Open JiahaoXia opened 1 year ago
Can you provide the detailed config demo/data/TrafficVideo/camera2.json
? We don't officially support running demo on ImVoxelNet.
@ZCMax This is the camera2.json
{
"images": [
{
"file_name": "camera2.jpg",
"cam_intrinsic": [
[
1598.590308370044,
0.0,
1296
],
[
0.0,
1591.578947368421,
972
],
[
0.0,
0.0,
1.0
]
]
}
]
}
ImVoxelNet is different from other monocular methods like FCOS3D. It needs the transformation between LiDAR and camera systems, i.e., extrinsic transformation, instead of only requiring intrinsic parameters in FCOS3D. You'll need to define your LiDAR system and align ImVoxelNet to your case. You can probably define a pseudo-LiDAR system aligned with the XYZ directions of the mmdet3d LiDAR system while aligning its origin with the camera system.
Prerequisite
Task
I have modified the scripts/configs, or I'm working on my own tasks/models/datasets.
Branch
master branch https://github.com/open-mmlab/mmdetection3d
Environment
Reproduces the problem - code sample
demo/mono_det_demo.py
Reproduces the problem - command or script
Reproduces the problem - error message
Additional information
I have added
to configure file imvoxelnet_4x8_kitti-3d-car.py however, I got other errors