CN109657575A - Outdoor construction personnel's intelligent video track algorithm - Google Patents
Outdoor construction personnel's intelligent video track algorithm Download PDFInfo
- Publication number
- CN109657575A CN109657575A CN201811482771.3A CN201811482771A CN109657575A CN 109657575 A CN109657575 A CN 109657575A CN 201811482771 A CN201811482771 A CN 201811482771A CN 109657575 A CN109657575 A CN 109657575A
- Authority
- CN
- China
- Prior art keywords
- construction personnel
- construction
- algorithm
- personnel
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010276 construction Methods 0.000 title claims abstract description 103
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 14
- 230000033001 locomotion Effects 0.000 claims abstract description 12
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 230000018199 S phase Effects 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract description 14
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000009430 construction management Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of outdoor construction personnel intelligent video track algorithms, comprising the following steps: S1: the work image of the outer site operation scene of video camera collection room, and is manually demarcated according to the work image of acquisition to construction personnel relative position；S2: machine training is carried out using the image data set that the Yolo algorithm of target detection based on deep learning completes step S1 calibration；S3: the algorithm model finished by using training detects the given area in outdoor construction scene, tracks construction personnel and its motion profile of given area；S4: the motion profile with determining region construction personnel obtained according to step S3 calculates construction personnel whether in given area, and then judges whether normative operation.Inventive algorithm step is simple, can greatly improve the monitoring precision and efficiency at outdoor construction scene, and target, the operation overall process of effective monitoring construction personnel will not be lost by guaranteeing real-time tracing to the continuous monitoring of construction personnel's progress.
Description
Technical field
The present invention relates to the pedestrian detection of computer vision field and track algorithms, and in particular to a kind of outdoor construction personnel
Intelligent video track algorithm.
Background technique
Large-scale outdoor construction has the characteristics that construction area is big, distribution is wide, construction battle line is longer, and safe mass problem is not allowed
Ignore.However, there are the harshness of natural conditions, partial supervised pipe the personnel specialty difficulties such as not enough for security control, increase big
The control difficulty of type construction site.
Further to implement national security regulation, reinforce field operation control, there is an urgent need to a set of efficient for construction management
Control means achieve the purpose that manage construction site overall process safety and quality to position construction personnel in real time.Mesh
It is preceding using it is more be operation track using photographic technique construction personnel, largely taken the photograph in the angle installation for being conducive to shooting
Camera completes shooting, which has stronger territory restriction, large-scale outdoor construction scene by arrange a large amount of video cameras into
Row is recorded a video without dead angle, is had very big difficulty of construction, while supervisor's moment being needed to observe video record, is expended a large amount of people
Work cost and time cost.
In recent years, it is widely applied in pedestrian's identification using intelligent video analysis technology.Wherein, special based on HOG
The pedestrian detection model of SVM algorithm of seeking peace has been successfully applied to many protection and monitor fields.However, outdoor construction background scene
Increasingly complex, these classic algorithms are difficult to meet the required precision in such scene.
Therefore it is urgent to provide a kind of novel outdoor construction personnel's intelligent video track algorithms to solve the above problems.
Summary of the invention
In view of the above existing problems in the prior art, the present invention provides a kind of tracking of outdoor construction personnel intelligent video to calculate
Method can greatly improve the monitoring precision and efficiency at outdoor construction scene.
To achieve the goals above, the present invention provides technical solutions below: a kind of outdoor construction personnel intelligent video
Track algorithm, comprising the following steps:
S1: the work image of the outer site operation scene of video camera collection room, and according to the work image of acquisition to constructor
Member is manually demarcated relative position；
S2: it is carried out using the image data set that the Yolo algorithm of target detection based on deep learning completes step S1 calibration
Machine training；
S3: the algorithm model finished by using training detects the given area in outdoor construction scene, tracks
The construction personnel of given area and its motion profile；
S4: whether the motion profile with determining region construction personnel obtained according to step S3 calculates construction personnel given
In region, and then judge whether normative operation.
In a preferred embodiment of the present invention, the Yolo algorithm of target detection uses convolutional neural networks structure, packet
Convolutional layer, full articulamentum are included, the convolutional layer is used to predict the probability of output, passes through for extracting characteristics of image, full articulamentum
It is predicted using full figure information, the summary information of target is arrived in study.
In a preferred embodiment of the present invention, in step S3, in given area, tracking construction personnel uses centroid tracking
The specific steps of algorithm, the centroid tracking algorithm include:
S3.1: training the algorithm model finished to be trained for the work image of input includes the video of several bands of position
Sequence, each frame information of video sequence include several bands of position, and each region has a construction personnel, according to detection
All bands of position arrived, calculate the centroid position of construction personnel；
S3.2: all mass centers corresponding to any one frame of the video sequence calculate the frame to all mass centers of former frame
Euclidean distance；
S3.3: according to apart from minimum principle, the personnel area of the before and after frames of any one frame of the video sequence is matched.
Further, the matching process of step S3.3 are as follows:
According to any one content frame of the video sequence, positioned at the matching of its a later frame less than point, it is corresponding to delete its
Personal information；
According to any one content frame of the video sequence, positioned at its former frame matching less than point, correspondence establishment is new
Personal information.
In a preferred embodiment of the present invention, in step S4, according to the movement rail with determining region construction personnel of acquisition
Mark, calculate construction personnel whether in given area normative operation, judgment method are as follows:
Assuming that being rectangle frame, the construction area manually demarcated by the construction personnel region that the algorithm model that training finishes obtains
Domain is the polygon construction area including at least three endpoints,
The construction personnel's rectangle frame bottom edge midpoint detected and obtained is set as P0(x0, y0), polygon construction area is by point Mi
(xi, yi) (1=1,2 ..., N) it determines, while being respectivelyCount in N number of side whether simultaneously satisfaction is as follows
The number on the side of rule:
If the number for meeting the polygon edge of above formula is odd number, then it represents that point P0In polygon { MiIn, that is, indicate constructor
Member constructs in given area.
By adopting the above technical scheme, compared with prior art, a kind of outdoor construction personnel of the invention intelligently regard the present invention
Frequency track algorithm, has the advantages that
1. outdoor construction personnel intelligent video track algorithm of the present invention, by using the Yolo mesh based on deep learning
Collected construction site image can effectively be filtered construction site background by mark detection algorithm, quickly be captured containing constructor
The video sequence of member's information, the motion profile of real-time continuous tracking construction personnel is realized using centroid tracking algorithm, in conjunction with calculating
Geometry basic theories calculates it whether in given construction area, thus judge its whether normative operation；
2. outdoor construction personnel intelligent video track algorithm of the present invention, algorithm steps are simple, can greatly improve room
The monitoring precision and efficiency of outer construction site connect construction personnel under the premise of to use a small amount of outdoor camera
Continuous monitoring, which guarantees real-time tracing, will not lose target, the operation overall process of effective monitoring construction personnel.
3. the invention proposes a kind of standard construction operations to judge algorithm, construction personnel only can be judged by machine algorithm
Construction whether standardize, meet the requirement of real time of monitoring site, do not need monitoring personnel moment observation monitored picture and supervised
Control and tracking, effectively save management cost, while also enhancing the work quality and working efficiency of practice of construction.
Detailed description of the invention
Fig. 1 is the flow chart of outdoor construction personnel intelligent video track algorithm of the present invention.
Specific embodiment
In order to make the objectives, technical solutions and advantages of the present invention clearer, right below by attached drawing and embodiment
The present invention is further elaborated.However, it should be understood that specific embodiment described herein is only used to explain this hair
Range that is bright, being not intended to restrict the invention.
Referring to Fig. 1, a kind of outdoor construction personnel intelligent video track algorithm, by advance to the outdoor site operation of acquisition
Picture carries out sampling machine learning, and then detects to the given area in outdoor construction scene；
Preferably as a kind of embodiment, a kind of outdoor construction personnel intelligent video track algorithm it is specific
Step includes the following:
S1: the work image of the outer site operation scene of video camera collection room, and according to the work image of acquisition to constructor
Member is manually demarcated relative position, and preferred acquisition 5000 of the present invention opens master drawing as machine learning master drawing, and selected by guarantee
Master drawing includes looks, figure or the operating attitude of different construction personnel, it is ensured that machine training can be carried out efficiently；
S2: it is carried out using the image data set that the Yolo algorithm of target detection based on deep learning completes step S1 calibration
Machine training, to obtain efficient construction personnel's detection algorithm, training process carries out on the Open Source Code of Yolo, and in public affairs
It opens and carries out pre-training on extensive target detection data set MSCOCO, and then improve the precision of training；
The Yolo algorithm of target detection uses convolutional neural networks structure, including convolutional layer, full articulamentum, the convolution
Layer is used to predict the probability of output, is predicted by using full figure information for extracting characteristics of image, full articulamentum, learns
To the summary information of target.The Yolo algorithm is fast with recognition speed, the error rate of error detection is low, generalization ability is strong and accurate
Collected construction site image can effectively be filtered construction site background by the high feature of rate, quickly be captured containing construction
The video sequence of personal information.
S3: the algorithm model finished by using training detects the given area in outdoor construction scene, tracks
The construction personnel of given area and its motion profile；
In given area, tracking construction personnel uses centroid tracking algorithm, and specific steps include:
S3.1: training the algorithm model finished to be trained for the work image of input includes the video of several bands of position
Sequence, each frame information of video sequence include several bands of position, and each band of position has a construction personnel, according to
All bands of position detected, calculate the centroid position of construction personnel；
S3.2: all mass centers corresponding to any one frame of the video sequence calculate the frame to all mass centers of former frame
Euclidean distance；
S3.3: according to apart from minimum principle, the personnel area of the before and after frames of any one frame of the video sequence is matched.
Further, the matching process of step S3.3 are as follows:
According to any one content frame of the video sequence, positioned at the matching of its a later frame less than point, it is corresponding to delete its
Personal information；Or any one content frame according to the video sequence, positioned at its former frame matching less than point, correspondence establishment
New personal information.
The motion profile of real-time continuous tracking construction personnel is realized using centroid tracking algorithm.
S4: whether the motion profile with determining region construction personnel obtained according to step S3 calculates construction personnel given
In region, and then judge whether normative operation.Judgment method is as follows:
Assuming that being rectangle frame by the construction personnel band of position that the algorithm model that training finishes obtains, that manually demarcates applies
Work area domain is the polygon construction area including at least three endpoints,
Video frame is that real world projective transformation obtains as a result, the relative position that projective transformation can't change object is closed
System, therefore, target at picture close to the point of image base be part with ground face contact.Accordingly, substantially former in conjunction with computational geometry
Reason sets the construction personnel's rectangle frame bottom edge midpoint detected and obtained as P0(x0, y0), polygon construction area is by point Mi(xi, yi)}
(1=1,2 ..., N) it determines, while being respectivelyCount N number of when whether meeting following regular simultaneously in
Number:
If the number for meeting the polygon edge of above formula is odd number, then it represents that point P0In polygon { MiIn, that is, indicate constructor
Member constructs in given area.
Inventive algorithm step is simple, the monitoring precision and efficiency at outdoor construction scene can be greatly improved, to use
Under the premise of a small amount of outdoor camera, mesh will not be lost by guaranteeing real-time tracing to the continuous monitoring of construction personnel's progress
Mark, the operation overall process of effective monitoring construction personnel.The invention proposes a kind of standard construction operations to judge algorithm, can only lead to
It crosses machine algorithm and judges whether the construction of construction personnel standardizes, meet the requirement of real time of monitoring site, when not needing monitoring personnel
It carves observation monitored picture to be monitored and track, effectively save management cost, while also enhancing the as received basis of practice of construction
Amount and working efficiency.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (5)
1. a kind of outdoor construction personnel intelligent video track algorithm, comprising the following steps:
S1: the work image of the outer site operation scene of video camera collection room, and according to the work image of acquisition to construction personnel's phase
Position is manually demarcated；
S2: machine is carried out using the image data set that the Yolo algorithm of target detection based on deep learning completes step S1 calibration
Training；
S3: the algorithm model finished by using training detects the given area in outdoor construction scene, and tracking is given
The construction personnel in region and its motion profile；
S4: whether the motion profile with determining region construction personnel obtained according to step S3 calculates construction personnel in given area
It is interior, and then judge whether normative operation.
2. outdoor construction personnel intelligent video track algorithm according to claim 1, which is characterized in that the Yolo target
Detection algorithm uses convolutional neural networks structure, including convolutional layer, full articulamentum, and the convolutional layer is used to extract characteristics of image,
Full articulamentum is used to predict the probability of output, is predicted by using full figure information, and the summary information of target is arrived in study.
3. outdoor construction personnel intelligent video track algorithm according to claim 1, which is characterized in that in step S3,
Given area tracks construction personnel and uses centroid tracking algorithm, and the specific steps of the centroid tracking algorithm include:
S3.1: training the algorithm model finished to be trained for the work image of input includes the video sequence of several bands of position
Column, each frame information of video sequence include several bands of position, and each region has a construction personnel, according to detecting
All bands of position, calculate the centroid position of construction personnel；
S3.2: all mass centers corresponding to any one frame of the video sequence, calculate the frame to all mass centers of former frame Euclidean
Distance；
S3.3: according to apart from minimum principle, the personnel area of the before and after frames of any one frame of the video sequence is matched.
4. outdoor construction personnel intelligent video track algorithm according to claim 3, which is characterized in that of step S3.3
Method of completing the square are as follows:
According to any one content frame of the video sequence, positioned at the matching of its a later frame less than point, delete its corresponding personnel
Information；Or
According to any one content frame of the video sequence, positioned at the matching of its former frame less than point, the new personnel of correspondence establishment
Information.
5. outdoor construction personnel intelligent video track algorithm according to claim 1, which is characterized in that in step S4, root
According to the motion profile with determining region construction personnel of acquisition, calculate construction personnel whether normative operation, judgement in given area
Method is as follows:
Assuming that being rectangle frame by the construction personnel region that the algorithm model that training finishes obtains, the construction area manually demarcated is
Including at least the polygon construction area of three endpoints,
The construction personnel's rectangle frame bottom edge midpoint detected and obtained is set as P0(x0, y0), polygon construction area is by point Mi(xi,
yi) (i=1,2 ..., N) it determines, while being respectivelyCount whether meet simultaneously in N number of side it is following regular
Side number:
If the number for meeting the polygon edge of above formula is odd number, then it represents that point P0In polygon { MiIn, i.e. expression construction personnel exists
It constructs in given area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811482771.3A CN109657575B (en) | 2018-12-05 | 2018-12-05 | Intelligent video tracking algorithm for outdoor constructors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811482771.3A CN109657575B (en) | 2018-12-05 | 2018-12-05 | Intelligent video tracking algorithm for outdoor constructors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109657575A true CN109657575A (en) | 2019-04-19 |
| CN109657575B CN109657575B (en) | 2022-04-08 |
Family
ID=66111896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811482771.3A Active CN109657575B (en) | 2018-12-05 | 2018-12-05 | Intelligent video tracking algorithm for outdoor constructors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109657575B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232320A (en) * | 2019-05-08 | 2019-09-13 | 华中科技大学 | Method and system of the real-time detection building-site worker danger close to construction machinery |
| CN110490930A (en) * | 2019-08-21 | 2019-11-22 | 谷元(上海)文化科技有限责任公司 | A kind of scaling method of camera position |
| CN110602449A (en) * | 2019-09-01 | 2019-12-20 | 天津大学 | Intelligent construction safety monitoring system method in large scene based on vision |
| CN111083640A (en) * | 2019-07-25 | 2020-04-28 | 中国石油天然气股份有限公司 | Intelligent supervision method and system for construction site |
| CN111561915A (en) * | 2020-05-27 | 2020-08-21 | 永康龙飘传感科技有限公司 | Building construction state monitoring feedback device, system and method |
| CN112016409A (en) * | 2020-08-11 | 2020-12-01 | 艾普工华科技（武汉）有限公司 | Deep learning-based process step specification visual identification determination method and system |
| CN112270381A (en) * | 2020-11-16 | 2021-01-26 | 电子科技大学 | People flow detection method based on deep learning |
| CN112418136A (en) * | 2020-12-02 | 2021-02-26 | 云南电网有限责任公司电力科学研究院 | Target area detection tracking method and device for field operating personnel |
| CN112487891A (en) * | 2020-11-17 | 2021-03-12 | 云南电网有限责任公司 | Visual intelligent dynamic recognition model construction method applied to electric power operation site |
| CN112906566A (en) * | 2021-02-18 | 2021-06-04 | 天津大学 | Depth of field discrimination method for descending people in violation stay in boom vehicle operation scene |
| CN112949511A (en) * | 2021-03-08 | 2021-06-11 | 中国建筑一局(集团)有限公司 | Construction site personnel management method based on machine learning and image recognition |
| CN113420919A (en) * | 2021-06-21 | 2021-09-21 | 郑州航空工业管理学院 | Engineering abnormity control method based on unmanned aerial vehicle visual perception |
| CN113655750A (en) * | 2021-09-08 | 2021-11-16 | 北华航天工业学院 | Building construction supervision system and method based on AI object detection algorithm |
| CN115082849A (en) * | 2022-05-23 | 2022-09-20 | 哈尔滨工业大学 | Template support safety intelligent monitoring method based on deep learning |
| CN116758111A (en) * | 2023-08-21 | 2023-09-15 | 中通信息服务有限公司 | Construction site target object tracking method and device based on AI algorithm |
| CN117132942A (en) * | 2023-10-20 | 2023-11-28 | 山东科技大学 | Indoor personnel real-time distribution monitoring method based on region segmentation |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120274781A1 (en) * | 2011-04-29 | 2012-11-01 | Siemens Corporation | Marginal space learning for multi-person tracking over mega pixel imagery |
| CN104244113A (en) * | 2014-10-08 | 2014-12-24 | 中国科学院自动化研究所 | Method for generating video abstract on basis of deep learning technology |
| CN106981163A (en) * | 2017-03-26 | 2017-07-25 | 天津普达软件技术有限公司 | A kind of personnel invade abnormal event alarming method |
| CN107133564A (en) * | 2017-03-26 | 2017-09-05 | 天津普达软件技术有限公司 | A kind of frock work hat detection method |
| CN108053427A (en) * | 2017-10-31 | 2018-05-18 | 深圳大学 | A kind of modified multi-object tracking method, system and device based on KCF and Kalman |
-
2018
- 2018-12-05 CN CN201811482771.3A patent/CN109657575B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120274781A1 (en) * | 2011-04-29 | 2012-11-01 | Siemens Corporation | Marginal space learning for multi-person tracking over mega pixel imagery |
| CN104244113A (en) * | 2014-10-08 | 2014-12-24 | 中国科学院自动化研究所 | Method for generating video abstract on basis of deep learning technology |
| CN106981163A (en) * | 2017-03-26 | 2017-07-25 | 天津普达软件技术有限公司 | A kind of personnel invade abnormal event alarming method |
| CN107133564A (en) * | 2017-03-26 | 2017-09-05 | 天津普达软件技术有限公司 | A kind of frock work hat detection method |
| CN108053427A (en) * | 2017-10-31 | 2018-05-18 | 深圳大学 | A kind of modified multi-object tracking method, system and device based on KCF and Kalman |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232320B (en) * | 2019-05-08 | 2021-07-02 | 华中科技大学 | Method and system for detecting danger of workers approaching construction machinery on construction site in real time |
| CN110232320A (en) * | 2019-05-08 | 2019-09-13 | 华中科技大学 | Method and system of the real-time detection building-site worker danger close to construction machinery |
| CN111083640A (en) * | 2019-07-25 | 2020-04-28 | 中国石油天然气股份有限公司 | Intelligent supervision method and system for construction site |
| CN110490930A (en) * | 2019-08-21 | 2019-11-22 | 谷元(上海)文化科技有限责任公司 | A kind of scaling method of camera position |
| CN110490930B (en) * | 2019-08-21 | 2022-12-13 | 谷元(上海)文化科技有限责任公司 | Calibration method for camera position |
| CN110602449A (en) * | 2019-09-01 | 2019-12-20 | 天津大学 | Intelligent construction safety monitoring system method in large scene based on vision |
| CN111561915A (en) * | 2020-05-27 | 2020-08-21 | 永康龙飘传感科技有限公司 | Building construction state monitoring feedback device, system and method |
| CN112016409A (en) * | 2020-08-11 | 2020-12-01 | 艾普工华科技（武汉）有限公司 | Deep learning-based process step specification visual identification determination method and system |
| CN112270381A (en) * | 2020-11-16 | 2021-01-26 | 电子科技大学 | People flow detection method based on deep learning |
| CN112270381B (en) * | 2020-11-16 | 2022-06-03 | 电子科技大学 | People flow detection method based on deep learning |
| CN112487891B (en) * | 2020-11-17 | 2023-07-18 | 云南电网有限责任公司 | Visual intelligent dynamic identification model construction method applied to electric power operation site |
| CN112487891A (en) * | 2020-11-17 | 2021-03-12 | 云南电网有限责任公司 | Visual intelligent dynamic recognition model construction method applied to electric power operation site |
| CN112418136B (en) * | 2020-12-02 | 2023-11-24 | 云南电网有限责任公司电力科学研究院 | Method and device for detecting and tracking target area of field operator |
| CN112418136A (en) * | 2020-12-02 | 2021-02-26 | 云南电网有限责任公司电力科学研究院 | Target area detection tracking method and device for field operating personnel |
| CN112906566B (en) * | 2021-02-18 | 2024-02-13 | 天津大学 | Depth of field judging method for offending and staying of descending person in operation scene of suspension arm vehicle |
| CN112906566A (en) * | 2021-02-18 | 2021-06-04 | 天津大学 | Depth of field discrimination method for descending people in violation stay in boom vehicle operation scene |
| CN112949511A (en) * | 2021-03-08 | 2021-06-11 | 中国建筑一局(集团)有限公司 | Construction site personnel management method based on machine learning and image recognition |
| CN113420919B (en) * | 2021-06-21 | 2023-05-05 | 郑州航空工业管理学院 | Engineering anomaly control method based on unmanned aerial vehicle visual perception |
| CN113420919A (en) * | 2021-06-21 | 2021-09-21 | 郑州航空工业管理学院 | Engineering abnormity control method based on unmanned aerial vehicle visual perception |
| CN113655750B (en) * | 2021-09-08 | 2023-08-18 | 北华航天工业学院 | Building construction supervision system and method based on AI object detection algorithm |
| CN113655750A (en) * | 2021-09-08 | 2021-11-16 | 北华航天工业学院 | Building construction supervision system and method based on AI object detection algorithm |
| CN115082849A (en) * | 2022-05-23 | 2022-09-20 | 哈尔滨工业大学 | Template support safety intelligent monitoring method based on deep learning |
| CN116758111A (en) * | 2023-08-21 | 2023-09-15 | 中通信息服务有限公司 | Construction site target object tracking method and device based on AI algorithm |
| CN116758111B (en) * | 2023-08-21 | 2023-11-17 | 中通信息服务有限公司 | Construction site target object tracking method and device based on AI algorithm |
| CN117132942A (en) * | 2023-10-20 | 2023-11-28 | 山东科技大学 | Indoor personnel real-time distribution monitoring method based on region segmentation |
| CN117132942B (en) * | 2023-10-20 | 2024-01-26 | 山东科技大学 | Indoor personnel real-time distribution monitoring method based on region segmentation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109657575B (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109657575A (en) | Outdoor construction personnel's intelligent video track algorithm | |
| CN109829436B (en) | Multi-face tracking method based on depth appearance characteristics and self-adaptive aggregation network | |
| CN105405154B (en) | Target object tracking based on color-structure feature | |
| WO2020042419A1 (en) | Gait-based identity recognition method and apparatus, and electronic device | |
| CN110399844A (en) | It is a kind of to be identified and method for tracing and system applied to cross-platform face key point | |
| CN105574506A (en) | Intelligent face tracking system and method based on depth learning and large-scale clustering | |
| CN104123544A (en) | Video analysis based abnormal behavior detection method and system | |
| CN108447091A (en) | Object localization method, device, electronic equipment and storage medium | |
| CN106203260A (en) | Pedestrian's recognition and tracking method based on multiple-camera monitoring network | |
| CN107256386A (en) | Human behavior analysis method based on deep learning | |
| CN106295558A (en) | A kind of pig Behavior rhythm analyzes method | |
| CN103605971B (en) | Method and device for capturing face images | |
| CN104463174A (en) | Multi-angle dynamic people recognition and behavior prediction system | |
| CN102262727A (en) | Method for monitoring face image quality at client acquisition terminal in real time | |
| CN110569785B (en) | Face recognition method integrating tracking technology | |
| CN109784130A (en) | Pedestrian recognition methods and its device and equipment again | |
| CN106981150A (en) | A kind of supermarket's intelligent anti-theft system and method | |
| CN107230267A (en) | Intelligence In Baogang Kindergarten based on face recognition algorithms is registered method | |
| CN105022999A (en) | Man code company real-time acquisition system | |
| CN111008993A (en) | Method and device for tracking pedestrian across mirrors | |
| CN109934098A (en) | A kind of video camera intelligence system and its implementation with secret protection | |
| CN108460983A (en) | Parking stall condition detection method based on convolutional neural networks | |
| CN110176025A (en) | A kind of proctor's tracking based on posture | |
| CN108196680A (en) | Robot vision following method based on human body feature extraction and retrieval | |
| CN112395967A (en) | Mask wearing monitoring method, electronic device and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: No. 397, Tongcheng South Road, Baohe District, Hefei City, Anhui Province 230061 Patentee after: Super high voltage branch of State Grid Anhui Electric Power Co.,Ltd. Patentee after: STATE GRID CORPORATION OF CHINA Address before: 230051 No.397, Tongcheng South Road, Baohe District, Hefei City, Anhui Province Patentee before: STATE GRID ANHUI POWER SUPPLY COMPANY OVERHAUL BRANCH Patentee before: STATE GRID CORPORATION OF CHINA |