Learning Visual Odometry with a Convolutional Network

We present an approach to predicting velocity and direction changes from visual information (”visual odometry”) using an end-to-end, deep learning-based architecture. The architecture uses a single type of computational module and learning rule to extract visual motion, depth, and finally odometry information from the raw data. Representations of depth and motion are extracted by detecting synchrony across time and stereo channels using network layers with multiplicative interactions. The extracted representations are turned into information about changes in velocity and direction using a convolutional neural network. Preliminary results show that the architecture is capable of learning the resulting mapping from video to egomotion.