Title | ||
---|---|---|
Recurrent Neural Network Architectures for Vulnerable Road User Trajectory Prediction |
Abstract | ||
---|---|---|
We present an experimental study comparing various Recurrent Neural Network architectures for the task of Vulnerable Road User (VRU) motion trajectory prediction in the intelligent vehicle domain. Making use of temporal motion cues and visual appearance features, we design multi-cue RNN-based architectures with dedicated optimization process to predict future moving trajectories from historical consecutive frames. Experiments are performed on image sequences recorded from on-board a moving vehicle and public tracking datasets. In particular, the Tsinghua-Daimler Cyclist Benchmark (TDCB) has been augmented with additional annotations (vari-ous VRU types) to support the evaluation of object tracking approaches and trajectory prediction methods. This newly introduced dataset is termed TDCB-Track. We demonstrate the effectiveness of the proposed RNN architectures on the public MOT16 dataset and the TDCB-Track dataset. We show that the proposed approaches outperform simpler baseline methods and stay ahead with the state-of-the-art. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/IVS.2019.8814275 | 2019 IEEE Intelligent Vehicles Symposium (IV) |
Keywords | Field | DocType |
object tracking approaches,trajectory prediction methods,RNN architectures,public MOT16 dataset,TDCB-Track dataset,intelligent vehicle domain,temporal motion cues,visual appearance features,dedicated optimization process,historical consecutive frames,moving vehicle,public tracking datasets,recurrent neural network architectures,Tsinghua-Daimler cyclist benchmark,vulnerable road user motion trajectory prediction,VRU types,image sequences | Computer vision,Motion cues,Moving vehicle,Computer science,Recurrent neural network,Video tracking,Artificial intelligence,Trajectory,Visual appearance | Conference |
ISSN | ISBN | Citations |
1931-0587 | 978-1-7281-0561-1 | 0 |
PageRank | References | Authors |
0.34 | 4 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hui Xiong | 1 | 4958 | 290.62 |
Fabian Flohr | 2 | 97 | 6.49 |
Sijia Wang | 3 | 0 | 0.68 |
Baofeng Wang | 4 | 0 | 0.34 |
Jianqiang Wang | 5 | 1240 | 68.36 |
Keqiang Li | 6 | 583 | 52.39 |