Pillar-Based Object Detection for Autonomous Driving
Abstract
We present a simple and flexible object detection framework optimized for autonomous driving. Building on the observation that point clouds in this application are extremely sparse, we propose a practical pillar-based approach to fix the imbalance issue caused by anchors. In particular, our algorithm incorporates a cylindrical projection into multi-view feature learning, predicts bounding box parameters per pillar rather than per point or per anchor, and includes an aligned pillar-to-point projection module to improve the final prediction. Our anchor-free approach avoids hyperparameter search associated with past methods, simplifying 3D object detection while significantly improving upon state-of-the-art.
Cite
Text
Wang et al. "Pillar-Based Object Detection for Autonomous Driving." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58542-6_2Markdown
[Wang et al. "Pillar-Based Object Detection for Autonomous Driving." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/wang2020eccv-pillarbased/) doi:10.1007/978-3-030-58542-6_2BibTeX
@inproceedings{wang2020eccv-pillarbased,
title = {{Pillar-Based Object Detection for Autonomous Driving}},
author = {Wang, Yue and Fathi, Alireza and Kundu, Abhijit and Ross, David A. and Pantofaru, Caroline and Funkhouser, Tom and Solomon, Justin},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2020},
doi = {10.1007/978-3-030-58542-6_2},
url = {https://mlanthology.org/eccv/2020/wang2020eccv-pillarbased/}
}