一种对光照和遮挡鲁棒的单应性估计方法  

A homography estimation method robust to illumination and occlusion

作　　者：范震 刘晓静[1] 李小波 崔亚超 FAN Zhen;LIU Xiao-jing;LI Xiao-bo;CUI Ya-chao(Department of Computer Technology and Application,Qinghai University,Xining Qinghai 810016,China)

机构地区：[1]青海大学计算机技术与应用系,青海西宁810016

出　　处：《图学学报》2023年第1期166-176,共11页Journal of Graphics

基　　金：国家自然科学基金项目(61862053,61863031)。

摘　　要：单应性估计是计算机视觉领域中的一项基本任务。为了提高单应性估计对光照和遮挡的鲁棒性,提出了一个基于无监督学习的单应性估计模型,该模型以2幅堆叠的图像为输入,以估计所得单应矩阵为输出。提出双向单应性估计平均光度损失;然后,为了增加感受野和提高网络模型对形变、位置变化等的抗性,为网络模型引入空间转换网络(STN)模块和变形卷积;最后,通过插入随机遮挡形状,首次将遮挡因素引入单应性估计任务的合成数据集,使训练出的模型对遮挡具有鲁棒性。与传统方法相比,该方法保持了相当或更好的准确性,且在估计低纹理或光照变化大的图像对的单应性时表现更好;与基于学习的单应性估计方法相比,该方法对遮挡具有鲁棒性,且在真实数据集上具有更好的表现。Homography estimation is a basic task in the field of computer vision. In order to improve the robustness of homography estimation to illumination and occlusion, a homography estimation model based on unsupervised learning was proposed. This model took two stacked images as input and the estimated homography matrix as output.The bidirectional homography was proposed to estimate the average photometric loss. Then, in order to increase the receptive field and improve the resistance of the network model to deformation and position change, we introduced the spatial transformer networks(STN) module and deformation convolution to the network model. Finally, by inserting random occlusion shapes, the occlusion factors were introduced into the synthetic dataset of the homography estimation task for the first time, thus making the trained model robust to occlusion. Compared with the traditional methods, the proposed method could maintain the same or achieve better accuracy, and give superior performance in estimating the homography of image pairs with low texture or large illumination changes. Compared with the learning-based homography estimation method, the proposed method is robust to occlusion and performs better on real datasets.

关 键 词：单应性估计 深度学习 无监督 数据增强 卷积神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]