MonoRCNN

MonoRCNN is a monocular 3D object detection method for automonous driving, published at ICCV 2021. This project is an implementation of MonoRCNN.

Visualization

Methodology

Related Link

• ICCV paper
• KITTI video demo

Installation

• Python 3.6
• PyTorch 1.5.0
• Detectron2 0.1.3

Please use the Detectron2 included in this project. To ignore fully occluded objects during training, build.py, rpn.py, and roi_heads.py have been modified.

Dataset Preparation

• KITTI

Model & Log

• KITTI val1 split

Organize the downloaded files as follows:

├── projects
│   ├── MonoRCNN
│   │   ├── output
│   │   │   ├── model
│   │   │   ├── log.txt
│   │   │   ├── ...

Test

cd projects/MonoRCNN
./main.py --config-file config/MonoRCNN_KITTI.yaml --num-gpus 1 --resume --eval-only

Set VISUALIZE as True to visualize 3D object detection results (saved in output/evaluation/test/visualization).

Training

cd projects/MonoRCNN
./main.py --config-file config/MonoRCNN_KITTI.yaml --num-gpus 1

Citation

If you find this project useful in your research, please cite:

@inproceedings{MonoRCNN_ICCV21,
    title = {Geometry-based Distance Decomposition for Monocular 3D Object Detection},
    author = {Xuepeng Shi and Qi Ye and 
              Xiaozhi Chen and Chuangrong Chen and 
              Zhixiang Chen and Tae-Kyun Kim},
    booktitle = {ICCV},
    year = {2021},
}

Contact

[email protected]

Acknowledgement

• Detectron2
• M3D-RPN
• MMDetection