Realtime Water-Hazard Detection and Visualisation for Autonomous Navigation and Advanced Driving Assistance
Juntao Li, Chuong Vinh Nguyen · 2019
Water on road is a potential hazard for road vehicles. In complex traffic, it is difficult for drivers and autonomous navigation systems to safely share the road with other vehicles and pedestrians while detecting and avoiding water puddles and pot holes. Detection of water puddles needs to be both accurate and fast enough for realtime assistance or planning. We present a new fast deep-learning based water detection network that exploits temporal information to achieve an accuracy comparable to the state-of-the-art accuracy while requiring less than half memory and CUDA cores. We also show how the detection results are visualised in 3D for AR/VR applications.