Constructing big panorama from video sequence based on deep local feature
Constructing big panorama from video sequence based on deep local feature
复制标题
基于深度局部特征的视频序列构建大全景
DOI：
10.1016/j.imavis.2020.103972
复制
发表时间：
2020-09-01
影响因子：
4.7
通讯作者：
Liu, Xiaoping
中科院分区：
文献类型：
--
作者：
Cao, Mingwei;Zheng, Liping;Liu, Xiaoping
构建高质量全景图是计算机视觉和计算机图形学领域的一项基本任务，因此产生了许多用于全景图构建的图像拼接方法。然而，传统的图像拼接方法构造的全景图视角有限，计算成本高。为了解决这些问题，本文提出利用视频序列作为输入来构建大全景图像，从而获得高质量的全景图像，该方法是建立在稳定视频和鲁棒特征跟踪方法的基础上的。具体来说，输入的视频序列是通过移动的手持摄像机捕获的，这可以是任何类型的消费级摄像机。为了减轻卷帘式快门对视频的影响，提出了一种新的视频稳像方法，对不稳定的摄像机路径进行滤波，从而得到稳定的全景视频。此外，提出了一种基于深度局部特征的特征跟踪方法，生成连续视频帧之间的特征对应关系，用于视频稳定和图像拼接中的摄像机运动估计。最后，在基准数据集上进行了全面的实验，以验证所提出方法的有效性。(C) 2020 Elsevier B.V.版权所有
Constructing high-quality panorama is a fundamental task in both computer vision and computer graphics communities, thus, leading to many image stitching approaches for panorama construction. However, panorama constructed by traditional image stitching has a limited angle of view and has an expensively computational cost. To defend the issues, in this paper, we proposed to use video sequence as input for constructing big panorama, resulting in a high-quality panoramic image, the presented method is built on the stabilized video and robust feature tracking method. Specifically, the input video sequences are captured by moving hand cameras which can be any type of consumer-level camera. To mitigate the affections from rolling shutters in videos, a novel video stabilization method is introduced to filter the unstable camera's path, then resulting in a stabilized video for panorama construction. Additionally, a deep local feature-based feature tracking method is proposed to produce feature correspondences between consecutive video frames for camera motion estimation used in both video stabilization and image stitching. Finally, a comprehensive experiment conducted on the benchmarking datasets is presented to demonstrate the effectiveness of the proposed method. (C) 2020 Elsevier B.V. All rights reserved.