Shao Ruizhe, Du Chun, Chen Hao, Li Jun
Department of Cognitive Communication, College of Electronic Science and Technology, National University of Defense Technology, Changsha, Hunan 410000, China.
Sensors (Basel). 2020 Apr 3;20(7):2007. doi: 10.3390/s20072007.
With the development of unmanned aerial vehicle (UAV) techniques, UAV images are becoming more widely used. However, as an essential step of UAV image application, the computation of stitching remains time intensive, especially for emergency applications. Addressing this issue, we propose a novel approach to use the position and pose information of UAV images to speed up the process of image stitching, called FUIS (fast UAV image stitching). This stitches images by feature points. However, unlike traditional approaches, our approach rapidly finds several anchor-matches instead of a lot of feature matches to stitch the image. Firstly, from a large number of feature points, we design a method to select a small number of them that are more helpful for stitching as anchor points. Then, a method is proposed to more quickly and accurately match these anchor points, using position and pose information. Experiments show that our method significantly reduces the time consumption compared with the-state-of-art approaches with accuracy guaranteed.
随着无人机（UAV）技术的发展，无人机图像的应用越来越广泛。然而，作为无人机图像应用的关键步骤，图像拼接的计算仍然耗时较长，特别是在应急应用中。为了解决这个问题，我们提出了一种新颖的方法，利用无人机图像的位置和姿态信息来加速图像拼接过程，称为FUIS（快速无人机图像拼接）。该方法通过特征点进行图像拼接。然而，与传统方法不同的是，我们的方法通过快速找到几个锚点匹配而不是大量的特征匹配来拼接图像。首先，从大量特征点中，我们设计了一种方法来选择少量对拼接更有帮助的特征点作为锚点。然后，提出了一种利用位置和姿态信息更快、更准确地匹配这些锚点的方法。实验表明，与现有最先进的方法相比，我们的方法在保证精度的同时显著减少了时间消耗。
