深層畳み込みネットワークによる占有格子地図上の物体検出と分類
Object Detection and Classification in Occupancy Grid Maps using Deep Convolutional Networks
距離センサ情報を多層格子地図に符号化し、深層畳み込みネットワークで回転バウンディングボックスと意味クラスを推定する手法を提案し、KITTI Bird's Eye Viewベンチマークで高精度を達成した。
著者: Sascha Wirges, Tom Fischer, Jesus Balado Frias, Christoph Stiller
分類: cs.CV, cs.RO
原文アブストラクト
A detailed environment perception is a crucial component of automated vehicles. However, to deal with the amount of perceived information, we also require segmentation strategies. Based on a grid map environment representation, well-suited for sensor fusion, free-space estimation and machine learning, we detect and classify objects using deep convolutional neural networks. As input for our networks we use a multi-layer grid map efficiently encoding 3D range sensor information. The inference output consists of a list of rotated bounding boxes with associated semantic classes. We conduct extensive ablation studies, highlight important design considerations when using grid maps and evaluate our models on the KITTI Bird's Eye View benchmark. Qualitative and quantitative benchmark results show that we achieve robust detection and state of the art accuracy solely using top-view grid maps from range sensor data.
