Skip to content

Official Repo of ITSC2024: Enhancing Indoor Mobility with Connected Sensor Nodes: A Real-Time, Delay-Aware Cooperative Perception Approach

Notifications You must be signed in to change notification settings

NingMingHao/MVSLab-IndoorCooperativePerception

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 

Repository files navigation

MVSLab-IndoorCooperativePerception

Official Repo of ITSC2024: "Enhancing Indoor Mobility with Connected Sensor Nodes: A Real-Time, Delay-Aware Cooperative Perception Approach" Authored by, Minghao Ning, Yaodong Cui, Yufeng Yang, Shucheng Huang, Zhenan Liu, Ahmad Reza Alghooneh, Ehsan Hashemi and Amir Khajepour.

For questions please contact Minghao Ning, [email protected].

Overview of the project

This cooperative perception project is a part of the MVSLab project, which aims to enhance indoor mobility with connected sensor nodes. The project is divided into two parts: local perception and global perception. The local perception is responsible for detecting and tracking objects in the local area of the sensor node. The global perception is responsible for fusing the local perception results from multiple sensor nodes to generate a global perception result. The proposed delay-aware cooperative perception framework is shown in the following figure. Cooperative Perception Framework

An overview of the whole project can be found in the following video: Watch the video

Dataset

The dataset is stored in ROS bag format. The required camera parameters are saved in camera_info, sensor transformations are saved in tf, so you can easily visualize each dataset via Rviz. The dataset is available at Google Drive.

The dataset is labeled with CVAT, the labels are oriented bounding boxes in the BEV (Bird's Eye View) format. An example is shown in: Watch the video

Results

Local Perception for varying density case

Watch the video

Local Perception for crowded case

Watch the video

Global Perception for 3People1Bed

Watch the video

Global Perception for 9People

Watch the video

Citation

If you find this work useful, please consider citing:

@inproceedings{ning2024enhancing,
  title={Enhancing Indoor Mobility with Connected Sensor Nodes: A Real-Time, Delay-Aware Cooperative Perception Approach},
  author={Ning, Minghao and Cui, Yaodong and Yang, Yufeng and Huang, Shucheng and Liu, Zhenan and Alghooneh, Ahmad Reza and Hashemi, Ehsan and Khajepour, Amir},
  booktitle={2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)},
  year={2024},
  organization={IEEE}
}

About

Official Repo of ITSC2024: Enhancing Indoor Mobility with Connected Sensor Nodes: A Real-Time, Delay-Aware Cooperative Perception Approach

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published