3D cascade RCNN for object detection on point cloud

Last update: Dec 02, 2022

Overview

3D Cascade RCNN

This is the implementation of 3D Cascade RCNN: High Quality Object Detection in Point Clouds.

We designed a 3D object detection model on point clouds by:

Presenting a simple yet effective 3D cascade architecture
Analyzing the sparsity of the point clouds and using point completeness score to re-weighting training samples. Following is detection results on Waymo Open Dataset.

Results on KITTI

	Easy Car	Moderate Car	Hard Car
AP 11	90.05	86.02	79.27
AP 40	93.20	86.19	83.48

Results on Waymo

	Overall Vehicle	0-30m Vehicle	30-50m Vehicle	50m-Inf Vehicle
LEVEL_1 mAP	76.27	92.66	74.99	54.49
LEVEL_2 mAP	67.12	91.95	68.96	41.82

Installation

Requirements. The code is tested on the following environment:

Ubuntu 16.04 with 4 V100 GPUs
Python 3.7
Pytorch 1.7
CUDA 10.1
spconv 1.2.1

Build extensions

python setup.py develop

Getting Started

Prepare for the data.

Please download the official KITTI dataset and generate data infos by following command:

python -m pcdet.datasets.kitti.kitti_dataset create_kitti_infos tools/cfgs/kitti_dataset.yaml

The folder should be like:

data
├── kitti
│   │── ImageSets
│   │── training
│   │   ├──calib & velodyne & label_2 & image_2
│   │── testing
│   │   ├──calib & velodyne & image_2
|   |── kitti_dbinfos_train.pkl
|   |── kitti_infos_train.pkl
|   |── kitti_infos_val.pkl

Training and evaluation.

The configuration file is in tools/cfgs/3d_cascade_rcnn.yaml, and the training scripts is in tools/scripts.

cd tools
sh scripts/3d-cascade-rcnn.sh

Test a pre-trained model

The pre-trained KITTI model is at: model. Run with:

cd tools
sh scripts/3d-cascade-rcnn_test.sh

The evaluation results should be like:

2021-08-10 14:06:14,608   INFO  Car [email protected], 0.70, 0.70:
bbox AP:97.9644, 90.1199, 89.7076
bev  AP:90.6405, 89.0829, 88.4391
3d   AP:90.0468, 86.0168, 79.2661
aos  AP:97.91, 90.00, 89.48
Car [email protected], 0.70, 0.70:
bbox AP:99.1663, 95.8055, 93.3149
bev  AP:96.3107, 92.4128, 89.9473
3d   AP:93.1961, 86.1857, 83.4783
aos  AP:99.13, 95.65, 93.03
Car [email protected], 0.50, 0.50:
bbox AP:97.9644, 90.1199, 89.7076
bev  AP:98.0539, 97.1877, 89.7716
3d   AP:97.9921, 90.1001, 89.7393
aos  AP:97.91, 90.00, 89.48
Car [email protected], 0.50, 0.50:
bbox AP:99.1663, 95.8055, 93.3149
bev  AP:99.1943, 97.8180, 95.5420
3d   AP:99.1717, 95.8046, 95.4500
aos  AP:99.13, 95.65, 93.03

Acknowledge

The code is built on OpenPCDet and Voxel R-CNN.

3D cascade RCNN for object detection on point cloud

Related tags

Overview

3D Cascade RCNN

Results on KITTI

Results on Waymo

Installation

Getting Started

Prepare for the data.

Training and evaluation.

Test a pre-trained model

Acknowledge

Owner

Qi Cai

Arch-Net: Model Distillation for Architecture Agnostic Model Deployment

GLNet for Memory-Efficient Segmentation of Ultra-High Resolution Images

Pytorch implementation for our ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering".

Image Segmentation Evaluation

Code for our SIGCOMM'21 paper "Network Planning with Deep Reinforcement Learning".

Practical tutorials and labs for TensorFlow used by Nvidia, FFN, CNN, RNN, Kaggle, AE

Code for Understanding Pooling in Graph Neural Networks

A project which aims to protect your privacy using inexpensive hardware and easily modifiable software

MIMIC Code Repository: Code shared by the research community for the MIMIC-III database

Simple Python project using Opencv and datetime package to recognise faces and log attendance data in a csv file.

No Code AI/ML platform

Repository for the Bias Benchmark for QA dataset.

Bianace Prediction Pytorch Model

A benchmark dataset for mesh multi-label-classification based on cube engravings introduced in MeshCNN

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals, CVPR2021

Converting CPT to bert form for use

Simulation-based inference for the Galactic Center Excess

Learning Neural Painters Fast! using PyTorch and Fast.ai

Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation

Official implementation of "Articulation Aware Canonical Surface Mapping"