503632A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145696A (en) * | 2017-06-28 | 2019-01-04 | 安徽清新互联信息科技有限公司 | A kind of Falls Among Old People detection method and system based on deep learning |
| CN109492575A (en) * | 2018-11-06 | 2019-03-19 | 东北大学 | A kind of staircase safety monitoring method based on YOLOv3 |
| CN109726750A (en) * | 2018-12-21 | 2019-05-07 | 上海三菱电梯有限公司 | A kind of passenger falls down detection device and its detection method and passenger conveying appliance |
| CN110009650A (en) * | 2018-12-20 | 2019-07-12 | 浙江新再灵科技股份有限公司 | A kind of escalator handrail borderline region crosses the border detection method and system |
| US10351392B1 (en) | 2018-10-23 | 2019-07-16 | Otis Elevator Company | Escalator and moving walkway system with safety sensor |
| CN110472473A (en) * | 2019-06-03 | 2019-11-19 | 浙江新再灵科技股份有限公司 | The method fallen based on people on Attitude estimation detection staircase |
| CN111144247A (en) * | 2019-12-16 | 2020-05-12 | 浙江大学 | Escalator passenger reverse-running detection method based on deep learning |
| CN113011290A (en) * | 2021-03-03 | 2021-06-22 | 上海商汤智能科技有限公司 | Event detection method and device, electronic equipment and storage medium |
| US20210335391A1 (en) * | 2019-06-24 | 2021-10-28 | Tencent Technology (Shenzhen) Company Limited | Resource display method, device, apparatus, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573612A (en) * | 2013-10-16 | 2015-04-29 | 北京三星通信技术研究有限公司 | Equipment and method for estimating postures of multiple overlapped human body objects in range image |
| CN105678811A (en) * | 2016-02-25 | 2016-06-15 | 上海大学 | Motion-detection-based human body abnormal behavior detection method |
| CN105701467A (en) * | 2016-01-13 | 2016-06-22 | 河海大学常州校区 | Many-people abnormal behavior identification method based on human body shape characteristic |
| CN105975923A (en) * | 2016-05-03 | 2016-09-28 | 湖南拓视觉信息技术有限公司 | Method and system for tracking human object |
| CN107292908A (en) * | 2016-04-02 | 2017-10-24 | 上海大学 | Pedestrian tracting method based on KLT feature point tracking algorithms |
-
2016
- 2016-10-10 CN CN201610885329.XA patent/CN106503632A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573612A (en) * | 2013-10-16 | 2015-04-29 | 北京三星通信技术研究有限公司 | Equipment and method for estimating postures of multiple overlapped human body objects in range image |
| CN105701467A (en) * | 2016-01-13 | 2016-06-22 | 河海大学常州校区 | Many-people abnormal behavior identification method based on human body shape characteristic |
| CN105678811A (en) * | 2016-02-25 | 2016-06-15 | 上海大学 | Motion-detection-based human body abnormal behavior detection method |
| CN107292908A (en) * | 2016-04-02 | 2017-10-24 | 上海大学 | Pedestrian tracting method based on KLT feature point tracking algorithms |
| CN105975923A (en) * | 2016-05-03 | 2016-09-28 | 湖南拓视觉信息技术有限公司 | Method and system for tracking human object |
Non-Patent Citations (2)
| Title |
|---|
| 杨冠宝: ""基于全景视觉的自动扶梯节能及职能监控系统"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 柳絮青: ""电梯监控系统的研究与应用"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145696B (en) * | 2017-06-28 | 2021-04-09 | 安徽清新互联信息科技有限公司 | Old people falling detection method and system based on deep learning |
| CN109145696A (en) * | 2017-06-28 | 2019-01-04 | 安徽清新互联信息科技有限公司 | A kind of Falls Among Old People detection method and system based on deep learning |
| EP3647251B1 (en) * | 2018-10-23 | 2022-11-30 | Otis Elevator Company | Escalator and moving walkway system with safety sensor |
| US10351392B1 (en) | 2018-10-23 | 2019-07-16 | Otis Elevator Company | Escalator and moving walkway system with safety sensor |
| CN109492575A (en) * | 2018-11-06 | 2019-03-19 | 东北大学 | A kind of staircase safety monitoring method based on YOLOv3 |
| CN110009650B (en) * | 2018-12-20 | 2021-06-29 | 浙江新再灵科技股份有限公司 | Escalator handrail boundary area border crossing detection method and system |
| CN110009650A (en) * | 2018-12-20 | 2019-07-12 | 浙江新再灵科技股份有限公司 | A kind of escalator handrail borderline region crosses the border detection method and system |
| CN109726750A (en) * | 2018-12-21 | 2019-05-07 | 上海三菱电梯有限公司 | A kind of passenger falls down detection device and its detection method and passenger conveying appliance |
| CN109726750B (en) * | 2018-12-21 | 2023-09-12 | 上海三菱电梯有限公司 | Passenger fall detection device, passenger fall detection method and passenger conveying device |
| CN110472473A (en) * | 2019-06-03 | 2019-11-19 | 浙江新再灵科技股份有限公司 | The method fallen based on people on Attitude estimation detection staircase |
| US20210335391A1 (en) * | 2019-06-24 | 2021-10-28 | Tencent Technology (Shenzhen) Company Limited | Resource display method, device, apparatus, and storage medium |
| CN111144247A (en) * | 2019-12-16 | 2020-05-12 | 浙江大学 | Escalator passenger reverse-running detection method based on deep learning |
| CN111144247B (en) * | 2019-12-16 | 2023-10-13 | 浙江大学 | Escalator passenger reverse detection method based on deep learning |
| CN113011290A (en) * | 2021-03-03 | 2021-06-22 | 上海商汤智能科技有限公司 | Event detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106503632A (en) | A kind of escalator intelligent and safe monitoring method based on video analysis | |
| Jiansheng | Vision-based real-time traffic accident detection | |
| CN102765365B (en) | Pedestrian detection method based on machine vision and pedestrian anti-collision warning system based on machine vision | |
| CN113516076B (en) | Attention mechanism improvement-based lightweight YOLO v4 safety protection detection method | |
| KR101748121B1 (en) | System and method for detecting image in real-time based on object recognition | |
| CN103400111B (en) | Method for detecting fire accident on expressway or in tunnel based on video detection technology | |
| CN105184274B (en) | A kind of based on depth image acquisition passenger flow speed and the method for density parameter | |
| US20070035622A1 (en) | Method and apparatus for video surveillance | |
| CN103971380A (en) | Pedestrian trailing detection method based on RGB-D | |
| CN105141885A (en) | Method for video monitoring and device | |
| CN113743256B (en) | Intelligent early warning method and device for site safety | |
| CN110287906A (en) | Method and system based on image/video detection people " playing mobile phone " | |
| CN106210634A (en) | A kind of wisdom gold eyeball identification personnel fall down to the ground alarm method and device | |
| CN101968848A (en) | Video monitoring method and system and video monitoring alarm system | |
| CN103198296A (en) | Method and device of video abnormal behavior detection based on Bayes surprise degree calculation | |
| CN111680613A (en) | Method for detecting falling behavior of escalator passengers in real time | |
| CN109353907A (en) | The security prompt method and system of elevator operation | |
| CN104331687B (en) | A kind of behavioral value method of not fastening the safety belt based on vehicular video analysis | |
| CN104268548A (en) | Accumulated snow detection method based on road images | |
| CN111062238A (en) | Escalator flow monitoring method and system based on human skeleton information and multi-target tracking | |
| CN116299751A (en) | Method and device for rapidly extracting passive terahertz human body security inspection information | |
| CN106372566A (en) | Digital signage-based emergency evacuation system and method | |
| CN105741503A (en) | Parking lot real time early warning method under present monitoring device | |
| CN109308467A (en) | Traffic accident prior-warning device and method for early warning based on machine learning | |
| CN104392201A (en) | Human fall identification method based on omnidirectional visual sense |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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: 20170315 |
|
| RJ01 | Rejection of invention patent application after publication |