arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.06326cs.CV
收藏

PIXOR:基于点云的实时的三维目标检测

PIXOR: Real-time 3D Object Detection from Point Clouds

Uber Advanced Technologies Group(优步先进技术集团);University of Toronto(多伦多大学)

Bin Yang, Wenjie Luo, Raquel Urtasun

摘要:

我们解决的问题,实时的【形】三维目标检测从点云自动驾驶的背景下。计算速度至关重要,因为检测是安全的必要组成部分。然而,现有的方法是昂贵的计算,由于高维的点云。我们利用3D数据更有效地表示从鸟瞰图(BEV)的场景,并提出PIXOR,一个无命题,单级检测器,输出面向3D对象的估计解码像素明智的神经网络预测。输入表示、网络架构和模型优化都经过特别设计,以平衡高精度和实时的【形】效率。我们在两个数据集上验证PIXOR:KITTI BEV目标检测基准和大规模3D车辆检测基准。在这两个数据集中,我们表明,所提出的检测器优于其他最先进的方法,特别是在平均精度(AP)方面,同时仍然运行在>28 FPS。

英文摘要:

We address the problem of real-time 3D object detection from point clouds in the context of autonomous driving. Computation speed is critical as detection is a necessary component for safety. Existing approaches are, however, expensive in computation due to high dimensionality of point clouds. We utilize the 3D data more efficiently by representing the scene from the Bird's Eye View (BEV), and propose PIXOR, a proposal-free, single-stage detector that outputs oriented 3D object estimates decoded from pixel-wise neural network predictions. The input representation, network architecture, and model optimization are especially designed to balance high accuracy and real-time efficiency. We validate PIXOR on two datasets: the KITTI BEV object detection benchmark, and a large-scale 3D vehicle detection benchmark. In both datasets we show that the proposed detector surpasses other state-of-the-art methods notably in terms of Average Precision (AP), while still runs at >28 FPS.

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。

↑