Land-Cover Classification With High-Resolution Remote Sensing Images Using Interactive Segmentation

Abstract

Deep convolutional neural network (CNN) has been increasingly applied in interpretation of remote sensing image such as automatically mapping land cover. Although the automatic CNN method achieves relatively high accuracy, there are still many misclassified areas. Considering that it is still far from practical application, this paper proposes a semi-automatic auxiliary scheme for land cover classification whose core idea is to use an interactive segmentation network. To infer the rough positions and categories of objects, a CNN is relied on to classify images in a patch-wise manner. Then an interactive segmentation method is proposed by accepting user-clicks on the inside and outside of object to guide the model for the segmentation task in the patches. This model also introduces different interactive modules to better integrate features of different scales. In addition, we create a large-scale sample library containing five common land cover categories which covers Jiangsu Province, China, and includes both aerial and satellite imagery. On our sample, we gave a thorough evaluation of most recent deep learning-based methods. The experimental results shown by our interactive segmentation also far outperform the recent semantic segmentation method, which provides a reference for semi-automatic land cover mapping.INDEX TERMS deep learning; CNN; sample; interactive segmentation.

Bridging the gap: deep learning in the semantic segmentation of remote sensing data

“…19 They are able to capture both the spatial and spectral features of hyperspectral images. 20 To illustrate, a novel CNN framework that integrates 1D, 2D and 3D CNNs has been proposed to achieve highly accurate and fast land cover classification from airborne hyperspectral images. 20 This integration effectively improves hyperspectral image land cover classification computational efficiency while maintaining high accuracy.…”

Utilizing Geospatial Techniques for Change Detection of the Baghdad Campus landscape From 1988 to 2022

“…Its predominant usage revolves around monitoring drought stress and vegetation moisture content [20]. NDMI indicators exhibit a strong association with dry matter in leaves [21]. NDMI may imply for discriminating between various vegetation types [ 22 , 23,24 ].…”

Automatic Classification of Selected Corine Classes Using Deep Learning Based Semantic Segmentation

“…The U-net algorithm, originally designed for biomedical image segmentation, has been widely employed in numerous studies. It finds applications not only on very high spatial resolution (VHR) images but also on medium resolution images characterized by wide coverage and high temporal resolution, such as Landsat or Sentinel, particularly within the realm of land cover classification studies (Ronneberger et al, 2015;Pollatos et al, 2020;Solórzano et al, 2021;Xu et al, 2023;Tzepkenlis et al, 2023).…”