Authors:Jishu Miao;Tsubasa Hirakawa;Takayoshi Yamashita andHironobu Fujiyoshi
Affiliation:Chubu University, 1200 Matsumoto-cho, Kasugai, Aichi, Japan
Keyword(s):Object Detection, Deep Learning, Point Cloud Processing, Autonomous Vehicles.
Abstract:In this paper, we propose a novel point clouds based 3D object detection method for achieving higher-accuracy of autonomous driving. Different types of objects on the road has a different shape. A LiDAR sensor can provide a point cloud including more than ten thousand points reflected from object surfaces in one frame. Recent studies show that hand-crafted features directly extracted from point clouds can achieve nice detection accuracy. The proposed method employs YOLOv4 as feature extractor and gives Normal-map as additional input. Our Normal-map is a three channels bird’s eye view image, retaining detailed object surface normals. It makes the input information have more enhanced spatial shape information and can be associated with other hand-crafted features easily. In an experiment on the KITTI 3D object detection dataset, it performs better than conventional methods. Our method can achieve higher-precision 3D object detection and is less affected by distance. It has excellent yaw angle predictability for the object, especially for cylindrical objects like pedestrians, even if it omits the intensity information.(More)
In this paper, we propose a novel point clouds based 3D object detection method for achieving higher-accuracy of autonomous driving. Different types of objects on the road has a different shape. A LiDAR sensor can provide a point cloud including more than ten thousand points reflected from object surfaces in one frame. Recent studies show that hand-crafted features directly extracted from point clouds can achieve nice detection accuracy. The proposed method employs YOLOv4 as feature extractor and gives Normal-map as additional input. Our Normal-map is a three channels bird’s eye view image, retaining detailed object surface normals. It makes the input information have more enhanced spatial shape information and can be associated with other hand-crafted features easily. In an experiment on the KITTI 3D object detection dataset, it performs better than conventional methods. Our method can achieve higher-precision 3D object detection and is less affected by distance. It has excellent yaw angle predictability for the object, especially for cylindrical objects like pedestrians, even if it omits the intensity information.