Optical Flow Based Motion Detection for Autonomous Driving

3 Mar 2022  ·  Ka Man Lo ·

Motion detection is a fundamental but challenging task for autonomous driving. In particular scenes like highway, remote objects have to be paid extra attention for better controlling decision. Aiming at distant vehicles, we train a neural network model to classify the motion status using optical flow field information as the input. The experiments result in high accuracy, showing that our idea is viable and promising. The trained model also achieves an acceptable performance for nearby vehicles. Our work is implemented in PyTorch. Open tools including nuScenes, FastFlowNet and RAFT are used. Visualization videos are available at https://www.youtube.com/playlist?list=PLVVrWgq4OrlBnRebmkGZO1iDHEksMHKGk .

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Motion Detection nuScenes FastFlowNet (Kitti) F1 (%) 92.9 # 1
Motion Detection nuScenes Raft (Kitti) F1 (%) 89.5 # 2


No methods listed for this paper. Add relevant methods here