论文标题
随时随地：截止日期感知3D对象检测
Anytime-Lidar: Deadline-aware 3D Object Detection
论文作者
论文摘要
在这项工作中，我们提出了一个新颖的调度框架，可随时对基于深神经网络（DNN）的3D对象检测管道的感知。我们专注于计算昂贵的区域建议网络（RPN）和每个类别多头检测器组件，这些探测器组件在3D对象检测管道中很常见，并使它们变得截止日期。我们提出了一种调度算法，该算法智能选择了组件的子集，以实现有效的时间和准确的权衡。我们通过通过估计将先前检测到的对象投射到当前场景上，从而最大程度地减少跳过某些神经网络子组件的准确性损失。我们将方法应用于ART 3D对象检测网络，Pointpillars，并使用Nuscenes数据集评估其在Jetson Xavier Agx上的性能。与基线相比，在各种截止日期限制下，我们的方法可显着提高网络的准确性。
In this work, we present a novel scheduling framework enabling anytime perception for deep neural network (DNN) based 3D object detection pipelines. We focus on computationally expensive region proposal network (RPN) and per-category multi-head detector components, which are common in 3D object detection pipelines, and make them deadline-aware. We propose a scheduling algorithm, which intelligently selects the subset of the components to make effective time and accuracy trade-off on the fly. We minimize accuracy loss of skipping some of the neural network sub-components by projecting previously detected objects onto the current scene through estimations. We apply our approach to a state-of-art 3D object detection network, PointPillars, and evaluate its performance on Jetson Xavier AGX using nuScenes dataset. Compared to the baselines, our approach significantly improve the network's accuracy under various deadline constraints.
