Semantic Segmentation Network combining Gaussian Perception and Iterative Multi-Scale Attention

• Published in: Multimedia systems Vol. 31; no. 5
• Main Authors: Ke, Zunwang, Wang, Guosheng, Zhang, Yugui, Shi, YunLong, Guo, Fengyu, Zou, Yuelin, Li, Zhaofan, Guo, Run, Zhou, Ji-Sheng
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.10.2025; Springer Nature B.V
• Subjects: Attention; Computer Communication Networks; Computer Graphics; Computer Science; Cryptology; Data Storage Representation; Feature extraction; Image segmentation; Multimedia Information Systems; Operating Systems; Perception; Pixels; Regular Paper; Scene analysis; Semantic segmentation; Semantics; Source code; Local–global features; Gaussian function; Semantic segmentation; Spatial and channel attention mechanisms

Semantic segmentation is crucial in autonomous driving, offering exceptional scene understanding to tackle challenges like small object edges and blurred textures in complex traffic environments. By performing pixel-level classification, it provides vehicles with comprehensive environmental informat...