arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10323cs.CVcs.LGcs.RO
收藏

基于支柱的自动驾驶目标检测

Pillar-based Object Detection for Autonomous Driving

MIT(麻省理工学院);Google(谷歌)

Yue Wang, Alireza Fathi, Abhijit Kundu, David Ross, Caroline Pantofaru, Thomas Funkhouser, Justin Solomon

摘要:

我们提出了一个简单而灵活的目标检测框架优化自动驾驶。基于此应用程序中的点云非常稀疏的观察结果,我们提出了一种实用的基于支柱的方法来解决锚点引起的不平衡问题。特别是,我们的算法将圆柱投影纳入多视图特征学习,预测每个柱而不是每个点或每个锚的限界框参数,并包括对齐的柱到点投影模块,以提高最终的预测。我们的无锚方法避免了与过去方法相关的超参数搜索,简化了3D目标检测,同时显着提高了最先进的。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑