A remote-sensing image-retrieval model based on an ensemble neural networks. Issue 4 (2nd October 2018)

• Record Type: Journal Article
• Authors: Ma, Caihong; Chen, Fu; Yang, Jin; Liu, Jianbo; Xia, Wei; Li, Xinpeng
• Is Part Of: Big earth data. Volume 2:Issue 4(2018)
• Page Start: 351
• Page End: 367
• Publication Date: 2018-10-02
• Subjects: Content-based remote-sensing image retrieval -- neural network -- multi-features; Earth sciences -- Periodicals; Earth sciences -- Research -- Periodicals; Geographic information systems Periodicals; 550
• DOI: 10.1080/20964471.2019.1570815
• Languages: English
• ISSNs: 2096-4471

Abstract

ABSTRACT: With the rapid development of remote-sensing technology and the increasing number of Earth observation satellites, the volume of image datasets is growing exponentially. The management of big Earth data is also becoming increasingly complex and difficult, with the result that it can be hard for users to access the imagery that they are interested in quickly, efficiently and intelligently. To address these challenges, this paper proposes a remote-sensing image-retrieval model based on an ensemble neural networks. This model can make full use of existing training data to improve the efficiency and accuracy of the initial retrieval of remote-sensing images and keep model simple. The retrieval of aerial images using the proposed model is compared with the results obtained using ten individual neural networks and two ensemble neural networks and the results show that the proposed approach has a high degree of precision. In addition, the coverage rate and mean precision show a dramatic improvement of more than 40% compared with existing methods based on normal way. And, the coverage ratio gets 86% for the top 10 return results.