基于多尺度残差网络的单应估计方法

Homography estimation method based on multi-scale residual network

单应估计是许多计算机视觉任务中一个基础且重要的步骤。传统单应估计方法基于特征点匹配,难以在弱纹理图像中工作。深度学习已经应用于单应估计以提高其鲁棒性,但现有方法均未考虑到由于物体尺度差异导致的多尺度问题,所以精度受限。针对上述问题,提出了一种用于单应估计的多尺度残差网络。该网络能够提取图像的多尺度特征信息,并使用多尺度特征融合模块对特征进行有效融合,此外还通过估计四角点归一化偏移进一步降低了网络优化难度。实验表明,在MS-COCO数据集上,该方法平均角点误差仅为0.788个像素,达到了亚像素级的精度,并且在99%情况下能够保持较高的精度。由于综合利用了多尺度特征信息且更容易优化,该方法精度显著提高,并具有更强的鲁棒性。

Homography estimation is a basic and important step in many computer vision tasks.Traditional homography estimation methods are based on feature point matching,which are difficult to work in weak texture images.Deep learning has been applied to homography estimation to improve its robustness,but the existing methods do not consider the multi-scale pro-blem caused by object scale differences,resulting in limited accuracy.To solve the above problems,this paper proposed a multi-scale residual network for homography estimation.The network could extract the multi-scale feature of the image,and used the multi-scale feature fusion module to effectively fuse the features.In addition,it further reduced the difficulty of network optimization by estimating the four-corner normalized offset.Experiments on MS-COCO dataset show that the average corner error of this method is only 0.788 pixels,which achieves sub-pixel accuracy,and can maintain high accuracy in 99%of cases.Due to the comprehensive utilization of multi-scale features and easier to optimize,this method has significantly improved accuracy and stronger robustness.