RWSNet: a semantic segmentation network based on SegNet combined with random walk for remote sensing
2020
Jiang, Jie | Lyu, Chengjin | Liu, Siying | He, Yongqiang | Hao, Xuetao
Semantic segmentation methods based on deep learning considerably improve the segmentation performance of remote sensing images. However, with the extensive application of high-resolution remote sensing images, additional details introduce considerable interference to the learning process for classification, thereby diminishing the accuracy of segmentation and resulting in blurry object boundaries. To address this problem, this study designed Random-Walk-SegNet (RWSNet), a semantic segmentation network based on SegNet combined with random walk. First, SegNet is used as the basic architecture with the sliding window strategy that optimizes the network output to improve the continuity and smoothness of segmentation. Second, seed regions of the random walk are selected in accordance with the classification output of SegNet. Third, the weights of the undirected graph edge are determined by fusing the gradient of the original image and probability map of SegNet. Finally, random walk is implemented on the entire image, thus reducing edge blur and realizing high-performance semantic segmentation of remote sensing images. In comparison with mainstream and other improved methods, the proposed network has lower complexity but better performance, and the algorithm is state-of-the-art and robust.
اظهر المزيد [+] اقل [-]الكلمات المفتاحية الخاصة بالمكنز الزراعي (أجروفوك)
المعلومات البيبليوغرافية
تم تزويد هذا السجل من قبل National Agricultural Library