CN110765900A - DSSD-based automatic illegal building detection method and system - Google Patents

DSSD-based automatic illegal building detection method and system Download PDF

Info

Publication number
CN110765900A
CN110765900A CN201910956710.4A CN201910956710A CN110765900A CN 110765900 A CN110765900 A CN 110765900A CN 201910956710 A CN201910956710 A CN 201910956710A CN 110765900 A CN110765900 A CN 110765900A
Authority
CN
China
Prior art keywords
dssd
image
images
neural network
based automatic
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
Application number
CN201910956710.4A
Other languages
Chinese (zh)
Other versions
CN110765900B (en
Inventor
江寅
朱传瑞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Pan Public Mdt Infotech Ltd
Original Assignee
Anhui Pan Public Mdt Infotech Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Anhui Pan Public Mdt Infotech Ltd filed Critical Anhui Pan Public Mdt Infotech Ltd
Priority to CN201910956710.4A priority Critical patent/CN110765900B/en
Publication of CN110765900A publication Critical patent/CN110765900A/en
Application granted granted Critical
Publication of CN110765900B publication Critical patent/CN110765900B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/176—Urban or other man-made structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Abstract

The invention relates to the field of illegal building image recognition, in particular to a DSSD-based automatic illegal building detection method and system. The method comprises the steps that an image workstation acquires a collected illegal building picture, then a DSSD neural network is used for distinguishing, and finally a result obtained by processing of a detection system is sent to a system terminal. The invention completes an automatic detection violation building system based on an intelligent image processing technology and a neural network, can reduce the workload of manual identification to a certain extent, and has important significance for urban dynamic monitoring, violation building identification, geographic information updating and the like.

Description

DSSD-based automatic illegal building detection method and system
Technical Field
The invention relates to the technical field of illegal building image identification, in particular to a DSSD-based automatic illegal building detection method and a DSSD-based automatic illegal building detection system.
Background
The building change detection is one of important contents of geographic national condition monitoring, and has important significance for illegal building identification, city dynamic monitoring, geographic information updating and the like. Taking urban illegal building detection as an example, along with the continuous development of the economic society of China, the urbanization process is continuously accelerated, urban buildings are continuously increased, the number and the scale of illegal buildings are also continuously increased, the phenomenon not only destroys urban planning and urban landscape, but also influences urban image and resident life, is a hotspot problem concerned by common people, is a difficult problem of urban management, and is one of negative factors influencing social harmony. At present, the 'law enforcement cost is low and the law enforcement cost is high' is one of the main reasons for repeated prohibition of illegal buildings, besides the lack of related legal links, the detection aspect of the illegal buildings is weak, and due to the lack of automatic monitoring means for the illegal buildings, the mode of utilizing manual inspection has a plurality of disadvantages, namely, the period of the discovery process is long, and the large-scale monitoring cost is high. In recent years, illegal building detection is attempted by using satellite image data in cities such as Beijing, but the automatic analysis technology of image information is still not mature enough, and the specific gravity of manual identification and verification participation in the process is large. Billions of manpower and material resources are invested by land law enforcement, city management, nationwide each year for this task. The method with high automation degree, robustness and reliability is urgently needed in the market to detect urban illegal buildings, so that the renovation process of the urban illegal buildings is promoted.
Disclosure of Invention
The invention aims to provide a DSSD-based automatic illegal building detection method and a DSSD-based automatic illegal building detection system, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a DSSD-based automatic illegal building detection method comprises the following steps:
step 1: the image workstation is responsible for acquiring images of the building area, firstly carries out image definition pretreatment on the images, and then sends the images into the detection system for image processing;
step 2: the detection system divides the collected images into a training set and a testing set for processing and analysis, wherein: the training set and the test set comprise preprocessing, labeling and neural network discrimination;
and step 3: and sending the identification result to a system terminal, and delivering the identification result to a user for final diagnosis as an auxiliary diagnosis result.
Preferably, the training set and test set preprocessing comprises multi-scale image denoising and enhancing, labeling the training set and test set images, and putting the training set and test set images into a DSSD neural network for training and recognition.
Preferably, the DSSD neural network includes a feature layer, a deconvolution module, a deconvolution layer, and a prediction module.
Preferably, the characteristic layer is 6 layers, the structure of which is a ResNet 101-based network, the conv3_ x layer is used as a convolution layer in the ResNet101, and the following five layers are a series of gradually-reduced convolution layers; the prediction module is formed by adding a residual error unit on the basis of the SSD prediction module (a), and performing convolution processing on an original feature map in a residual error bypass and performing inter-channel addition on the feature map of a network trunk road.
Preferably, the DSSD neural network identifies lesions based on a regression and classification process, wherein: generating the recognition frame is a regression process, and judging the category to which the lesion in the recognition frame belongs is a classification process, so that the overall objective loss function is the weighted sum of the localization loss and the confidence loss:
Figure BDA0002227574050000021
where N is the number of default bounding boxes corresponding to the true bounding box, c is the confidence of each class, α is the weight term set to 1, the localization loss Lloc(x, l, g) is the smooth between the prediction box l and the real target box gL1And (4) loss. l ═ l (l)x,ly,lw,lh) Each item respectively represents the central position (x, y) of the predicted frame and the width w and the height h of the frame; g ═ g (g)x,gy,gw,gh) Each item represents the center position (x, y) of the real target and the width w and the height h of the frame of the real target respectively,
Figure BDA0002227574050000031
confidence loss Lconf(x, c) is the Softmax loss for multiple classes of confidence:
Figure BDA0002227574050000035
preferably, K clustering centers of lesion aspect ratio are obtained using a K-means clustering algorithm, and an optimal K value is determined using an elbow method, the core indicators of which are SSE (sum of the squared errors):
Figure BDA0002227574050000036
wherein, ciIs the ith cluster, p is ciSample point of (1), miIs ciCenter of mass (c)iAverage value of all samples) and SSE is the clustering error of all samples, which represents the good or bad clustering effect, when K is smaller than the real clustering number, the descending amplitude of the SSE is large, and when K reaches the real clustering number, the descending amplitude of the SSE is reduced, therefore, the width and the height of the focus are obtained from the label file, so as to obtain the aspect ratio, and then the K-means algorithm is operated by taking the aspect ratio as the characteristic.
The invention also provides a DSSD-based automatic illegal building detection method, which comprises the following steps:
the image workstation is used for collecting the images of the building area and uploading the collected images to the detection system for image processing;
the detection system divides the collected images into a training set and a test set for processing and analysis, and then sends the images to a DSSD neural network;
the DSSD neural network is used for training and identifying the processing analysis images uploaded by the detection system and then sending the identification result to the system terminal;
and the detection system receives the identification result and delivers the identification result as an auxiliary diagnosis result to a user for final diagnosis.
Preferably, the detection system comprises training set and test set preprocessing, labeling and DSSD neural network discrimination.
Preferably, the training set and test set preprocessing includes multi-scale image denoising and enhancement.
Preferably, the image workstation comprises a photographing device and an image scanning device, the photographing device photographs the building area, and the image scanning device performs image definition preprocessing on the picture photographed by the photographing device; wherein: the photographing device can adopt an unmanned aerial vehicle, the image scanning device is based on a PC, and Matlab710 based on Retinex image enhancement algorithm is installed in the PC.
Compared with the prior art, the invention has the beneficial effects that:
the invention can provide effective auxiliary diagnosis information, and the invention completes an automatic detection violation building system based on intelligent image processing technology and neural network, can reduce the workload of manual identification to a certain extent, and has important significance for city dynamic monitoring, violation building identification, geographic information update and the like.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a flow chart of the system operation of the present invention;
FIG. 3 is a schematic diagram of a DSSD neural network structure according to the present invention;
FIG. 4 is a schematic diagram of a deconvolution module structure of a DSSD neural network according to the present invention;
FIG. 5 is a schematic diagram of the prediction module structure of the DSSD neural network in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 5, the present invention provides a technical solution:
referring to fig. 1, the DSSD-based automatic illegal building detection system comprises an image workstation, a detection system and a system terminal. The image workstation is responsible for collecting the image collection of the building area. The detection system comprises training set and test set preprocessing, labeling and neural network discrimination. The training set and the test set preprocessing comprise multi-scale image denoising and enhancing. The judgment mainly utilizes a DSSD neural network.
By adopting the DSSD neural network, the DSSD designs the deconvolution module to fuse the semantic information of each feature extraction layer, so that the DSSD has more excellent performance on detection precision and small focus target detection capability. The structure is shown in fig. 2, and the basic network is ResNet101, wherein the conv3_ x layer is a convolutional layer in ResNet101, and the five layers are a series of tapered convolutional layers, which together serve as the characteristic layer (total 6 layers) of the DSSD network. After that the DSSD adds a series of deconvolution layers and designs a deconvolution module to fuse the previous feature layer (conv3_ x, convolution layer) and the deconvolution layer. In addition, the DSSD also designs a new prediction module and moves the prediction to a deconvolution layer for processing.
The function of the deconvolution module is to fuse the high-level feature mapping information with the low-level feature mapping information, and the structure is shown in fig. 2. It can be seen that DSSD uses learned deconvolution layers instead of bilinear upsampling, and adds a normalization layer after each convolution layer. In addition, DSSDs use an element dot product based approach to achieve better accuracy when combining higher-level feature mapping and lower-level feature mapping.
The prediction module of the DSSD is shown in the following figure 4, which is a new prediction module (b) formed by adding a residual unit on the basis of the SSD prediction module (a), performing convolution processing on an original feature map in a residual bypass, and performing inter-channel addition on the feature map of a network main road.
DSSD identification of lesions is a process of regression and classification. The generation of the recognition frame is a regression process, and the judgment of the category of the focus in the recognition frame is a classification process. Thus, the overall objective loss function is a weighted sum of the localization loss and the confidence loss:
where N is the number of default bounding boxes corresponding to the true bounding box, c is the confidence of each class, α is the weight term set to 1, the localization loss Lloc(x, l, g) is the smooth between the prediction box l and the real target box gL1And (4) loss. l ═ l (l)x,ly,lw,lh) Each item respectively represents the central position (x, y) of the predicted frame and the width w and the height h of the frame; g ═ g (g)x,gy,gw,gh) Each item represents the center position (x, y) of the real target and the width w and height h of its border, respectively.
Figure BDA0002227574050000062
Figure BDA0002227574050000063
Figure BDA0002227574050000064
Figure BDA0002227574050000065
Confidence loss Lconf(x, c) is the Softmax loss for multiple classes of confidence:
Figure BDA0002227574050000066
Figure BDA0002227574050000067
as known from the DSSD identification process, the more the number of the aspect ratios is, the more the number of the prior frames is, the more the prior frames can be found, so that the detection accuracy is improved, but more time is spent in predicting and performing NMS. It is important to choose a suitable aspect ratio. Therefore, we re-choose the aspect ratio of the prior frame for the own data set.
K clustering centers of lesion aspect ratio are obtained using K-means clustering algorithm and the optimal K value is determined using elbow method. The core indicators of the elbow method are SSE (sum of the squared errors):
Figure BDA0002227574050000071
wherein, ciIs the ith cluster, p is ciSample point of (1), miIs ciCenter of mass (c)iMean of all samples), SSE is the clustering error of all samples, and represents how good the clustering effect is. When k is smaller than the true cluster number, the magnitude of the SSE drop is large, and when k reaches the true cluster number, the magnitude of the SSE drop is abruptly decreased. Therefore, the width and height of the lesion are obtained from the tag file to obtain the aspect ratio, and then the K-means algorithm is run by taking the aspect ratio as a characteristic.
And finally, sending the identification result to a system terminal, and giving the identification result to a user (user) as an auxiliary diagnosis result for final identification to obtain the position of the violation building.
The technical scheme of the invention is as follows:
a DSSD-based automatic illegal building detection method comprises an image workstation, a detection system and a system terminal. The image workstation is responsible for collecting the images of the building area. The detection system comprises training set and test set preprocessing, labeling and neural network discrimination. The training set and the test set preprocessing comprise multi-scale image denoising and enhancing. The judgment mainly utilizes a DSSD neural network. According to the invention, the unmanned aerial vehicle is used as the photographing equipment, low-altitude photographing can be carried out through the unmanned aerial vehicle, and the manual photographing difficulty and workload are reduced. The unmanned aerial vehicle shoots buildings (including illegal buildings) in a city or other regions according to a preset route, an obtained picture image is input into image scanning equipment for preprocessing, the preprocessing is carried out under a Windows XP or above operating system by adopting a computer (PC), Matlab710 based on a Retinex image enhancement algorithm is installed in the Windows XP, and the picture or the photo shot by the unmanned aerial vehicle can be subjected to sharpening processing based on the Retinex algorithm. Because unmanned aerial vehicle is at the in-process of taking a picture and collecting evidence, there is the influence of weather or other factors, for example there is the haze condition or receives the wind fast disturbance and make the photo of taking a picture greatly reduced in the whole contrast and the luminance of image, image color distortion. By adopting the Retinex post-processing of the restored image, the image is integrally enhanced, the detail information of the image is enhanced, the edge is clear, the image color information is further enhanced, the image color is better recovered, and the purpose of enhancing the highlight area is achieved. The Matlab710 based on the Retinex image enhancement algorithm is the prior art, and specifically, reference may be made to the image enhancement algorithm based on the Retinex principle-article number: 1009-3044(2018)11-0185-02, a method for improving the definition of a foggy image-article No. 100325060(2011)0120083204 and the like.
The working principle and the working process of the invention are as follows:
1. the image workstation is responsible for collecting images of the building area, firstly carries out image definition preprocessing on the images, and then sends the images into the detection system for image processing.
2. The detection system divides the collected images into a training set and a test set for processing and analysis. The method comprises training set and test set preprocessing, labeling and neural network discrimination. Wherein the training set and test set preprocessing includes multi-scale image denoising and enhancement. And marking the training set and the test set images, and putting the training set and the test set images into a DSSD neural network for training and recognition.
3. And the identification result is sent to the system terminal and is used as an auxiliary diagnosis result to be delivered to the user for final diagnosis, so that the exact position of the illegal building in the city or other areas can be obtained, and the illegal building can be conveniently removed by law enforcement departments.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (10)

1. A DSSD-based automatic illegal building detection method is characterized by comprising the following steps:
step 1: the image workstation is responsible for acquiring images of the building area, firstly carries out image definition pretreatment on the images, and then sends the images into the detection system for image processing;
step 2: the detection system divides the collected images into a training set and a testing set for processing and analysis, wherein: the training set and the test set comprise preprocessing, labeling and neural network discrimination;
and step 3: and sending the identification result to a system terminal, and delivering the identification result to a user for final diagnosis as an auxiliary diagnosis result.
2. The DSSD-based automatic illegal building detection method according to claim 1, characterized in that: the training set and test set preprocessing comprises multi-scale image denoising and enhancing, labeling the training set and test set images, and putting the training set and test set images into a DSSD neural network for training and recognition.
3. The DSSD-based automatic illegal building detection method according to claim 2, characterized in that: the DSSD neural network comprises a feature layer, a deconvolution module, a deconvolution layer and a prediction module.
4. The DSSD-based automatic construction violation detection method according to claim 3, wherein: the characteristic layer is 6 layers, the structure of the characteristic layer is based on ResNet101, a conv3_ x layer is used as a convolution layer in ResNet101, and the following five layers are a series of gradually-reduced convolution layers; the prediction module is formed by adding a residual error unit on the basis of the SSD prediction module (a), and performing convolution processing on an original feature map in a residual error bypass and performing inter-channel addition on the feature map of a network trunk road.
5. The DSSD-based automatic illegal building detection method according to any one of claims 2-4, characterized in that: DSSD neural network identification lesion regression and classification based process, wherein: generating the recognition frame is a regression process, and judging the category to which the lesion in the recognition frame belongs is a classification process, so that the overall objective loss function is the weighted sum of the localization loss and the confidence loss:
Figure FDA0002227574040000011
where N is the number of default bounding boxes corresponding to the true bounding box, c is the confidence of each class, α is the weight term set to 1, the localization loss Lloc(x, l, g) is the smooth between the prediction box l and the real target box gL1And (4) loss. l ═ l (l)x,ly,lw,lh) Each item respectively represents the central position (x, y) of the predicted frame and the width w and the height h of the frame; g ═ g (g)x,gy,gw,gh) Each item represents the center position (x, y) of the real target and the width w and the height h of the frame of the real target respectively,
Figure FDA0002227574040000022
Figure FDA0002227574040000023
Figure FDA0002227574040000024
confidence loss Lconf(x, c) is the Softmax loss for multiple classes of confidence:
Figure FDA0002227574040000025
6. the DSSD-based automatic construction violation detection method according to claim 5, wherein: k clustering centers of lesion aspect ratio are obtained using a K-means clustering algorithm, and an optimal K value is determined using an elbow method, the core indicator of which is SSE (sum of the squared errors):
wherein, ciIs the ith cluster, p is ciSample point of (1), miIs ciCenter of mass (c)iAverage value of all samples) and SSE is the clustering error of all samples, which represents the good or bad clustering effect, when K is smaller than the real clustering number, the descending amplitude of the SSE is large, and when K reaches the real clustering number, the descending amplitude of the SSE is reduced, therefore, the width and the height of the focus are obtained from the label file, so as to obtain the aspect ratio, and then the K-means algorithm is operated by taking the aspect ratio as the characteristic.
7. A DSSD-based automatic violation building detection system as recited in any one of claims 1 to 6, comprising:
the image workstation is used for collecting the images of the building area and uploading the collected images of the buildings against the regulations to the detection system for image processing;
the detection system divides the collected images into a training set and a test set for processing and analysis, and then sends the images to a DSSD neural network;
the DSSD neural network is used for training and identifying the processing analysis images uploaded by the detection system and then sending the identification result to the system terminal;
and the detection system receives the identification result and delivers the identification result as an auxiliary diagnosis result to a user for final diagnosis.
8. The DSSD-based automatic detection violation construction system according to claim 6, wherein: the detection system comprises training set and test set preprocessing, labeling and DSSD neural network discrimination.
9. The DSSD-based automatic detection violation construction system according to claim 8, wherein: training set and test set preprocessing includes multi-scale image denoising and enhancement.
10. The DSSD-based automatic detection violation construction system according to claim 8, wherein: the image workstation comprises a photographing device and an image scanning device, wherein the photographing device photographs the building area, and the image scanning device performs image definition preprocessing on the picture photographed by the photographing device; wherein: the photographing device can adopt an unmanned aerial vehicle, the image scanning device is based on a PC, and Matlab710 based on Retinex image enhancement algorithm is installed in the PC.
CN201910956710.4A 2019-10-10 2019-10-10 Automatic detection illegal building method and system based on DSSD Active CN110765900B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910956710.4A CN110765900B (en) 2019-10-10 2019-10-10 Automatic detection illegal building method and system based on DSSD

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910956710.4A CN110765900B (en) 2019-10-10 2019-10-10 Automatic detection illegal building method and system based on DSSD

Publications (2)

Publication Number Publication Date
CN110765900A true CN110765900A (en) 2020-02-07
CN110765900B CN110765900B (en) 2023-09-05

Family

ID=69331587

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910956710.4A Active CN110765900B (en) 2019-10-10 2019-10-10 Automatic detection illegal building method and system based on DSSD

Country Status (1)

Country Link
CN (1) CN110765900B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111582117A (en) * 2020-04-29 2020-08-25 长江大学 Unmanned aerial vehicle illegal building inspection method, equipment and storage medium
CN113033289A (en) * 2021-01-29 2021-06-25 南瑞集团有限公司 Safety helmet wearing inspection method, device and system based on DSSD algorithm

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190042867A1 (en) * 2017-12-28 2019-02-07 Yen-Kuang Chen Multi-domain cascade convolutional neural network
CN109711348A (en) * 2018-12-28 2019-05-03 湖南航天远望科技有限公司 Intelligent monitoring method and system based on the long-term real-time architecture against regulations in hollow panel
CN110211137A (en) * 2019-06-08 2019-09-06 西安电子科技大学 Satellite Image Segmentation method based on residual error network and U-Net segmentation network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190042867A1 (en) * 2017-12-28 2019-02-07 Yen-Kuang Chen Multi-domain cascade convolutional neural network
CN109711348A (en) * 2018-12-28 2019-05-03 湖南航天远望科技有限公司 Intelligent monitoring method and system based on the long-term real-time architecture against regulations in hollow panel
CN110211137A (en) * 2019-06-08 2019-09-06 西安电子科技大学 Satellite Image Segmentation method based on residual error network and U-Net segmentation network

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
张勇;: "遥感与GIS在厦门市违章建筑监测与管理中的应用" *
甘欣悦;佘天唯;龙瀛;: "街道建成环境中的城市非正规性 基于北京老城街景图片的人工打分与机器学习相结合的识别探索" *
钟波;: "应用无人机对于违法建筑物的影像对比判别" *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111582117A (en) * 2020-04-29 2020-08-25 长江大学 Unmanned aerial vehicle illegal building inspection method, equipment and storage medium
CN113033289A (en) * 2021-01-29 2021-06-25 南瑞集团有限公司 Safety helmet wearing inspection method, device and system based on DSSD algorithm

Also Published As

Publication number Publication date
CN110765900B (en) 2023-09-05

Similar Documents

Publication Publication Date Title
CN111368687B (en) Sidewalk vehicle illegal parking detection method based on target detection and semantic segmentation
CN108509954A (en) A kind of more car plate dynamic identifying methods of real-time traffic scene
CN109325502B (en) Shared bicycle parking detection method and system based on video progressive region extraction
CN112070135A (en) Power equipment image detection method and device, power equipment and storage medium
CN110852164A (en) YOLOv 3-based method and system for automatically detecting illegal building
CN111914634A (en) Complex-scene-interference-resistant automatic manhole cover type detection method and system
Ren et al. YOLOv5s-M: A deep learning network model for road pavement damage detection from urban street-view imagery
CN113450573A (en) Traffic monitoring method and traffic monitoring system based on unmanned aerial vehicle image recognition
CN103679214A (en) Vehicle detection method based on online area estimation and multi-feature decision fusion
CN112668375B (en) Tourist distribution analysis system and method in scenic spot
CN114694178A (en) Method and system for monitoring safety helmet in power operation based on fast-RCNN algorithm
CN110765900A (en) DSSD-based automatic illegal building detection method and system
CN115131747A (en) Knowledge distillation-based power transmission channel engineering vehicle target detection method and system
Li et al. Automated classification and detection of multiple pavement distress images based on deep learning
CN112785610B (en) Lane line semantic segmentation method integrating low-level features
CN112836590B (en) Flood disaster monitoring method and device, electronic equipment and storage medium
CN116384844B (en) Decision method and device based on geographic information cloud platform
CN116229396B (en) High-speed pavement disease identification and warning method
CN111598885A (en) Automatic visibility grade marking method for highway foggy pictures
CN110163081A (en) Regional invasion real-time detection method, system and storage medium based on SSD
CN115563652A (en) Track embedding leakage prevention method and system
CN115170783A (en) Expressway pavement crack detection method using street view image
Haryono et al. Accuracy in Object Detection Based on Image Processing at the Implementation of Motorbike Parking on the Street
CN112036246B (en) Construction method of remote sensing image classification model, remote sensing image classification method and system
CN111428752B (en) Visibility detection method based on infrared image

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