Dual‐Litenet: A Lightweight Real‐Time Semantic Segmentation and Boundary Detection Method for Mobile Embodied Agents
Xin He, Hu Lu, Fei Niu · Electronics Letters · 2025
ABSTRACT Semantic segmentation and boundary detection serve as the foundational stages in the visual language navigation task within embodied intelligence. Nevertheless, existing semantic segmentation and boundary detection methods employed in visual language navigation fail to satisfy the demands for real‐time performance and accuracy under resource‐constrained scenarios. In response to this challenge, this study introduces a dual‐branch network. This architecture is designed to be lightweight while fulfilling the real‐time requirements of the agent and achieving an accuracy that is only marginally lower than that of non‐lightweight state‐of‐the‐art methods. Experimental results demonstrate that this approach achieves a parameter count of 2.7M, FLOPs of 29.93G, and a frame rate of 32.18 FPS.