RGB-T Semantic Segmentation With Location, Activation, and Sharpening

• Published in: IEEE transactions on circuits and systems for video technology Vol. 33; no. 3; pp. 1223 - 1235
• Main Authors: Li, Gongyang, Wang, Yike, Liu, Zhi, Zhang, Xinpeng, Zeng, Dan
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Coders; Collaboration; collaborative location; complementary activation; Decoding; discriminative treatment; edge sharpening; Feature extraction; Image segmentation; Infrared imagery; Lighting; Modules; Optical fibers; RGB-T semantic segmentation; Scene analysis; Semantic segmentation; Semantics

Semantic segmentation is important for scene understanding. To address the scenes of adverse illumination conditions of natural images, thermal infrared (TIR) images are introduced. Most existing RGB-T semantic segmentation methods follow three cross-modal fusion paradigms, i. e., encoder fusion, de...