Building Change Detection with Deep Learning by Fusing Spectral and Texture Features of Multisource Remote Sensing Images: A GF-1 and Sentinel 2B Data Case

Abstract

Building change detection is an important task in the remote sensing field, and the powerful feature extraction ability of the deep neural network model shows strong advantages in this task. However, the datasets used for this study are mostly three-band high-resolution remote sensing images from a single data source, and few spectral features limit the development of building change detection from multisource remote sensing images. To investigate the influence of spectral and texture features on the effect of building change detection based on deep learning, a multisource building change detection dataset (MS-HS BCD dataset) is produced in this paper using GF-1 high-resolution remote sensing images and Sentinel-2B multispectral remote sensing images. According to the different resolutions of each Sentinel-2B band, eight different multisource spectral data combinations are designed, and six advanced network models are selected for the experiments. After adding multisource spectral and texture feature data, the results show that the detection effects of the six networks improve to different degrees. Taking the MSF-Net network as an example, the F1-score and IOU improved by 0.67% and 1.09%, respectively, compared with high-resolution images, and by 7.57% and 6.21% compared with multispectral images.

Typical Ground Object Recognition in Desert Areas Based on DYDCNet: A Case Study in the Circum-Tarim Region, Xinjiang, China

“…Traditional image recognition methods mainly consist of pixel-based threshold segmentation [5][6][7], cluster segmentation [8], decision tree classification [9], region-based segmentation [10], and semantic learning using random forest and conditional random field [11] to construct classifiers. These methods are limited to images with uniform gray-scale distribution and more obvious differences between the grayscale of the recognition target and the background [12], and although they are relatively simple to operate, they are not able to segment a large amount of semantic information, which greatly challenges the increasing proliferation of remote sensing data [13]. With the introduction of deep learning technology, research in the computer vision field has greatly progressed, and convolutional neural networks have been gradually applied in the image processing field [14] to achieve the semantic segmentation of images at the pixel level [15].…”