OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication

By Runsheng Xu, Hao Xiang, Xin Xia, Xu Han, Jinlong Liu, Jiaqi Ma. IEEE International Conference on Robotics and Automation, 2021

664 citations recorded by the source corpus.

Employing Vehicle-to-Vehicle communication to enhance perception performance in self-driving technology has attracted considerable attention recently; however, the absence of a suitable open dataset for benchmarking algorithms has made it difficult to develop and assess cooperative perception technologies. To this end, we present the first large-scale open simulated dataset for Vehicle-to-Vehicle perception. It contains over 70 interesting scenes, 11,464 frames, and 232,913 annotated 3D vehicle bounding boxes, collected from 8 towns in CARLA and a digital town of Culver City, Los Angeles. We then construct a comprehensive benchmark with a total of 16 implemented models to evaluate several information fusion strategies (i.e. early, late, and intermediate fusion) with state-of-the-art LiDAR detection algorithms. Moreover, we propose a new Attentive Intermediate Fusion pipeline to aggregate information from multiple connected vehicles. Our experiments show that the proposed pipeline can be easily integrated with existing 3D LiDAR detectors and achieve outstanding performance even with large compression rates. To encourage more researchers to investigate Vehicle-to-Vehicle perception, we will release the dataset, benchmark methods, and all related codes in https://mobility-lab.seas.ucla.edu/opv2v/.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/96bf7e5f028f46391f8ba5cac34bdadf5b6fd163

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

Citations in the corpus

V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving (2022, background): “Moreover, OPV2V [20] and CODD [28] only support the detection task in the V2V scenario.”
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers (2022, methodology): “We compare with the state-of-the-art multi-agent perception algorithms: F-Cooper [21], AttFuse [12], V2VNet [20], and DiscoNet [14].”
V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer (2022, methodology): “(a) OPV2V [44] (b) V2VNet [39] (c) DiscoNet [21] (d) V2X-ViT (ours)”
ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions (2022, background): “OD has many applications, such as fraud detection ([3], [4], [5]), network intrusion detection ([6], [7]), social media analysis ([8], [9]), video analysis [10], intelligent transportation [11], [12], [13], and data generation [14].”
V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception (2023, methodology): “, 3D bounding boxes, confidence scores) are shared, then fused to a ‘consensus’ prediction, and (3) Intermediate Fusion [4,27,42,55] where intermediate representations are extracted based on each agent’s observation and then shared with CAVs.”