arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.15540cs.CV
收藏

基于核线引导的深度目标匹配场景变化检测

Epipolar-Guided Deep Object Matching for Scene Change Detection

The University of Tokyo(东京大学);National Institute of Advanced Industrial Science and Technology (AIST)(产业技术综合研究所)

Kento Doi, Ryuhei Hamaguchi, Shun Iwase, Rio Yokota, Yutaka Matsuo, Ken Sakurada

摘要:

本文描述了一个视点鲁棒的基于对象的变化检测网络(OBJ-CDNet)。由于相机轨迹和快门定时的差异,行车记录仪等移动相机每次都从不同的视点捕获图像。然而,以前的方法,逐像素的变化检测是脆弱的视点差异,因为他们假设对齐的图像对作为输入。为了解决这个困难,我们引入了一个深度图匹配网络,它在图像对之间建立对象对应关系。介绍使我们能够检测对象明智的场景变化,而无需精确的图像对齐。为了更准确的对象匹配,我们提出了一个核线引导的深度图匹配网络(EGMNet),它将核线约束纳入OBJCDNet中使用的深度图匹配层。为了评估我们的网络对视点差异的鲁棒性,我们从图像对中创建了用于场景变化检测的合成和真实数据集。实验结果验证了该网络的有效性。

英文摘要:

This paper describes a viewpoint-robust object-based change detection network (OBJ-CDNet). Mobile cameras such as drive recorders capture images from different viewpoints each time due to differences in camera trajectory and shutter timing. However, previous methods for pixel-wise change detection are vulnerable to the viewpoint differences because they assume aligned image pairs as inputs. To cope with the difficulty, we introduce a deep graph matching network that establishes object correspondence between an image pair. The introduction enables us to detect object-wise scene changes without precise image alignment. For more accurate object matching, we propose an epipolar-guided deep graph matching network (EGMNet), which incorporates the epipolar constraint into the deep graph matching layer used in OBJCDNet. To evaluate our network's robustness against viewpoint differences, we created synthetic and real datasets for scene change detection from an image pair. The experimental results verified the effectiveness of our network.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑