CN113989719A - Construction site theft monitoring method and system - Google Patents
Construction site theft monitoring method and system Download PDFInfo
- Publication number
- CN113989719A CN113989719A CN202111277965.1A CN202111277965A CN113989719A CN 113989719 A CN113989719 A CN 113989719A CN 202111277965 A CN202111277965 A CN 202111277965A CN 113989719 A CN113989719 A CN 113989719A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- coordinates
- algorithm
- yolo
- euclidean distance
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000010276 construction Methods 0.000 title claims abstract description 28
- 230000036544 posture Effects 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000010606 normalization Methods 0.000 claims abstract description 5
- 238000013135 deep learning Methods 0.000 claims abstract description 4
- 210000000707 wrist Anatomy 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000016273 neuron death Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Human Resources & Organizations (AREA)
- Biophysics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Economics (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computer Security & Cryptography (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Burglar Alarm Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to a construction site theft monitoring method and a system, wherein the method comprises the following steps: s1, acquiring a scene image from a monitoring video of a monitoring area by a monitoring camera, detecting a target monitoring material in the image through a deep learning target detection algorithm framework YOLO V3, and identifying and outputting the target monitoring material by using a rectangular frame; s2, detecting and outputting body skeleton postures of all individuals in the image through a real-time multi-person posture estimation algorithm model OpenPose; s3, integrating two algorithm models, and calculating the shortest Euclidean distance from the coordinates of the palm key points of the human body to all rectangular frames by using a KDTree algorithm; and S4, dividing the shortest Euclidean distance by the shorter side of the corresponding rectangular frame to realize normalization, and if the value is smaller than a preset threshold value T, judging that the material at the construction site is likely to be stolen. The method and the system are beneficial to real-time and accurate safety monitoring of important materials in the construction site so as to protect the important materials from being stolen.
Description
Technical Field
The invention belongs to the technical field of monitoring, and particularly relates to a construction site theft monitoring method and system.
Background
Along with the continuous development of engineering construction, the scale of a construction site is larger and larger, a large amount of personnel are needed to participate, the site environment is complex, and therefore the management and control and security difficulty of the site are larger and larger. Materials used on a construction site cannot be completely placed in a warehouse, partial materials such as communication cables, valves, bolts, frame buckles and the like can be generally placed in a material stacking area and an auxiliary operation area of the construction site, the situation that the materials are stolen easily occurs after the construction site is shut down, and property safety of the construction site and property safety of workers are seriously threatened. The traditional anti-theft method needs the alternate guard of the guard, wastes time and labor, and cannot well meet the industrial requirement. Therefore, the intelligent anti-theft technology is applied to the site security management and has important significance.
Disclosure of Invention
The invention aims to provide a construction site theft monitoring method and a construction site theft monitoring system, which are beneficial to real-time and accurate safety monitoring of important materials in a construction site so as to protect the important materials from being stolen.
In order to achieve the purpose, the invention adopts the technical scheme that: a worksite theft monitoring method, comprising the steps of:
s1, acquiring a scene image from a monitoring video of a monitoring area by a monitoring camera, detecting a target monitoring material in the image through a deep learning target detection algorithm framework YOLO V3, and identifying and outputting the target monitoring material by using a rectangular frame;
s2, detecting and outputting body skeleton postures of all individuals in the image through a real-time multi-person posture estimation algorithm model OpenPose;
step S3, integrating two algorithm models, and calculating the shortest Euclidean distance from the coordinates of the palm key points of the human body to all rectangular frames by using a KDTree algorithm;
and step S4, the shortest Euclidean distance is divided by the shorter side of the corresponding rectangular frame to realize normalization, and if the value is smaller than a preset threshold value T, the material on the construction site is judged to be possibly stolen.
Further, in step S1, the training of the YOLO V3 model includes the following steps:
a1, firstly, constructing a data set of a target monitoring material picture, then amplifying the data set, and then enhancing the collected data set to generate a data set comprising a set number of high-quality pictures; marking the position of the target and the coordinates of the central point of the target on the images in the data set;
a2, constructing a neural network model required by a YOLO V3 framework, wherein a leakage Relu activation function is adopted as an activation function between layers; the conditions for stopping model training include: stopping when the iteration reaches the set number, and stopping when the loss performance converges.
Further, a neural network model required by a YOLO V3 framework is constructed by taking Darknet-53 as a backbone network, the Darknet-53 adopts 3 feature layers with different scales, the feature layers are respectively 13 multiplied by 13, 26 multiplied by 26 and 52 multiplied by 52, and YOLO V3 firstly sets 3 prior frames for each downsampling scale, so that the prior frames with 9 sizes are obtained by clustering; in the entire YOLO V3 structure, with no pooling layer and full connectivity layer, downsampling of the network is achieved by setting the stride of the convolution to 2.
Further, the target monitoring material comprises important materials in a material piling area of a construction site, scattered materials in an auxiliary operation area and important outdoor properties in an office living area.
Further, in step S3, the shortest euclidean distance between the coordinates of the palm key point of the human body and all the rectangular frames is calculated by using the KDTree algorithm, which includes the following steps:
step B1, adding wrist key points of the body skeleton posture detected by the OpenPose algorithm model into a body key point set, and adding the central points of the rectangular frames of all the target monitoring materials monitored by the YOLO V3 algorithm model into a central point set;
step B2, establishing KDTree according to all the central point coordinates in the central point set;
step B3, inserting the coordinates of the wrist key points into the established KDTree, and quickly calculating the shortest Euclidean distance from the coordinates of the wrist key points to all coordinates of the central point set by using a KDTree algorithm, wherein the Euclidean distance expression formula is as follows:
wherein xi represents the ith coordinate of the key point of the wrist, and yi represents the ith coordinate of the central point; by utilizing the KDTree algorithm, the Euclidean distance between the wrist key point and the coordinate of which central point can be obtained without traversing and calculating the Euclidean distances between the wrist key point and the coordinates of all central points.
The present invention also provides a worksite theft monitoring system comprising a memory, a processor, and computer program instructions stored on the memory and executable by the processor, the method steps being carried out when the computer program instructions are executed by the processor.
Compared with the prior art, the invention has the following beneficial effects: the invention provides a construction site theft monitoring method and a system based on OpenPose and YOLO V3, a monitoring image is shot by using a monitoring camera, a key material in an area is monitored by using a YOLO V3 model, an anti-theft mode is started after the construction site is stopped, when a person enters a monitoring range, a video frame with a human body is sent into OpenPose to identify a key point of the body, a wrist key point coordinate is obtained, the shortest Euclidean distance from a palm joint point coordinate of the human body to all rectangular frames is calculated by using a KDTree algorithm, and whether the construction site material is stolen is judged by using the relation between the shortest distance and the corresponding rectangular frame, so that the Euclidean distance from the wrist key point to which central point coordinate is the shortest can be obtained without traversing the Euclidean distances from the wrist key point to all central point coordinates, and the construction site theft monitoring method and the system have good real-time performance and accuracy, important materials in the construction site can be protected from theft.
Drawings
FIG. 1 is a flow chart of a method implementation of an embodiment of the present invention.
FIG. 2 is a schematic diagram of a network model of YOLO V3 in the embodiment of the present invention.
Fig. 3 is a schematic diagram of an identification result of human body key point detection in the embodiment of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, the present embodiment provides a worksite theft monitoring method, including the steps of:
and S1, acquiring a scene image from a monitoring video of a monitoring area by the monitoring camera, detecting a target monitoring material in the image through a deep learning target detection algorithm framework YOLO V3, and identifying and outputting the target monitoring material by using a rectangular frame. Wherein the target monitoring material comprises important materials in a material stacking area of a construction site, scattered materials in an auxiliary operation area and outdoor important property in an office living area.
And step S2, detecting and outputting body skeleton postures of all individuals in the image through a real-time multi-person posture estimation algorithm model OpenPose.
And step S3, integrating two algorithm models, and calculating the shortest Euclidean distance from the coordinates of the palm key points of the human body to all rectangular frames by using a KDTree algorithm.
And step S4, the shortest Euclidean distance is divided by the shorter side of the corresponding rectangular frame to realize normalization, and if the value is smaller than a preset threshold value T, wherein 0< T <1, the material on the construction site is judged to be possibly stolen.
In step S1, the training of the YOLO V3 model includes the following steps:
a1, firstly, constructing a data set of a target monitoring material picture, then amplifying the data set by affine transformation and other methods, and then enhancing the collected data set by histogram stipulation, wiener filtering and other image enhancement means to generate a data set comprising pictures with sufficient quantity and high quality; and marking the position of the target and the coordinates of the central point of the target on the images in the data set.
A2, constructing a neural network model required by a YOLO V3 framework, wherein a leakage Relu activation function is adopted as an activation function between layers, so that the problem of neuron death when an input value is a negative value is solved; the conditions for stopping model training include: stopping when the iteration reaches the set number, and stopping when the loss performance converges.
The YoLO V3 network model is shown in FIG. 2. In this embodiment, a neural network model required by a YOLO V3 framework is constructed by using Darknet-53 as a backbone network, the Darknet-53 adopts 3 feature layers with different scales, which are respectively 13 × 13, 26 × 26 and 52 × 52, and YOLO V3 firstly sets 3 prior frames for each downsampling scale, so as to cluster to obtain prior frames with 9 sizes; in the entire YOLO V3 structure, with no pooling layer and full connectivity layer, downsampling of the network is achieved by setting the stride of the convolution to 2.
In this embodiment, the YOLO V3 model uses the leak ReLU as an activation function and is trained using an end-to-end approach. The loss function used when the YOLO V3 model was subjected to the gradient descent method is as follows:
the first part and the second part are responsible for predicting bbox (boundary box) of an object, the first part represents error values of center point coordinates and ground truth center point mislabels obtained by forward propagation of the image along the neural network, and the second part measures error values of frame width height and ground truth width height obtained by forward propagation of the image along the neural network; the third part represents an error value of the confidence coefficient of the prediction frame containing the target object, and the confidence coefficient of the prediction frame containing the target object reaches 1 after training; the fourth part represents an error value of the confidence coefficient of the prediction frame without the target object, and the confidence coefficient of the prediction widening without the target object is trained to reach 0; the fifth part is a mesh prediction classification error term that contains the target object.
In this embodiment, in step S3, the method for calculating the shortest euclidean distance between the coordinates of the palm key point of the human body and all the rectangular frames by using the KDTree algorithm includes the following steps:
and step B1, adding wrist key points of the body skeleton posture detected by the OpenPose algorithm model into the body key point set, and adding the central points of the rectangular frames of all the target monitoring materials monitored by the YOLO V3 algorithm model into the central point set. The recognition result of the human body key point detection is shown in fig. 3.
And step B2, establishing KDTree according to all the central point coordinates in the central point set.
The specific method for establishing the KDTree comprises the following steps:
c1, calculating the variance of the x-direction feature and the y-direction feature of the central point coordinate set, and selecting the direction feature with large variance as a segmentation feature;
c2, selecting the coordinates of the median of the features as root nodes;
c3, coordinates less than the median are divided into left children and coordinates greater than the median are divided into right children.
And C4, recursively executing the steps C1-C4 until all the coordinates of the central point are added into the KDTree.
Step B3, inserting the coordinates of the wrist key points into the established KDTree, and quickly calculating the shortest Euclidean distance from the coordinates of the wrist key points to all coordinates of the central point set by using a KDTree algorithm, wherein the Euclidean distance expression formula is as follows:
wherein xi represents the ith coordinate of the key point of the wrist, and yi represents the ith coordinate of the central point; by utilizing the KDTree algorithm, the Euclidean distance between the wrist key point and the coordinate of which central point can be obtained without traversing and calculating the Euclidean distances between the wrist key point and the coordinates of all central points.
The specific method for calculating the shortest Euclidean distance comprises the following steps:
d1, inserting the coordinates of the key points of the palm of the human body into the leaf nodes of the established KDTree according to the rules of a binary balanced tree, and stacking all the coordinates of the nodes passing through;
d2, calculating the Euclidean distance between the coordinates of the key points of the palm of the human body and the coordinates of the first center point of the pop-up, and if the distance is shortest, keeping the distance;
d3, calculating the distance between the coordinates of the key points of the palm of the human body and the feature plane of the coordinates of the first central point of the pop-up, if the distance is smaller than the shortest distance, pressing all the coordinates of the children on the other side of the pop-up coordinates, returning to the step D2, and if the distance is larger than the shortest distance, directly returning to the step D2 until the stack is empty and outputting the calculated shortest Euclidean distance.
In step S4, it is prevented that the difference in euclidean distance is too large due to the inconsistency of the patterns of the important materials on the construction site, and it is not easy to select an appropriate threshold to determine whether the construction site material is stolen, so that the obtained shortest euclidean distance is divided by the shorter side of the corresponding rectangular frame to realize normalization, and a standard determination threshold is obtained.
The present embodiment also provides a worksite theft monitoring system for implementing the above-described method, comprising a memory, a processor, and computer program instructions stored on the memory and executable by the processor, which when executed by the processor, enable the above-described method steps to be implemented.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is directed to preferred embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow. However, any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present invention are within the protection scope of the technical solution of the present invention.
Claims (6)
1. A method of site theft monitoring, comprising the steps of:
s1, acquiring a scene image from a monitoring video of a monitoring area by a monitoring camera, detecting a target monitoring material in the image through a deep learning target detection algorithm framework YOLO V3, and identifying and outputting the target monitoring material by using a rectangular frame;
s2, detecting and outputting body skeleton postures of all individuals in the image through a real-time multi-person posture estimation algorithm model OpenPose;
step S3, integrating two algorithm models, and calculating the shortest Euclidean distance from the coordinates of the palm key points of the human body to all rectangular frames by using a KDTree algorithm;
and step S4, the shortest Euclidean distance is divided by the shorter side of the corresponding rectangular frame to realize normalization, and if the value is smaller than a preset threshold value T, the material on the construction site is judged to be possibly stolen.
2. The worksite theft monitoring method according to claim 1, wherein the training of the YOLO V3 model in step S1 comprises the steps of:
a1, firstly, constructing a data set of a target monitoring material picture, then amplifying the data set, and then enhancing the collected data set to generate a data set comprising a set number of high-quality pictures; marking the position of the target and the coordinates of the central point of the target on the images in the data set;
a2, constructing a neural network model required by a YOLO V3 framework, wherein a leakage Relu activation function is adopted as an activation function between layers; the conditions for stopping model training include: stopping when the iteration reaches the set number, and stopping when the loss performance converges.
3. The construction site theft monitoring method according to claim 2, characterized in that, a neural network model required by a YOLO V3 framework is constructed by using Darknet-53 as a backbone network, the Darknet-53 adopts 3 feature layers with different scales, namely 13 × 13, 26 × 26 and 52 × 52, and YOLO V3 firstly sets 3 prior frames for each downsampling scale, so as to cluster to obtain 9 prior frames; in the entire YOLO V3 structure, with no pooling layer and full connectivity layer, downsampling of the network is achieved by setting the stride of the convolution to 2.
4. The worksite theft monitoring method of claim 1, wherein the target monitoring material comprises important material of a worksite material piling area, scattered material of an auxiliary working area, and outdoor important property of an office living area.
5. The worksite theft monitoring method according to claim 1, wherein in step S3, the KDTree algorithm is used to calculate the shortest euclidean distance from the coordinates of the palm key points of the human body to all the rectangular frames, and the method comprises the following steps:
step B1, adding wrist key points of the body skeleton posture detected by the OpenPose algorithm model into a body key point set, and adding the central points of the rectangular frames of all the target monitoring materials monitored by the YOLO V3 algorithm model into a central point set;
step B2, establishing KDTree according to all the central point coordinates in the central point set;
step B3, inserting the coordinates of the wrist key points into the established KDTree, and quickly calculating the shortest Euclidean distance from the coordinates of the wrist key points to all coordinates of the central point set by using a KDTree algorithm, wherein the Euclidean distance expression formula is as follows:
wherein xi represents the ith coordinate of the key point of the wrist, and yi represents the ith coordinate of the central point; by utilizing the KDTree algorithm, the Euclidean distance between the wrist key point and the coordinate of which central point can be obtained without traversing and calculating the Euclidean distances between the wrist key point and the coordinates of all central points.
6. A worksite theft monitoring system comprising a memory, a processor, and computer program instructions stored on the memory and executable by the processor, the computer program instructions, when executed by the processor, being operable to perform the method steps of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111277965.1A CN113989719A (en) | 2021-10-30 | 2021-10-30 | Construction site theft monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111277965.1A CN113989719A (en) | 2021-10-30 | 2021-10-30 | Construction site theft monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113989719A true CN113989719A (en) | 2022-01-28 |
Family
ID=79744986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111277965.1A Pending CN113989719A (en) | 2021-10-30 | 2021-10-30 | Construction site theft monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113989719A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115471787A (en) * | 2022-08-09 | 2022-12-13 | 东莞先知大数据有限公司 | Construction site object stacking detection method and device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629935A (en) * | 2018-05-17 | 2018-10-09 | 山东深图智能科技有限公司 | A kind of method and system for climbing building pivot frame larceny based on video monitoring detection |
| CN110490893A (en) * | 2019-07-18 | 2019-11-22 | 广州大学 | A kind of quick Euclidean distance point cloud segmentation method |
| CN110502965A (en) * | 2019-06-26 | 2019-11-26 | 哈尔滨工业大学 | A kind of construction safety helmet wearing monitoring method based on the estimation of computer vision human body attitude |
| CN113255509A (en) * | 2021-05-20 | 2021-08-13 | 福州大学 | Building site dangerous behavior monitoring method based on Yolov3 and OpenPose |
| CN113450534A (en) * | 2020-03-27 | 2021-09-28 | 海信集团有限公司 | Device and method for detecting approach of children to dangerous goods |
-
2021
- 2021-10-30 CN CN202111277965.1A patent/CN113989719A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629935A (en) * | 2018-05-17 | 2018-10-09 | 山东深图智能科技有限公司 | A kind of method and system for climbing building pivot frame larceny based on video monitoring detection |
| CN110502965A (en) * | 2019-06-26 | 2019-11-26 | 哈尔滨工业大学 | A kind of construction safety helmet wearing monitoring method based on the estimation of computer vision human body attitude |
| CN110490893A (en) * | 2019-07-18 | 2019-11-22 | 广州大学 | A kind of quick Euclidean distance point cloud segmentation method |
| CN113450534A (en) * | 2020-03-27 | 2021-09-28 | 海信集团有限公司 | Device and method for detecting approach of children to dangerous goods |
| CN113255509A (en) * | 2021-05-20 | 2021-08-13 | 福州大学 | Building site dangerous behavior monitoring method based on Yolov3 and OpenPose |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115471787A (en) * | 2022-08-09 | 2022-12-13 | 东莞先知大数据有限公司 | Construction site object stacking detection method and device and storage medium |
| CN115471787B (en) * | 2022-08-09 | 2023-06-06 | 东莞先知大数据有限公司 | Method and device for detecting stacking of objects on site and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kim et al. | Detecting construction equipment using a region-based fully convolutional network and transfer learning | |
| CN109829436B (en) | Multi-face tracking method based on depth appearance characteristics and self-adaptive aggregation network | |
| CN111488804B (en) | Labor insurance product wearing condition detection and identity identification method based on deep learning | |
| Luo et al. | Recognizing diverse construction activities in site images via relevance networks of construction-related objects detected by convolutional neural networks | |
| EP1879149B1 (en) | method and apparatus for tracking a number of objects or object parts in image sequences | |
| CN107833236A (en) | Semantic vision positioning system and method are combined under a kind of dynamic environment | |
| CN104318578A (en) | Video image analyzing method and system | |
| CN113255509A (en) | Building site dangerous behavior monitoring method based on Yolov3 and OpenPose | |
| DeGol et al. | Improved structure from motion using fiducial marker matching | |
| CN109711322A (en) | A kind of people's vehicle separation method based on RFCN | |
| CN104850857B (en) | Across the video camera pedestrian target matching process of view-based access control model spatial saliency constraint | |
| CN101883209A (en) | Method by integrating background model and three-frame difference to detect video background | |
| CN109685145A (en) | A kind of small articles detection method based on deep learning and image procossing | |
| CN104463869A (en) | Video flame image composite recognition method | |
| CN107292269A (en) | Facial image false distinguishing method, storage, processing equipment based on perspective distortion characteristic | |
| CN116563776A (en) | Method, system, medium and equipment for warning illegal behaviors based on artificial intelligence | |
| CN113989719A (en) | Construction site theft monitoring method and system | |
| CN113936210A (en) | Anti-collision method for tower crane | |
| US20050185834A1 (en) | Method and apparatus for scene learning and three-dimensional tracking using stereo video cameras | |
| Kang et al. | Robust visual tracking framework in the presence of blurring by arbitrating appearance-and feature-based detection | |
| CN109522969A (en) | Special article based on deep learning finds method | |
| CN107871315B (en) | Video image motion detection method and device | |
| CN113793251A (en) | Pose determination method and device, electronic equipment and readable storage medium | |
| Han et al. | Multi-sample image-based material recognition and formalized sequencing knowledge for operation-level construction progress monitoring | |
| CN108596121A (en) | A kind of face critical point detection method based on context and structural modeling |
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 |