High-resolution aerial imagery semantic labeling with dense pyramid network
Pan, Xuran and Gao, Lianru and Zhang, Bing and Yang, Fan and Liao, Wenzhi (2018) High-resolution aerial imagery semantic labeling with dense pyramid network. Sensors, 18 (11). pp. 1-15. 3774. ISSN 1424-8220 (https://doi.org/10.3390/s18113774)
Preview |
Text.
Filename: Pan_etal_S2018_High_resolution_aerial_imagery_semantic_labeling_dense_pyramid_network.pdf
Final Published Version License: Download (2MB)| Preview |
Abstract
Semantic segmentation of high-resolution aerial images is of great importance in certain fields, but the increasing spatial resolution brings large intra-class variance and small inter-class differences that can lead to classification ambiguities. Based on high-level contextual features, the deep convolutional neural network (DCNN) is an effective method to deal with semantic segmentation of high-resolution aerial imagery. In this work, a novel dense pyramid network (DPN) is proposed for semantic segmentation. The network starts with group convolutions to deal with multi-sensor data in channel wise to extract feature maps of each channel separately; by doing so, more information from each channel can be preserved. This process is followed by the channel shuffle operation to enhance the representation ability of the network. Then, four densely connected convolutional blocks are utilized to both extract and take full advantage of features. The pyramid pooling module combined with two convolutional layers are set to fuse multi-resolution and multi-sensor features through an effective global scenery prior manner, producing the probability graph for each class. Moreover, the median frequency balanced focal loss is proposed to replace the standard cross entropy loss in the training phase to deal with the class imbalance problem. We evaluate the dense pyramid network on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam 2D semantic labeling dataset, and the results demonstrate that the proposed framework exhibits better performances, compared to the state of the art baseline.
-
-
Item type: Article ID code: 69373 Dates: DateEvent5 November 2018Published1 November 2018AcceptedSubjects: Science > Physics Department: Faculty of Engineering > Electronic and Electrical Engineering Depositing user: Pure Administrator Date deposited: 15 Aug 2019 09:15 Last modified: 19 Nov 2024 19:55 URI: https://strathprints.strath.ac.uk/id/eprint/69373