Article: Patch-local self-similar network for ground terrain recognition Journal: International Journal of Intelligent Systems Technologies and Applications (IJISTA) 2023 Vol.21 No.3 pp.262 - 279 Abstract: We proposed a patch-local self-similar network (PLoSNet) to exploit the inherent correlations between the patch-level features and the local features among the ground terrain texture for ground terrain recognition. Firstly, the early features extracted from the shallow layer of the backbone network were enhanced by using a texture statistical information enhancement module (TSIEM). Then we adopted the patch extraction method to generate patch-level features on the enhanced features. Next, the patch-level features and the local feature extracted from the last layer of the backbone network were fused by patch-level and local feature fusion module (PLFFM). Finally, the two modules served as a feature encoding layer could be easily integrated into the convolutional neural networks to achieve end-to-end training. In this paper, ResNet-18 was used as the backbone network, and the results showed the proposed PLoSNet has a superior performance over existing approaches on three challenging ground terrain/material recognition datasets. Inderscience Publishers - linking academia, business and industry through research

Title: Patch-local self-similar network for ground terrain recognition

Authors: Xiao Zhu; Ming Li; Jianding Zhao; Liang Zhou

Addresses: School of Electronic Information, Shanghai Dianji University, Shanghai, 201306, China ' School of Electronic Information, Shanghai Dianji University, Shanghai, 201306, China ' School of Electronic Information, Shanghai Dianji University, Shanghai, 201306, China ' Department of Radiology, Jiading District Central Hospital, Shanghai, 201800, China; Affiliated to: Shanghai University of Medicine and Health Sciences, China

Abstract: We proposed a patch-local self-similar network (PLoSNet) to exploit the inherent correlations between the patch-level features and the local features among the ground terrain texture for ground terrain recognition. Firstly, the early features extracted from the shallow layer of the backbone network were enhanced by using a texture statistical information enhancement module (TSIEM). Then we adopted the patch extraction method to generate patch-level features on the enhanced features. Next, the patch-level features and the local feature extracted from the last layer of the backbone network were fused by patch-level and local feature fusion module (PLFFM). Finally, the two modules served as a feature encoding layer could be easily integrated into the convolutional neural networks to achieve end-to-end training. In this paper, ResNet-18 was used as the backbone network, and the results showed the proposed PLoSNet has a superior performance over existing approaches on three challenging ground terrain/material recognition datasets.

Keywords: convolutional neural networks; CNNs; patch-level feature; local feature; self-similarity; ground terrain images analysis.

DOI: 10.1504/IJISTA.2023.133696

International Journal of Intelligent Systems Technologies and Applications, 2023 Vol.21 No.3, pp.262 - 279

Received: 04 Aug 2022
Accepted: 10 Apr 2023
Published online: 29 Sep 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Patch-local self-similar network for ground terrain recognition

Keep up-to-date