ECFFNet: Effective and Consistent Feature Fusion Network for RGB-T Salient Object Detection

• Published in: IEEE transactions on circuits and systems for video technology Vol. 32; no. 3; pp. 1224 - 1235
• Main Authors: Zhou, Wujie, Guo, Qinling, Lei, Jingsheng, Yu, Lu, Hwang, Jenq-Neng
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; bilateral reversal fusion module; Color imagery; cross-modality fusion; Decoding; Feature extraction; Imaging; Lighting; Meteorology; Modules; multilevel consistent fusion module; Object recognition; RGB-T data; Salience; salient object detection; Sorting; Streaming media; Weather

Under ideal environmental conditions, RGB-based deep convolutional neural networks can achieve high performance for salient object detection (SOD). In scenes with cluttered backgrounds and many objects, depth maps have been combined with RGB images to better distinguish spatial positions and structu...