CN117058586A - Global land illegal activity monitoring method - Google Patents
Global land illegal activity monitoring method Download PDFInfo
- Publication number
- CN117058586A CN117058586A CN202311028105.3A CN202311028105A CN117058586A CN 117058586 A CN117058586 A CN 117058586A CN 202311028105 A CN202311028105 A CN 202311028105A CN 117058586 A CN117058586 A CN 117058586A
- Authority
- CN
- China
- Prior art keywords
- land
- illegal
- coordinates
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000000694 effects Effects 0.000 title abstract description 8
- 238000010276 construction Methods 0.000 claims abstract description 58
- 230000006399 behavior Effects 0.000 claims abstract description 20
- 238000006243 chemical reaction Methods 0.000 claims abstract description 19
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000012805 post-processing Methods 0.000 claims description 7
- 230000000007 visual effect Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 abstract description 9
- 238000013136 deep learning model Methods 0.000 abstract description 6
- 239000000463 material Substances 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 5
- 239000000523 sample Substances 0.000 description 4
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing 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
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
- G06Q50/18—Legal services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Technology Law (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The application discloses a global land illegal activity monitoring method. In order to overcome the defect that manual inspection consumes a great deal of manpower and material resource cost, the inspection and monitoring of the whole domain range cannot be achieved; the remote sensing image has the problems that the remote sensing image acquisition period is long, and timely discovery and timely treatment cannot be realized; the application comprises the following steps: s1: acquiring video stream information, training to obtain a construction vehicle classification extraction model, and extracting suspected land illegal construction vehicles in the video stream information; s2: establishing a conversion relation between video coordinates and geographic coordinates to obtain a suspected land illegal construction vehicle containing real geographic coordinates; s3: and combining the suspicious land illegal construction vehicles containing the real geographic coordinates with land management data, and applying GIS superposition analysis to obtain a land illegal monitoring result. The conversion relation between the video coordinates and the GIS geographic coordinates is established, the deep learning model is used for realizing the monitoring of the global land illegal behaviors, the time for extracting the illegal behaviors is short, and the illegal behaviors can be found and processed in time.
Description
Technical Field
The application relates to the field of land illegal activity monitoring, in particular to a global land illegal activity monitoring method based on a deep learning and view fusion technology.
Background
In recent years, law enforcement regulations of natural resources are highly paid attention to in various places, and the management order of natural resources is continuously good.
At present, in the actual application of land protection, a high-definition high-multiple digital monitoring camera installed on a base station iron tower is mainly utilized to transmit video images to a homeland resource management department, the bottom layer data development sharing and coordination of a monitoring platform probe are embedded into a homeland resource 'one-picture', and real-time online monitoring and supervision of the homeland resource are realized through a manual visual method.
On the one hand, the conventional land illegal activity monitoring method generally adopts a manual inspection mode, and illegal activity is found by manpower. On the other hand, the remote sensing image is used for extracting illegal actions such as newly-added construction land and the like in a visual interpretation mode. For example, a "homeland monitoring service system based on high-resolution remote sensing" disclosed in chinese patent literature, its bulletin number CN112287050a, including homeland inspection mobile phone APP and high-resolution remote sensing big data application platform web page end, both form a coordinated homeland monitoring service system through the database. The patrol personnel uploads the patrol position, the patrol track and the patrol event by using the land patrol mobile phone APP, can call the background management database in real time to carry out parallel analysis processing, and simultaneously analyze the land condition, the land supply use, the batch report condition and the like of the patrol pattern spot, and judge whether the illegal occupation condition exists on the basis of the land condition; the background manager can confirm and process the reported problem types, the treatment progress, the change types and the like in real time, so that the bidirectional line joint quality inspection is realized. The scheme adopts a mode of acquiring the remote sensing image to judge whether illegal behaviors exist or not, the remote sensing image acquisition period is long, the illegal behaviors are extracted for a long time, and timely discovery and timely disposal cannot be achieved.
The manual inspection mode needs to consume a great deal of manpower and material resource cost, and cannot realize the inspection and monitoring of the whole domain range. In another way, the remote sensing image acquisition period is longer, the illegal action extraction is long, and timely discovery and timely treatment cannot be achieved.
Disclosure of Invention
The application mainly solves the problems that the manual inspection mode in the prior art consumes a great deal of labor and material cost and cannot realize the inspection and monitoring in the whole domain; the remote sensing image is long in acquisition period, long in time consumption for extracting illegal behaviors, and incapable of achieving timely discovery and timely treatment; the method for monitoring the global land illegal behaviors is characterized by establishing a conversion relation between video coordinates and GIS geographic coordinates, and realizing the monitoring of the global land illegal behaviors by using a deep learning model.
The technical problems of the application are mainly solved by the following technical proposal:
a global land illegal activity monitoring method comprises the following steps:
s1: acquiring video stream information, training to obtain a construction vehicle classification extraction model, and extracting suspected land illegal construction vehicles in the video stream information;
s2: establishing a conversion relation between video coordinates and geographic coordinates to obtain a suspected land illegal construction vehicle containing real geographic coordinates;
s3: and combining the suspicious land illegal construction vehicles containing the real geographic coordinates with land management data, and applying GIS superposition analysis to obtain a land illegal monitoring result.
According to the scheme, the land illegal construction vehicles are identified through a deep learning model; establishing a conversion relation between video coordinates and GIS geographic coordinates, and obtaining land illegal construction vehicles which are truly geographic coordinates through conversion; and the method is combined with a land management system to obtain a final land illegal monitoring result, so that the time for extracting illegal behaviors is short, and the illegal behaviors can be found and processed in time.
Preferably, the step S1 specifically includes the following steps:
s101: obtaining video pictures frame by frame through the video stream address;
s102: analyzing construction vehicle interpretation marks and characteristics in the video pictures by a visual interpretation method, and manually marking samples;
s103: based on a convolutional neural network, inputting marked sample pictures for training, and constructing a construction vehicle classification extraction model;
s104: and inputting the video stream information into a trained construction vehicle classification extraction model, outputting a prediction result, and obtaining a final construction vehicle after post-processing.
And identifying the land illegal construction vehicles through the deep learning model, so that the subsequent land illegal behavior judgment is facilitated.
Preferably, the construction vehicle comprises a loader, a bulldozer, an excavator, a road roller and a concrete mixer truck. The variety is complete.
Preferably, the post-treatment includes:
removing a high-speed moving object and a completely stationary object by comparing the construction vehicle shapes extracted from a plurality of continuous video pictures;
and the agricultural operation vehicle is removed through multi-view and multi-focal length identification.
By post-processing, the accuracy of construction vehicle extraction can be improved, and agricultural vehicles, parked vehicles and passing vehicles can be eliminated.
Preferably, the step S2 includes the following steps:
s201: collecting camera parameter information, wherein the parameter information comprises an initial focal length, a target surface size, a vertical field angle, a camera mounting height, an initial direction angle and longitude and latitude;
s202: establishing a three-dimensional model for simulating camera imaging; the rendered size of the model is matched to the size of the object imaged on the negative.
S203: and calculating a three-dimensional model of the land which takes the camera as an origin and is the same as the actual land by using the camera mounting height, the land longitude and latitude and the camera longitude and latitude, and calculating the conversion relation between the video coordinates and the geographic coordinates through the three-dimensional model.
And converting the camera coordinates into actual geographic coordinates for combining local land management data to judge land illegal behaviors.
Preferably, the specific coordinate conversion includes:
1) Acquiring screen coordinates taking the lower left corner of a picture as an origin;
2) Converting the screen coordinates into normalized coordinates of the clipping space, wherein the normalized coordinates z are 1;
3) The normalized coordinates are converted into observation space coordinates;
4) The space coordinate is observed and inversely transformed into the space coordinate of the land block;
5) And obtaining a ray vector taking the camera as an origin, and calculating an intersection point with the ground to obtain the longitude and latitude of the actual shooting object.
Preferably, the direction angle, the pitch angle and the focal length of a camera in the video stream information are used as parameters, and the suspected land illegal construction vehicle containing real geographic coordinates is obtained by using a coordinate conversion relation. Both the plot and the camera are converted into projection coordinates, and the plot coordinates minus the camera coordinates become plane coordinates centered on the camera. Spatial attributes are assigned to suspected illicit acts.
Preferably, the method comprises the steps of combining the suspected illegal construction vehicles with the land management data, applying GIS superposition analysis, judging the suspected illegal construction vehicles which are not in the data range of land report, land supply, land parcel evidence, temporary land use and facility agricultural land as illegal, and obtaining illegal monitoring results.
And (5) performing nesting business data analysis to obtain a land illegal behavior monitoring result.
The beneficial effects of the application are as follows:
identifying land illegal construction vehicles through a deep learning model; establishing a conversion relation between video coordinates and GIS geographic coordinates, and obtaining land illegal construction vehicles which are truly geographic coordinates through conversion; and the method is combined with a land management system to obtain a final land illegal monitoring result, so that the time for extracting illegal behaviors is short, and the illegal behaviors can be found and processed in time.
Drawings
FIG. 1 is a flow chart of a global land violation monitoring method of the present application.
Detailed Description
The technical scheme of the application is further specifically described below through examples and with reference to the accompanying drawings.
Examples:
the method for monitoring the illegal actions of the global land according to the embodiment, as shown in fig. 1, comprises the following steps:
s1: and acquiring video stream information, training to obtain a construction vehicle classification extraction model, and extracting suspected illegal land construction vehicles in the video stream information.
S101: and obtaining video pictures frame by frame through the video stream address.
The common video stream information mainly obtains video pictures frame by frame through video stream addresses. And acquiring each frame of picture of the video through an RTSP stream address provided by the camera.
S102: construction vehicle interpretation signs and features in the video pictures were analyzed by visual interpretation, and samples were manually marked.
And generating construction vehicle interpretation marks and characteristics in the pictures extracted frame by a visual interpretation analysis module according to the data such as actual adjustment and the like, and manually marking the samples.
Construction vehicles include, but are not limited to, loaders, dozers, excavators, road rollers, and concrete mixer trucks.
S103: based on the convolutional neural network, inputting marked sample pictures for training, and constructing a construction vehicle classification extraction model.
S104: and inputting the video stream information into a trained construction vehicle classification extraction model, outputting a prediction result, and obtaining a final construction vehicle after post-processing.
In this embodiment, a construction vehicle classification extraction model is constructed based on Yolo v3 (convolutional neural network), a marked sample picture is input and trained, and finally the construction vehicle classification extraction model is obtained. And (3) taking video data used in production into an extraction model, outputting a prediction result, and obtaining the final construction vehicle through a series of post-processing.
The post-treatment method mainly comprises the steps of removing high-speed moving objects, removing completely stationary objects and removing the agricultural work vehicle.
By comparing the extracted forms of the plurality of picture objects before and after, the high-speed moving object and the completely stationary object can be removed. And the agricultural operation vehicle is removed through multi-view and multi-focal length identification. By post-processing, the accuracy of construction vehicle extraction can be improved, and agricultural vehicles, parked vehicles and passing vehicles can be eliminated.
S2: and establishing a conversion relation between the video coordinates and the geographic coordinates to obtain the suspected illegal land construction vehicle containing the real geographic coordinates.
S201: and acquiring camera parameter information, wherein the parameter information comprises an initial focal length, a target surface size, a vertical field angle, a camera mounting height, an initial direction angle and longitude and latitude.
S202: establishing a three-dimensional model for simulating camera imaging; the rendered size of the model is matched to the size of the object imaged on the negative.
S203: and calculating a three-dimensional model of the land which takes the camera as an origin and is the same as the actual land by using the camera mounting height, the land longitude and latitude and the camera longitude and latitude, and calculating the conversion relation between the video coordinates and the geographic coordinates through the three-dimensional model.
The specific coordinate transformation comprises the following steps:
1) And acquiring screen coordinates taking the lower left corner of the picture as an origin.
The process of obtaining the X-coordinate of the video point with respect to the lower left corner is expressed as:
pixelX=(evt.clientX - rect.left)*canvas.width/canvas.clientWidth
the process of obtaining the Y-coordinate of the video point with respect to the lower left corner is expressed as:
pixelY = canvas.height -(evt.clientY - rect.top)*canvas.height/canvas.clientheight
where pixelX and pixelY are the X and Y coordinates, respectively, of the video point relative to the lower left corner.
The evt.clientX and evt.clientY are the x-coordinate and Y-coordinate, respectively, of the video point.
rect. Left is the leftmost coordinate; top is the top coordinate.
canvas.width and canvas.height are picture width and height, respectively.
In this embodiment, screen coordinates with the lower left corner of the screen as the origin are acquired, resulting in screen coordinates [776.11,619.96].
2) The screen coordinates are converted into clipping space normalized coordinates, and the normalized coordinates z are 1.
The process of obtaining the normalized X-coordinate of the video point relative to the lower left corner is expressed as:
ndcX = 2 *(pixelX / canvas.width)- 1
the process of obtaining the normalized Y coordinate of the video point with respect to the lower left corner is expressed as:
ndcY = 2 *(pixelY / canvas.height)- 1
where ndcX and ndcY are normalized X and Y coordinates, respectively.
In this embodiment, the screen coordinates are converted into clipping space normalized coordinates, and the normalized coordinates z are 1 to obtain [0.4657,0.9935].
3) The normalized coordinates are converted into viewing space coordinates.
In this embodiment, the normalized coordinates are converted into observation space coordinates (the observation direction of the observation space is obtained), the normalized coordinates cannot be calculated by multiplying the inverse matrix, and the inverse calculation is performed when the projection matrix is multiplied by the observation space coordinates to obtain [170.33,204.37].
4) The observed spatial coordinates are inverse transformed to the plot spatial coordinates.
In this embodiment, the inverse transform of the viewing space coordinates is performed to the block space coordinates (world coordinates) [6037.08, -280.04,8004.53].
5) And obtaining a ray vector taking the camera as an origin, and calculating an intersection point with the ground to obtain the longitude and latitude of the actual shooting object.
In the embodiment, the ray vector formed by the camera coordinates and the video midpoint coordinates calculated in the previous step is used for calculating the intersection point between the camera coordinates and the ground, so as to obtain the longitude and latitude [40490742.880,3624048.26] of the actual shooting object.
Spatial attributes are assigned to suspected illicit acts.
And taking the obtained high-resolution image as a basis, taking the direction angle, the pitch angle and the focal length of a camera of the suspected illegal construction vehicle in the video stream information as parameters, and obtaining the suspected illegal construction vehicle containing real geographic coordinates by using a coordinate conversion relation.
Both the plot and the camera are converted into projection coordinates, and the plot coordinates minus the camera coordinates become plane coordinates centered on the camera.
S3: and combining the suspicious land illegal construction vehicles containing the real geographic coordinates with land management data, and applying GIS superposition analysis to obtain a land illegal monitoring result.
And combining the suspected illegal land construction vehicles with the real geographic coordinates with land management data, applying GIS superposition analysis, and judging the suspected illegal land construction vehicles which are not in the data range of land reporting, land supply, land parcel evidence, temporary land use and facility agricultural land as illegal land, thereby obtaining illegal land monitoring results.
And (5) performing nesting business data analysis to obtain a land illegal behavior monitoring result.
According to the scheme of the embodiment, the land illegal construction vehicles are identified through a deep learning model; establishing a conversion relation between video coordinates and GIS geographic coordinates, and obtaining land illegal construction vehicles which are truly geographic coordinates through conversion; and the method is combined with a land management system to obtain a final land illegal monitoring result, so that the time for extracting illegal behaviors is short, and the illegal behaviors can be found and processed in time.
It should be understood that the examples are only for illustrating the present application and are not intended to limit the scope of the present application. Furthermore, it should be understood that various changes and modifications can be made by one skilled in the art after reading the teachings of the present application, and such equivalents are intended to fall within the scope of the application as defined in the appended claims.
Claims (8)
1. The method for monitoring the illegal behaviors of the global land is characterized by comprising the following steps of:
s1: acquiring video stream information, training to obtain a construction vehicle classification extraction model, and extracting suspected land illegal construction vehicles in the video stream information;
s2: establishing a conversion relation between video coordinates and geographic coordinates to obtain a suspected land illegal construction vehicle containing real geographic coordinates;
s3: and combining the suspicious land illegal construction vehicles containing the real geographic coordinates with land management data, and applying GIS superposition analysis to obtain a land illegal monitoring result.
2. The method for monitoring global land violation according to claim 1, wherein the step S1 specifically comprises the following steps:
s101: obtaining video pictures frame by frame through the video stream address;
s102: analyzing construction vehicle interpretation marks and characteristics in the video pictures by a visual interpretation method, and manually marking samples;
s103: based on a convolutional neural network, inputting marked sample pictures for training, and constructing a construction vehicle classification extraction model;
s104: and inputting the video stream information into a trained construction vehicle classification extraction model, outputting a prediction result, and obtaining a final construction vehicle after post-processing.
3. A method of monitoring global land violation as claimed in claim 1 or 2, wherein said construction vehicles include loaders, dozers, excavators, road rollers and concrete mixer trucks.
4. A method of global land violation monitoring according to claim 2, wherein said post-processing comprises:
removing a high-speed moving object and a completely stationary object by comparing the construction vehicle shapes extracted from a plurality of continuous video pictures;
and the agricultural operation vehicle is removed through multi-view and multi-focal length identification.
5. A method for monitoring global land violation as claimed in claim 1, wherein said step S2 comprises the following steps:
s201: collecting camera parameter information, wherein the parameter information comprises an initial focal length, a target surface size, a vertical field angle, a camera mounting height, an initial direction angle and longitude and latitude;
s202: establishing a three-dimensional model for simulating camera imaging;
s203: and calculating a three-dimensional model of the land which takes the camera as an origin and is the same as the actual land by using the camera mounting height, the land longitude and latitude and the camera longitude and latitude, and calculating the conversion relation between the video coordinates and the geographic coordinates through the three-dimensional model.
6. A method of global land violation monitoring according to claim 1 or 5, characterized in that a specific coordinate transformation comprises:
1) Acquiring screen coordinates taking the lower left corner of a picture as an origin;
2) Converting the screen coordinates into normalized coordinates of the clipping space, wherein the normalized coordinates z are 1;
3) The normalized coordinates are converted into observation space coordinates;
4) The space coordinate is observed and inversely transformed into the space coordinate of the land block;
5) And obtaining a ray vector taking the camera as an origin, and calculating an intersection point with the ground to obtain the longitude and latitude of the actual shooting object.
7. The method for monitoring the global land violation behavior according to claim 6, wherein the direction angle, the pitch angle and the focal length of a camera of the suspected land violation construction vehicle in the video stream information are taken as parameters, and a coordinate conversion relation is used for obtaining the suspected land violation construction vehicle containing real geographic coordinates.
8. The method for monitoring the illegal actions of the global land according to claim 1 or 7, wherein the method is characterized in that the suspected illegal construction vehicles containing real geographic coordinates are combined with land management data, GIS superposition analysis is applied, and the suspected illegal construction vehicles which are not in the data range of land report, land supply, land parcel evidence, temporary land and facility agricultural land are judged to be illegal, so that an illegal monitoring result is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311028105.3A CN117058586A (en) | 2023-08-15 | 2023-08-15 | Global land illegal activity monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311028105.3A CN117058586A (en) | 2023-08-15 | 2023-08-15 | Global land illegal activity monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117058586A true CN117058586A (en) | 2023-11-14 |
Family
ID=88654759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311028105.3A Pending CN117058586A (en) | 2023-08-15 | 2023-08-15 | Global land illegal activity monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117058586A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117953430A (en) * | 2024-03-15 | 2024-04-30 | 湖南省第二测绘院 | Method and system for monitoring farmland damage in real time through communication iron tower video |
-
2023
- 2023-08-15 CN CN202311028105.3A patent/CN117058586A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117953430A (en) * | 2024-03-15 | 2024-04-30 | 湖南省第二测绘院 | Method and system for monitoring farmland damage in real time through communication iron tower video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tan et al. | Automatic detection of sewer defects based on improved you only look once algorithm | |
| Hadjidemetriou et al. | Automated pavement patch detection and quantification using support vector machines | |
| Chuang et al. | Pavement performance monitoring and anomaly recognition based on crowdsourcing spatiotemporal data | |
| Maeda et al. | Road damage detection and classification using deep neural networks with smartphone images | |
| Koch et al. | A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure | |
| CN110598784B (en) | Machine learning-based construction waste classification method and device | |
| US9365217B2 (en) | Mobile pothole detection system and method | |
| Rathore et al. | Smart traffic control: Identifying driving-violations using fog devices with vehicular cameras in smart cities | |
| Hadjidemetriou et al. | Vision-and entropy-based detection of distressed areas for integrated pavement condition assessment | |
| CN112307989B (en) | Road surface object identification method, device, computer equipment and storage medium | |
| CN110659546B (en) | Illegal booth detection method and device | |
| CN112800911A (en) | Pavement damage rapid detection and natural data set construction method | |
| Bello-Salau et al. | Image processing techniques for automated road defect detection: A survey | |
| Lingani et al. | Smart traffic management system using deep learning for smart city applications | |
| Radopoulou et al. | A framework for automated pavement condition monitoring | |
| CN110852236A (en) | Target event determination method and device, storage medium and electronic device | |
| CN117058586A (en) | Global land illegal activity monitoring method | |
| CN112084892B (en) | Road abnormal event detection management device and method thereof | |
| Baduge et al. | Assessment of crack severity of asphalt pavements using deep learning algorithms and geospatial system | |
| Guan et al. | Multi-scale asphalt pavement deformation detection and measurement based on machine learning of full field-of-view digital surface data | |
| CN115497242A (en) | Intelligent monitoring system and monitoring method for foreign matter invasion in railway business line construction | |
| CN114494845A (en) | Artificial intelligence hidden danger troubleshooting system and method for construction project site | |
| CN111539363A (en) | Highway rockfall identification and analysis method | |
| Al-Suleiman et al. | Assessment of the effect of alligator cracking on pavement condition using WSN-image processing | |
| CN104299002B (en) | A kind of tower crane image detecting method based on monitoring system |
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 |