Patch-based discriminative learning for remote sensing scene classification
|Author:||Muhammad, Usman1,2; Hoque, Md Ziaul1; Wang, Weiqiang2;|
1Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, FIN-90014 Oulu, Finland
2School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100864, China
3Medical Imaging, Physics, and Technology (MIPT), Faculty of Medicine, University of Oulu, FIN-90014 Oulu, Finland
|Online Access:||PDF Full Text (PDF, 2.9 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2023062157533
Multidisciplinary Digital Publishing Institute,
|Publish Date:|| 2023-06-21
The research focus in remote sensing scene image classification has been recently shifting towards deep learning (DL) techniques. However, even the state-of-the-art deep-learning-based models have shown limited performance due to the inter-class similarity and the intra-class diversity among scene categories. To alleviate this issue, we propose to explore the spatial dependencies between different image regions and introduce patch-based discriminative learning (PBDL) for remote sensing scene classification. In particular, the proposed method employs multi-level feature learning based on small, medium, and large neighborhood regions to enhance the discriminative power of image representation. To achieve this, image patches are selected through a fixed-size sliding window, and sampling redundancy, a novel concept, is developed to minimize the occurrence of redundant features while sustaining the relevant features for the model. Apart from multi-level learning, we explicitly impose image pyramids to magnify the visual information of the scene images and optimize their positions and scale parameters locally. Motivated by this, a local descriptor is exploited to extract multi-level and multi-scale features that we represent in terms of a codeword histogram by performing k-means clustering. Finally, a simple fusion strategy is proposed to balance the contribution of individual features where the fused features are incorporated into a bidirectional long short-term memory (BiLSTM) network. Experimental results on the NWPU-RESISC45, AID, UC-Merced, and WHU-RS datasets demonstrate that the proposed approach yields significantly higher classification performance in comparison with existing state-of-the-art deep-learning-based methods.
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
113 Computer and information sciences
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).