MMSMCNet: Modal Memory Sharing and Morphological Complementary Networks for RGB-T Urban Scene Semantic Segmentation

• Published in: IEEE transactions on circuits and systems for video technology Vol. 33; no. 12; p. 1
• Main Authors: Zhou, Wujie, Zhang, Han, Yan, Weiqing, Lin, Weisi
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: complementary supervision strategy; contour skeleton positioning; Data mining; Decoding; Feature extraction; Image segmentation; information memory sharing; Modules; morphological complementary; Morphology; RGB-T semantic segmentation; Semantic segmentation; Semantics; Skeleton; Thermal imaging

Combining color (RGB) images with thermal images can facilitate semantic segmentation of poorly lit urban scenes. However, for RGB-thermal (RGB-T) semantic segmentation, most existing models address cross-modal feature fusion by focusing only on exploring the samples while neglecting the connections...