• Corpus ID: 237532732

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

@article{Xu2021OPV2VAO,
  title={OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication},
  author={Runsheng Xu and Hao Xiang and Xin Xia and Xu Han and Jinlong Liu and Jiaqi Ma},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.07644}
}
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… 

Figures and Tables from this paper

Model-Agnostic Multi-Agent Perception Framework
TLDR
The proposed model-agnostic multi-agent framework to reduce the negative effect caused by model discrepancies and maintain confidentiality is proposed, and the results show that the proposed approach outperforms the state-of-the-art baseline methods for 3D object detection on the open OPV2V dataset.
V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer
TLDR
A robust cooperative perception framework with V2X communication using a novel vision Transformer architecture that sets new state-of-the-art performance for 3D object detection and achieves robust performance even under harsh, noisy environments.
COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles
TLDR
C OOPERNAUT is introduced, an end-to-end learning model that uses cross-vehicle perception for vision-based cooperative driving that encodes LiDAR information into compact point-based representations that can be transmitted as messages between vehicles via realistic wireless channels.
Accurate non-stationary short-term traffic flow prediction method
TLDR
A Long Short-Term Memory (LSTM) based method that can forecast the short-term traffic flow precisely and avoid local optimum problems during training is proposed and performs favorably against other state-of-the-art methods with better adaption performance on extreme outliers, delay effects, and trend- changing responses.
Disentangled Spatiotemporal Graph Generative Models
TLDR
A new Bayesian model is proposed that factorizes spatiotemporal graphs into spatial, temporal, and graph factors as well as the factors that explain the interplay among them to maximize the disentanglement among the factors with theoretical guarantees.
ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions
TLDR
A novel outlier detection method called ECOD (Empirical-Cumulative-distribution-based Outlier Detection), which is inspired by the fact that outliers are often the “rare events” that appear in the tails of a distribution.
Towards Better Driver Safety: Empowering Personal Navigation Technologies with Road Safety Awareness
TLDR
A definition for road safety is created that navigation systems can easily understand by adapting well-established safety standards from transportation studies and a machine learning-based road safety classifier is developed that predicts the safety level for road segments using a diverse feature set constructed only from publicly available geographic data.

References

SHOWING 1-10 OF 34 REFERENCES
V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction
TLDR
This paper explores the use of vehicle-to-vehicle (V2V) communication to improve the perception and motion forecasting performance of self-driving vehicles and shows that the approach of sending compressed deep feature map activations achieves high accuracy while satisfying communication bandwidth requirements.
PIXOR: Real-time 3D Object Detection from Point Clouds
TLDR
PIXOR is proposed, a proposal-free, single-stage detector that outputs oriented 3D object estimates decoded from pixel-wise neural network predictions that surpasses other state-of-the-art methods notably in terms of Average Precision (AP), while still runs at 10 FPS.
F-cooper: feature based cooperative perception for autonomous vehicle edge computing system using 3D point clouds
TLDR
To the best of the knowledge, this work is the first to introduce feature-level data fusion to connected autonomous vehicles for the purpose of enhancing object detection and making real-time edge computing on inter-vehicle data feasible for autonomous vehicles.
Cooper: Cooperative Perception for Connected Autonomous Vehicles Based on 3D Point Clouds
TLDR
This work is the first to conduct a study on raw-data level cooperative perception for enhancing the detection ability of self-driving systems and demonstrates it is possible to transmit point clouds data for cooperative perception via existing vehicular network technologies.
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
  • Yin Zhou, Oncel Tuzel
  • Computer Science, Environmental Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
VoxelNet is proposed, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network and learns an effective discriminative representation of objects with various geometries, leading to encouraging results in3D detection of pedestrians and cyclists.
OpenCDA: An Open Cooperative Driving Automation Framework Integrated with Co-Simulation
TLDR
This work proposes OpenCDA, a generalized framework and tool for developing and testing CDA systems that is highly modularized and installed with benchmark algorithms and test cases, and an example of platooning implementation is used to illustrate the framework's capability for CDA research.
Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles
TLDR
A federated learning (FL) based dynamic map fusion framework to achieve high map quality despite unknown numbers of objects in fields of view (FoVs), various sensing and model uncertainties, and missing data labels for online learning is proposed.
LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World
TLDR
This work develops a novel simulator that captures both the power of physics-based and learning-based simulation, and showcases LiDARsim's usefulness for perception algorithms-testing on long-tail events and end-to-end closed-loop evaluation on safety-critical scenarios.
Cooperative LIDAR Object Detection via Feature Sharing in Deep Networks
TLDR
In this paper, the concept of feature sharing for cooperative object detection (FSCOD) is introduced, and it is shown that the proposed approach has significant performance superiority over the conventional single-vehicle object detection approaches.
...
...