The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous driving. This paper studies monocular VO from the perspective of Deep Learning (DL). Unlike most current learning-based methods, our approach, called DeepAVO, is established on the intuition that features contribute discriminately to different motion patterns. Specifically, we present a novel four-branch network to learn the rotation and translation by leveraging Convolutional Neural Networks (CNNs) to focus on different quadrants of optical flow input. To enhance the ability of feature selection, we further introduce an effective channel-spatial attention mechanism to force each branch to explicitly distill related information for specific Frame to Frame (F2F) motion estimation. Experiments on various datasets involving outdoor driving and indoor walking scenarios show that the proposed DeepAVO outperforms the state-of-the-art monocular methods by a large margin, demonstrating competitive performance to the stereo VO algorithm and verifying promising potential for generalization.

视觉里程计 (VO) 技术通过分析车载摄像头捕获的图像序列来估计运动物体的位置和方向，随着人们对自动驾驶的兴趣日益浓厚，已经得到了很好的研究。本文从深度学习（DL）的角度研究单眼VO。与大多数当前基于学习的方法不同，我们的方法称为 DeepAVO，它建立在特征对不同运动模式有区别性贡献的直觉之上。具体来说，我们提出了一种新颖的四分支网络，通过利用卷积神经网络 (CNN) 专注于光流输入的不同象限来学习旋转和平移。为了增强特征选择的能力，我们进一步引入了一种有效的通道空间注意机制，以强制每个分支明确提取特定帧到帧 (F2F) 运动估计的相关信息。在涉及户外驾驶和室内步行场景的各种数据集上进行的实验表明，所提出的 DeepAVO 大大优于最先进的单目方法，证明了立体 VO 算法的竞争性能并验证了有前景的泛化潜力。