Journal
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
Volume 13, Issue -, Pages 318-328Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2019.2961634
Keywords
Fully convolutional networks (FCN); multilabel retrieval; multilabel vector; region convolutional features (RCFs); remote sensing image retrieval (RSIR); single-label retrieval
Categories
Funding
- National Key Research and Development Plan on Strategic International Scientific and Technological Innovation Cooperation Special Project [2016YFE0202300]
- National Natural Science Foundation of China [61671332, 41771452, 41771454]
- Natural Science Fund of Hubei Province in China [2018CFA007]
Ask authors/readers for more resources
Conventional remote sensing image retrieval (RSIR) system usually performs single-label retrieval where each image is annotated by a single label representing the most significant semantic content of the image. In this scenario, however, the scene complexity of remote sensing images is ignored, where an image might have multiple classes (i.e., multiple labels), resulting in poor retrieval performance. We therefore propose a novel multilabel RSIR approach based on fully convolutional network (FCN). Specifically, FCN is first trained to predict segmentation map of each image in the considered image archive. We then obtain multilabel vector and extract region convolutional features of each image based on its segmentation map. The extracted region features are finally used to perform region-based multilabel retrieval. The experimental results show that our approach achieves state-of-the-art performance in contrast to handcrafted and convolutional neural network features.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available