High Resolution Remote Sensing Image Classification Combining with Mean-Shift Segmentation and Fully Convolution Neural Network

Xu, 方旭 Fang; Guanghui, 王光辉 Wang; Huachao, 杨化超 Yang; Huijie, 刘慧杰 Liu; Libo, 闫立波 Yan

doi:10.3788/lop55.022802

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with traditional machine-learning classification methods such as RF and SVM, the U-Net method improves the classification accuracy by 6.42-25.91% using the same RGB image and the ground truth land-cover map. This result is in agreement with previous studies that applied the deep learning network model to remote-sensing land-use classification [45][46][47]. In this study, to form a reciprocity in data with traditional machine-learning classification methods, without too many manual steps to extract and select features [47,48], using 6 cm very-high-resolution UAV color images for AMD and mine land-cover classification, the overall classification accuracies of traditional machine-learning classification methods SVM and RF were lower than that of U-Net.…”

Section: Discussionsupporting

confidence: 93%

Acid Mine Drainage Discrimination Using Very High Resolution Imagery Obtained by Unmanned Aerial Vehicle in a Stone Coal Mining Area

Kou

Han

Cao

et al. 2023

Water

View full text Add to dashboard Cite

Mining of mineral resources exposes various minerals to oxidizing environments, especially sulfide minerals, which are decomposed by water after oxidation and make the water in the mine area acidic. Acid mine drainage (AMD) from mining can pollute surrounding rivers and lakes, causing serious ecological problems. Compared with traditional field surveys, unmanned aerial vehicle (UAV) technology has advantages in terms of real-time imagery, security, and image accuracy. UAV technology can compensate for the shortcomings of traditional technology in mine environmental surveys and effectively improve the implementat ion efficiency of the work. UAV technology has gradually become one of the important ways of mine environmental monitoring. In this study, a UAV aerial photography system equipped with a Red, Green, Blue (RGB) camera collected very-high-resolution images of the stone coal mining area in Ziyang County, northwest China, and classified the very-high-resolution images by support vector machine (SVM), random forest (RF), and U-Net methods, and detected the distribution of five types of land cover, including AMD, roof, water, vegetation, and bare land. Finally, the accuracy of the recognition results was evaluated based on the land-cover map using the confusion matrix. The recognition accuracy of AMD using the U-Net method is significantly better than that of SVM and RF traditional machine-learning methods. The results showed that a UAV aerial photography system equipped with an RGB camera and the depth neural network algorithm could be combined for the competent detection of mine environmental problems.

show abstract

Section: Discussionsupporting

confidence: 93%

Acid Mine Drainage Discrimination Using Very High Resolution Imagery Obtained by Unmanned Aerial Vehicle in a Stone Coal Mining Area

Kou

Han

Cao

et al. 2023

Water

View full text Add to dashboard Cite

show abstract

“…Many subsequent classification studies are based on the idea of the FCN network. Fang et al [36] applied the FCN to the classification of high-resolution remote sensing images; their results showed that the FCN can better obtain the essential features of ground features in images. Moreover, the mean drift segmentation algorithm can be used to optimize the edge of the obtained probability map results and improve the classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

An Improved Res-UNet Model for Tree Species Classification Using Airborne High-Resolution Images

2020

View full text Add to dashboard Cite

Tree species classification is important for the management and sustainable development of forest resources. Traditional object-oriented tree species classification methods, such as support vector machines, require manual feature selection and generally low accuracy, whereas deep learning technology can automatically extract image features to achieve end-to-end classification. Therefore, a tree classification method based on deep learning is proposed in this study. This method combines the semantic segmentation network U-Net and the feature extraction network ResNet into an improved Res-UNet network, where the convolutional layer of the U-Net network is represented by the residual unit of ResNet, and linear interpolation is used instead of deconvolution in each upsampling layer. At the output of the network, conditional random fields are used for post-processing. This network model is used to perform classification experiments on airborne orthophotos of Nanning Gaofeng Forest Farm in Guangxi, China. The results are then compared with those of U-Net and ResNet networks. The proposed method exhibits higher classification accuracy with an overall classification accuracy of 87%. Thus, the proposed model can effectively implement forest tree species classification and provide new opportunities for tree species classification in southern China.

show abstract

“…In the process of describing the characteristic image, it is necessary to accurately identify the fuzzy area of the image, collect and detect the noisy area in the image, that is, the fuzzy area, judge and analyze the characteristic point diffusion characteristics of the imaging area, and analyze the image blur characteristics in combination with the convolution principle of point spread function (PSF). The image features are converted into deconvolution characteristics [9] . Select the obvious feature points between the original image and the corrected image, establish the image dynamic reconstruction model, standardize the mapping relationship between the original image and the reconstructed image, and locate the real longitude and latitude of each pixel in the UAV remote sensing image.…”

Section: Implementation Of Dynamic Reconstruction Of Remote Sensing Imagementioning

confidence: 99%

Dynamic reconstruction method of unmanned aerial vehicle aerial remote sensing image based on compressed sensing

Yang

2021

JGC

View full text Add to dashboard Cite

Aiming at the current problems of poor dynamic reconstruction of UAV aerial remote sensing images and low image clarity, the dynamic reconstruction method of UAV aerial remote sensing images based on compression perception is proposed. Construct a quality reduction model for UAV aerial remote sensing images, obtain image feature information, and further noise reduction preprocessing of UAV aerial remote sensing images to better improve the resolution, spectral and multi-temporal trends of UAV aerial remote sensing images, and effectively solve the problems of resource waste such as large amount of sampled data, long sampling time and large amount of data transmission and storage. Maximize the UAV aerial remote sensing images sampling rate, reduce the complexity of dynamic reconstruction of UAV aerial remote sensing images, and effectively obtain the research requirements of high-quality image reconstruction. The experimental results show that the proposed dynamic reconstruction method of UAV aerial remote sensing images based on compressed sensing is correct and effective, which is better than the current mainstream methods.

show abstract

High Resolution Remote Sensing Image Classification Combining with Mean-Shift Segmentation and Fully Convolution Neural Network

Cited by 4 publications

References 0 publications

Acid Mine Drainage Discrimination Using Very High Resolution Imagery Obtained by Unmanned Aerial Vehicle in a Stone Coal Mining Area

Acid Mine Drainage Discrimination Using Very High Resolution Imagery Obtained by Unmanned Aerial Vehicle in a Stone Coal Mining Area

An Improved Res-UNet Model for Tree Species Classification Using Airborne High-Resolution Images

Dynamic reconstruction method of unmanned aerial vehicle aerial remote sensing image based on compressed sensing

Contact Info

Product

Resources

About