opencoodx 0.1.19

An opensource pytorch framework for autonomous driving cooperative detection

OpenCOODX

Overview

OpenCOOD is an Open COOperative Detection framework for autonomous driving. It is also the official implementation of the ICRA 2022 [Website] [Paper: OPV2V] [Documents] [OpenCOOD]

opencoodx is a ready-to-go package of OpenCOOD. You can install it easily by using pip.

Installation

pip install opencoodx

# to upgrade 
pip install --upgrade opencoodx

Features

• Provide easy data API for the Vehicle-to-Vehicle (V2V) multi-modal perception dataset OPV2V

  It currently provides easy API to load LiDAR data from multiple agents simultaneously in a structured format and convert to PyTorch Tesnor directly for model use.

• Provide multiple SOTA 3D detection backbone

  It supports state-of-the-art LiDAR detector including PointPillar, Pixor, VoxelNet, and SECOND.

• Support most common fusion strategies

  It includes 3 most common fusion strategies: early fusion, late fusion, and intermediate fusion across different agents.

• Support several SOTA multi-agent visual fusion model

  It supports the most recent multi-agent perception algorithms (currently up to Sep. 2021) including Attentive Fusion, Cooper (early fusion), F-Cooper, V2VNet etc. We will keep updating the newest algorithms.

• Provide a convenient log replay toolbox for OPV2V dataset (coming soon)

  It also provides an easy tool to replay the original OPV2V dataset. More importantly, it allows users to enrich the original dataset by attaching new sensors or define additional tasks (e.g. tracking, prediction) without changing the events in the initial dataset (e.g. positions and number of all vehicles, traffic speed).

Prerequisite - Dependency

1. Pytorch Installation (>=1.10)

Go to https://pytorch.org/ to install pytorch cuda version. Pytorch 1.11 version is recommended.

2. Spconv (2.x)

Install spconv 2.x based on your cuda version. For more details, please check: https://pypi.org/project/spconv/

3. Bbx IOU cuda version compile

Install bbx nms calculation cuda version using following command:

opencoodx --bbx

Prerequisite - Data files

1. Download trained model files

To download these models, you can run the following command in your terminal:

# download all models 
opencoodx --model all
# download one model
opencoodx --model ${model_name}

Arguments Explanation:

• all: To download all models

• model_name: We have 11 trained models that are ready to use, you can choose from the following:

  • pointpillar_attentive_fusion

  • pointpillar_early_fusion

  • pointpillar_fcooper

  • pointpillar_late_fusion

  • v2vnet

  • voxelnet_early_fusion

  • voxelnet_attentive_fusion

  • second_early_fusion

  • second_attentive_fusion

  • second_late_fusion

  • pixor_early_fusion

2. Offline data download (optional)

To download offline dataset, you can simply use the command:

opencoodx --data ${dataset_name}

Arguments Explanation:

• dataset_name: str type. There are 4 different dataset_name. You can choose from 'test_culver_city', 'test', 'validate' or 'train'

Quick Start

Data sequence visualization

To quickly visualize the LiDAR stream in the OPV2V dataset, you need to download offline data to your current working directory and the run the following command:

opencoodx --vis_data ${dataset_name} --vis_color ${color_mode}

Arguments Explanation:

• dataset_name: str type, including dataset you've download. You can choose from 'test_culver_city', 'test', 'validate' or 'train'

• color_mode : str type, indicating the lidar color rendering mode. You can choose from 'constant', 'intensity' or 'z-value'.

Benchmark and model zoo

Results on OPV2V dataset (AP@0.7 for no-compression/ compression)

	Backbone	Fusion Strategy	Bandwidth (Megabit), before/after compression	Default Towns	Culver City	Download
Naive Late	PointPillar	Late	0.024/0.024	0.781/0.781	0.668/0.668	url
Cooper	PointPillar	Early	7.68/7.68	0.800/x	0.696/x	url
Attentive Fusion	PointPillar	Intermediate	126.8/1.98	0.815/0.810	0.735/0.731	url
F-Cooper	PointPillar	Intermediate	72.08/1.12	0.790/0.788	0.728/0.726	url
V2VNet	PointPillar	Intermediate	72.08/1.12	0.822/0.814	0.734/0.729	url
Naive Late	VoxelNet	Late	0.024/0.024	0.738/0.738	0.588/0.588	url
Cooper	VoxelNet	Early	7.68/7.68	0.758/x	0.677/x	url
Attentive Fusion	VoxelNet	Intermediate	576.71/1.12	0.864/0.852	0.775/0.746	url
Naive Late	SECOND	Late	0.024/0.024	0.775/0.775	0.682/0.682	url
Cooper	SECOND	Early	7.68/7.68	0.813/x	0.738/x	url
Attentive	SECOND	Intermediate	63.4/0.99	0.826/0.783	0.760/0.760	url
Naive Late	PIXOR	Late	0.024/0.024	0.578/0.578	0.360/0.360	url
Cooper	PIXOR	Early	7.68/7.68	0.678/x	0.558/x	url
Attentive	PIXOR	Intermediate	313.75/1.22	0.687/0.612	0.546/0.492	url

Note:

• We suggest using PointPillar as the backbone when you are creating your method and try to compare with our benchmark, as we implement most of the SOTA methods with this backbone only.
• We assume the transimssion rate is 27Mbp/s. Considering the frequency of LiDAR is 10Hz, the bandwidth requirement should be less than 2.7Mbp to avoid severe delay.
• A 'x' in the benchmark table represents the bandwidth requirement is too large, which can not be considered to employ in practice.

Tutorials

We have a series of tutorials to help you understand OpenCOOD more. Please check the series of our tutorials.

Citation

If you are using our OpenCOOD framework or OPV2V dataset for your research, please cite the following paper:

@inproceedings{xu2022opencood,
 author = {Runsheng Xu, Hao Xiang, Xin Xia, Xu Han, Jinlong Li, Jiaqi Ma},
 title = {OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication},
 booktitle = {2022 IEEE International Conference on Robotics and Automation (ICRA)},
 year = {2022}}

Also, under this LICENSE, OpenCOOD is for non-commercial research only. Researchers can modify the source code for their own research only. Contracted work that generates corporate revenues and other general commercial use are prohibited under this LICENSE. See the LICENSE file for details and possible opportunities for commercial use.

Future Plans

• Provide camera APIs for OPV2V
• Provide the log replay toolbox
• Implement F-Cooper
• Implement V2VNet
• Implement DiscoNet

Contributors

OpenCOOD is supported by the UCLA Mobility Lab. We also appreciate the great work from OpenPCDet, as part of our works use their framework.

Lab Principal Investigator:

• Dr. Jiaqi Ma (linkedin, UCLA Samueli)

Project Lead:

• Runsheng Xu (linkedin, github)
  
• Hao Xiang (linkedin, github)