MCF3D: Multi-Stage Complementary Fusion for Multi-sensor 3D Object Detection
J.R.Wang; M.Zhu; D.Y.Sun; B.Wang; W.Gao; H.Wei
刊名Ieee Access
2019
卷号7页码:90801-90814
关键词3D object detection,multi-sensor fusion,attention mechanism,autonomous driving,cloud,Computer Science,Engineering,Telecommunications
ISSN号2169-3536
DOI10.1109/access.2019.2927012
英文摘要We present MCF3D, a multi-stage complementary fusion three-dimensional (3D) object detection network for autonomous driving, robot navigation, and virtual reality. This is an end-to-end learnable architecture, which takes both LIDAR point clouds and RGB images as inputs and utilizes a 3D region proposal subnet and second stage detector(s) subnet to achieve high-precision oriented 3D bounding box prediction. To fully exploit the strength of multimodal information, we design a series of fine and targeted fusion methods based on the attention mechanism and prior knowledge, including "pre-fusion," "anchorfusion," and "proposal-fusion." Our proposed RGB-Intensity form encodes the reflection intensity onto the input image to strengthen the representational power. Our designed proposal-element attention module allows the network to be guided to focus more on efficient and critical information with negligible overheads. In addition, we propose a cascade-enhanced detector for small classes, which is more selective against close false positives. The experiments on the challenging KITTI benchmark show that our MCF3D method produces state-of-the-art results while running in near real-time with a low memory footprint.
语种英语
内容类型期刊论文
源URL[http://ir.ciomp.ac.cn/handle/181722/63008]  
专题中国科学院长春光学精密机械与物理研究所
推荐引用方式
GB/T 7714
J.R.Wang,M.Zhu,D.Y.Sun,et al. MCF3D: Multi-Stage Complementary Fusion for Multi-sensor 3D Object Detection[J]. Ieee Access,2019,7:90801-90814.
APA J.R.Wang,M.Zhu,D.Y.Sun,B.Wang,W.Gao,&H.Wei.(2019).MCF3D: Multi-Stage Complementary Fusion for Multi-sensor 3D Object Detection.Ieee Access,7,90801-90814.
MLA J.R.Wang,et al."MCF3D: Multi-Stage Complementary Fusion for Multi-sensor 3D Object Detection".Ieee Access 7(2019):90801-90814.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace