Accurate Object Detection in Smart Transportation Using Multiple Cameras
Accurate Object Detection in Smart Transportation Using Multiple Cameras
复制标题
DOI：
10.1109/metrocad48866.2020.00011
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Zhinan Qiao;Andrew Sansom;M. McGuire;Andrew Kalaani;Xu Ma;Qing Yang;Song Fu
中科院分区：
文献类型：
--
作者：
Zhinan Qiao;Andrew Sansom;M. McGuire;Andrew Kalaani;Xu Ma;Qing Yang;Song Fu
近年来，为了获得更好的性能，连通目标检测受到越来越多的关注。最有趣的领域之一是以一种相互关联的方式从多个资源中学习。本文针对智能交通系统，提出了一种基于多摄像头的连通目标检测方法。该体系结构由三部分组成：对齐框架、深度多视角融合网络和目标检测网络。通过实验验证了我们提出的体系结构的性能。
Recently, more and more attention has been paid to the connected object detection for better performance. One of the most interesting fields is learning from multiple resources in a connected fashion. In this paper, we present a connected object detection method using multiple cameras for the smart transportation system. The proposed architecture consists of three parts: an alignment framework, a deep multi-view fusion network and an object detection network. Experiments are conducted to illustrate the performance of our proposed architecture.