Cooper: Cooperative Perception for Connected Autonomous Vehicles Based on 3D Point Clouds

By Qi Chen, Sihai Tang, Qing Yang, Song Fu. IEEE International Conference on Distributed Computing Systems, 2019

464 citations recorded by the source corpus.

Autonomous vehicles may make wrong decisions due to inaccurate detection and recognition. Therefore, an intelligent vehicle can combine its own data with that of other vehicles to enhance perceptive ability, and thus improve detection accuracy and driving safety. However, multi-vehicle cooperative perception requires the integration of real world scenes and the traffic of raw sensor data exchange far exceeds the bandwidth of existing vehicular networks. To the best our knowledge, we are the first to conduct a study on raw-data level cooperative perception for enhancing the detection ability of self-driving systems. In this work, relying on LiDAR 3D point clouds, we fuse the sensor data collected from different positions and angles of connected vehicles. A point cloud based 3D object detection method is proposed to work on a diversity of aligned point clouds. Experimental results on KITTI and our collected dataset show that the proposed system outperforms perception by extending sensing area, improving detection accuracy and promoting augmented results. Most importantly, we demonstrate it is possible to transmit point clouds data for cooperative perception via existing vehicular network technologies.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/7b81ea5021a637160c69aea3d473d4485028f1f9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Computer Vision and Pattern Recognition

In Environmental Engineering

Citations in the corpus

OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication (2021, methodology): “T&J dataset [11], [22] utilizes two golf carts equipped with 16-channel LiDAR for data collection.”
F-cooper: feature based cooperative perception for autonomous vehicle edge computing system using 3D point clouds (2019, methodology): “In (c), the top line is the result of our voxel fusion and the bottom line is the result of Cooper [3].”
Learning Distilled Collaboration Graph for Multi-Agent Perception (2021, background): “Early collaboration [3] aggregates the raw measurements from all the agents, promoting a holistic perspective; see Fig.”
V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer (2022, background): “be divided into 3 categories: 1) early fusion [5] where raw data is shared and gathered to form a holistic view, 2) intermediate fusion [39,44,36,4] where intermediate neural features are extracted based on each agent’s observation and then transmitted, and 3) late fusion [28,29] where detection out”
V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception (2023, methodology): “We benchmark a number of leading intermediate methods, including AttFuse [50], F-Cooper [4], V2VNet [40], V2X-Vit [49], and CoBEVT [47] (see Sec.”
V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction (2020, methodology): “[8] aggregate LiDAR point clouds from other vehicles, followed by a deep network for detection.”
Cooperative Perception for 3D Object Detection in Driving Scenarios Using Infrastructure Sensors (2019, methodology): “We would like to note that authors in [19] and [20] simulate an environment where two vehicles share their sensors’ information by using point clouds from the KITTI dataset [4] generated by the same vehicle at two time instants.”
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers (2022, unknown): “early fusion) [17, 18] or detection outputs (i.”