DBNet is a large-scale dataset for driving behavior research. It includes aligned video, point cloud, GPS and driver behavior (speed and wheel), which captures 1000 KM real-world driving data. It was developed by MVIG, Shanghai Jiao Tong University* and SCSC Lab, Xiamen University* (*alphabetical order). We hope it will become a useful resource for autonomous driving research community.


Research paper (if you use our dataset, please cite following paper)


LiDAR-Video Driving Dataset: Learning Driving Policies Effectively

Yiping Chen*, Jingkang Wang*, Jonathan Li, Cewu Lu, Zhipeng Luo, Han Xue, and Cheng Wang (*equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Corresponding author are Jonathan Li (junli@xmu.edu.cn/junli@uwaterloo.ca) and Cewu Lu (lucewu@sjtu.edu.cn)


Demo Code in Github


Team


Steering Committee



  Prof. Cewu Lu*


Prof. Jonathan Li*




    Yiping Chen*


 Jingkang Wang*


    Zhipeng Luo*


     Han Xue*


    Cheng Wang*


    Rongren Wu*



   Weisheng Lin*


    Jianlan Gao*


   Hongbin Zeng*