search

Owen-Liuyuxuan / visualDet3D

Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving / YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
https://owen-liuyuxuan.github.io/papers_reading_sharing.github.io/3dDetection/GroundAwareConvultion/
Apache License 2.0
365 stars 77 forks source link

Train on custom dataset with a stereo camera setup #42

Open kristoffercrj opened 2 years ago

kristoffercrj commented 2 years ago

Is it possible to modify the code such that I can use my own dataset that has the same structure as the KITTI dataset? In addition, can I make the calibration files match with my setup if I only have two cameras and no need for Lidar or velodyne.

Owen-Liuyuxuan commented 2 years ago

Sorry for the late reply. Sure, it should be possible to run without lidar calibration information. (The program does not read lidar-related information if it is not needed)