Guided Feature Selection for Deep Visual Odometry

Abstract

We present a novel end-to-end visual odometry architecture with guided feature selection based on deep convolutional recurrent neural networks. Different from current monocular visual odometry methods, our approach is established on the intuition that features contribute discriminately to different motion patterns. Specifically, we propose a dual-branch recurrent network to learn the rotation and translation separately by leveraging current Convolutional Neural Network (CNN) for feature representation and Recurrent Neural Network (RNN) for image sequence reasoning. To enhance the ability of feature selection, we further introduce an effective context-aware guidance mechanism to force each branch to distill related information for specific motion pattern explicitly. Experiments demonstrate that on the prevalent KITTI and ICL_NUIM benchmarks, our method outperforms current state-of-the-art model- and learning-based methods for both decoupled and joint camera pose recovery.

Accepted to ACCV 2018

References in corpus (9)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
• DeMoN: Depth and Motion Network for Learning Monocular Stereo
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• FlowNet: Learning Optical Flow with Convolutional Networks
• Context-aware Deep Feature Compression for High-speed Visual Tracking
• GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
• Direct Sparse Odometry
• UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning