点云
计算机科学
水准点(测量)
人工智能
代表(政治)
激光雷达
目标检测
计算机视觉
特征(语言学)
对象(语法)
最小边界框
RGB颜色模型
跳跃式监视
点(几何)
编码
国家(计算机科学)
方案(数学)
传感器融合
模式识别(心理学)
图像(数学)
算法
地理
数学
遥感
语言学
哲学
数学分析
化学
基因
法学
政治
几何学
政治学
大地测量学
生物化学
作者
Xiaozhi Chen,Huimin Ma,Ji Wan,Bo Li,Tian Xia
标识
DOI:10.48550/arxiv.1611.07759
摘要
This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D bounding boxes. We encode the sparse 3D point cloud with a compact multi-view representation. The network is composed of two subnetworks: one for 3D object proposal generation and another for multi-view feature fusion. The proposal network generates 3D candidate boxes efficiently from the bird's eye view representation of 3D point cloud. We design a deep fusion scheme to combine region-wise features from multiple views and enable interactions between intermediate layers of different paths. Experiments on the challenging KITTI benchmark show that our approach outperforms the state-of-the-art by around 25% and 30% AP on the tasks of 3D localization and 3D detection. In addition, for 2D detection, our approach obtains 10.3% higher AP than the state-of-the-art on the hard data among the LIDAR-based methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI