Encoder–Decoder Structure Fusing Depth Information for Outdoor Semantic Segmentation

• Published in: Applied sciences Vol. 13; no. 17; p. 9924
• Main Authors: Chen, Songnan, Tang, Mengxia, Dong, Ruifang, Kan, Jiangming
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2023
• Subjects: Accuracy; Artificial intelligence; Deep learning; feature pyramid; fusion structure; Interdisciplinary subjects; Machine learning; Neural networks; predicted depth map; RGB–D image; Robots; semantic segmentation; Semantics; Sensors

The semantic segmentation of outdoor images is the cornerstone of scene understanding and plays a crucial role in the autonomous navigation of robots. Although RGB–D images can provide additional depth information for improving the performance of semantic segmentation tasks, current state–of–the–art...