自動運転向けピラーベース物体検出
Pillar-based Object Detection for Autonomous Driving
点群の極端な疎性に着目し、アンカー不要のピラーベース手法で3D物体検出を行うフレームワークを提案した論文。
著者: Yue Wang, Alireza Fathi, Abhijit Kundu, David Ross, Caroline Pantofaru, Thomas Funkhouser, Justin Solomon
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
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.
