A novel split-frequency feature fusion framework for processing the dual-optical images of offshore oil spills. (May 2023)

• Record Type: Journal Article
• Authors: Chen, Yuqing; Yu, Wei; Tang, Jiayi; Sun, Yuhan; Hu, Huosheng
• Is Part Of: Marine pollution bulletin. Volume 190(2023)
• Publication Date: 2023-05
• Subjects: Oil spills -- Infrared-visible images -- Information entropy -- Self-encoding network; Marine pollution -- Periodicals; Marine Biology -- Periodicals; Water Pollution -- Periodicals; Mer -- Pollution -- Périodiques; Publications périodiques; Pollution des mers; Lutte antipollution; Electronic journals; 363.7394
• DOI: 10.1016/j.marpolbul.2023.114840
• Languages: English
• ISSNs: 0025-326X

Abstract

Abstract: This paper presents a novel split-frequency feature fusion framework used for processing the dual-optical (infrared-visible) images of offshore oil spills. The self-coding network is used for high-frequency features of oil spill images based on local cross-stage residual dense blocks to achieve feature extraction and construct a regularized fusion strategy. The adaptive weights are designed to increase the proportion of high-frequency features in source images during the low-frequency feature fusion process. A global residual branch is established to reduce the loss of oil spill texture features. The network structure of the primary residual dense block auto-encoding network is optimized based on the local cross-stage method to further reduce the network parameters and improve the network operation speed. To verify the effectiveness of the proposed infrared-visible image fusion algorithm, the BiSeNetV2 algorithm is selected as the oil spill detection algorithm to realize the pixel accuracy of the oil spill image features at 91 % . Highlights: An image decomposition fusion method is proposed. Infrared and visible images are divided into low/high frequency two parts. The information entropy is used to construct an adaptive weight for our oil spill image fusion method. Feature extraction is achieved based on local cross-stage residual dense blocks by using a regularized feature fusion strategy.