基于图像对齐和不确定估计的深度视觉里程计

Deep Visual Odometry Based on Image Alignment and Uncertainty Estimation

基于深度学习的视觉里程计方法(deepvisualodometry,DVO)通过神经网络直接估计单目图像的深度和相邻图像之间的相机运动,在保证精度的同时大大提高了运行速度。但这是基于灰度不变假设,作为一个很强的假设,灰度不变假设在现实场景中往往难以满足。为此,提出一种基于图像对齐(imagealignment,IA)的直接视觉里程计方法AUDVO(alignedU-CNNdeepVO),通过不确定性估计网络(uncertaintyCNN,U-CNN)引入正则项进行约束,使得估计的结果更具鲁棒性。为了处理大面积纹理缺失区域上因估计不准确带来的空洞,在设计深度估计模块时通过嵌入超分辨率网络进行上采样。在公开的KITTI数据集上的实验证明了AUDVO在深度和相机位姿估计上的有效性。

Deep learning based visual odometry methods can directly estimate the depth of monocular images and camera movement between adjacent images,which achieve high accuracy and improve running speed.However,this is based on a strong assumption of gray scale invariance,which is often not satisfied in real scenes.As a consequence,a self-supervised method for direct visual odometry based on image alignment is proposed,which gets a robust estimation result with the uncertainty regularization terms estimated from the uncertainty estimation network(uncertainty CNN,U-CNN)and it is called AUDVO(aligned U-CNN deep VO).Meanwhile,a super resolution network is incorporated into the depth estima-tion module instead of using a simple interpolation operation for upsampling in order to deal with the holes caused by the inaccurate estimation in the large non-texture area.The evaluation results on the public KITTI datasets demonstrate the effectiveness of AUDVO for robust single-view depth estimation and visual odometry.