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 2007.00493cs.CVeess.IVeess.SP
收藏

点云中3D目标检测的PointPillars网络优化

Optimisation of the PointPillars network for 3D object detection in point clouds

AGH University of Science and Technology(AGH科技大学)

Joanna Stanisz, Konrad Lis, Tomasz Kryjak, Marek Gorgon

摘要:

在本文中,我们介绍了我们对深度神经网络的优化研究,用于点云中的3D目标检测。使用了Brevitas和PyTorch工具中提供的量化和修剪等技术。我们对PointPillars网络进行了实验,该网络在检测精度和计算复杂度之间提供了合理的折衷。这项工作的目的是提出一个变种的网络,我们将最终实现在FPGA设备。这将允许以低能耗进行实时LiDAR数据处理。所获得的结果表明,即使在算法的主要部分中从32位浮点到2位整数的显著量化,也会导致检测精度降低5%-9%,同时允许模型大小减少近16倍。

英文摘要:

In this paper we present our research on the optimisation of a deep neural network for 3D object detection in a point cloud. Techniques like quantisation and pruning available in the Brevitas and PyTorch tools were used. We performed the experiments for the PointPillars network, which offers a reasonable compromise between detection accuracy and calculation complexity. The aim of this work was to propose a variant of the network which we will ultimately implement in an FPGA device. This will allow for real-time LiDAR data processing with low energy consumption. The obtained results indicate that even a significant quantisation from 32-bit floating point to 2-bit integer in the main part of the algorithm, results in 5%-9% decrease of the detection accuracy, while allowing for almost a 16-fold reduction in size of the model.

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。

↑