Skip to main content

Research Repository

Advanced Search

A Two-branch Edge Guided Lightweight Network for infrared image saliency detection

Liu, Zhaoying; Li, Xiang; Zhang, Ting; Zhang, Xuesi; Sun, Changming; Rehman, Sadaqat ur; Ahmad, Jawad

Authors

Zhaoying Liu

Xiang Li

Ting Zhang

Xuesi Zhang

Changming Sun

Sadaqat ur Rehman



Abstract

In the dynamic landscape of saliency detection, convolutional neural networks have emerged as catalysts for innovation, but remain largely tailored for RGB imagery, falling short in the context of infrared images, particularly in memory-restricted environments. These existing approaches tend to overlook the wealth of contour information vital for a nuanced analysis of infrared images. Addressing this notable gap, we introduce the novel Two-branch Edge Guided Lightweight Network (TBENet), designed explicitly for the robust analysis of infrared image saliency detection. The main contributions of this paper are as follows. First, we formulate the saliency detection task as two subtasks, contour enhancement and foreground segmentation. Therefore, the TBENet is divided into two specialized branches: a contour prediction branch for extracting target contour and a saliency map generation branch for separating the foreground from the background. The first branch employs an encoder–decoder architecture to meticulously delineate object contours, serving as a guiding blueprint for the second branch. This latter segment adeptly integrates spatial and semantic data, creating a precise saliency map that is refined further by an innovative edge-weighted contour loss function. Second, to enhance feature integration capabilities, we propose depthwise multi-scale and multi-cue modules, facilitating sophisticated feature aggregation. Third, a high-level linear bottleneck module is devised to ensure the extraction of rich semantic information, and by replacing the standard convolution with the depthwise convolution, it is beneficial to reduce model complexity. Additional, we reduce the number of channels of the feature maps from each stage of the decoder to further enhance the lightweight of the model. Last, we construct a novel infrared ship dataset Small-IRShip to train and evaluate our proposed model. Experimental results on the homemade dataset Small-IRShip and two publicly available datasets, namely RGB-T and IRSTD-1k, demonstrate TBENet’s superior performance over state-of-the-art methods, affirming its effectiveness in harnessing edge information and incorporating advanced feature integration strategies.

Citation

Liu, Z., Li, X., Zhang, T., Zhang, X., Sun, C., Rehman, S. U., & Ahmad, J. (2024). A Two-branch Edge Guided Lightweight Network for infrared image saliency detection. Computers and Electrical Engineering, 118(Part A), Article 109296. https://doi.org/10.1016/j.compeleceng.2024.109296

Journal Article Type Article
Acceptance Date May 6, 2024
Online Publication Date May 28, 2024
Publication Date 2024-08
Deposit Date Jun 28, 2024
Publicly Available Date Jun 28, 2024
Journal Computers and Electrical Engineering
Print ISSN 0045-7906
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 118
Issue Part A
Article Number 109296
DOI https://doi.org/10.1016/j.compeleceng.2024.109296
Keywords Infrared images, Lightweight module, Saliency detection, Contour information, Feature integration

Files





You might also like



Downloadable Citations