Lidar–Camera Semi-Supervised Learning for Semantic Segmentation

Sensors

Luca Caltagirone¹  Mattias Wahde¹  Lennart Svensson²  Raivo Sell³  Mauro Bellone⁴ 

[1] Applied Artificial Intelligence Research Group, Department of Mechanics and Maritime Sciences, Chalmers University of Technology, 412 58 Gothenburg, Sweden;Department of Electrical Engineering, Chalmers University of Technology, 412 58 Gothenburg, Sweden;Department of Mechanical and Industrial Engineering, Tallinn University of Technology, 12616 Tallinn, Estonia;Smart City Center of Excellence, Tallinn University of Technology, 12616 Tallinn, Estonia;

关键词: sensor fusion;    semi-supervised learning;    deep learning;    semantic segmentation;   

DOI  :  10.3390/s21144813

来源: DOAJ

【 摘 要 】

In this work, we investigated two issues: (1) How the fusion of lidar and camera data can improve semantic segmentation performance compared with the individual sensor modalities in a supervised learning context; and (2) How fusion can also be leveraged for semi-supervised learning in order to further improve performance and to adapt to new domains without requiring any additional labelled data. A comparative study was carried out by providing an experimental evaluation on networks trained in different setups using various scenarios from sunny days to rainy night scenes. The networks were tested for challenging, and less common, scenarios where cameras or lidars individually would not provide a reliable prediction. Our results suggest that semi-supervised learning and fusion techniques increase the overall performance of the network in challenging scenarios using less data annotations.

【 授权许可】

Unknown