期刊
AUTONOMOUS ROBOTS
卷 42, 期 7, 页码 1301-1322出版社
SPRINGER
DOI: 10.1007/s10514-018-9734-5
关键词
Change detection; Deep learning; Visual SLAM; Deconvolutional neural networks
资金
- Toshiba Research Europe
- Spanish MEC Project [TRA2014-57088-C2-1-R]
- NVIDIA Corporation
We propose a system for performing structural change detection in street-view videos captured by a vehicle-mounted monocular camera over time. Our approach is motivated by the need for more frequent and efficient updates in the large-scale maps used in autonomous vehicle navigation. Our method chains a multi-sensor fusion SLAM and fast dense 3D reconstruction pipeline, which provide coarsely registered image pairs to a deep Deconvolutional Network (DN) for pixel-wise change detection. We investigate two DN architectures for change detection, the first one is based on the idea of stacking contraction and expansion blocks while the second one is based on the idea of Fully Convolutional Networks. To train and evaluate our networks we introduce a new urban change detection dataset which is an order of magnitude larger than existing datasets and contains challenging changes due to seasonal and lighting variations. Our method outperforms existing literature on this dataset, which we make available to the community, and an existing panoramic change detection dataset, demonstrating its wide applicability.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据