Exploiting Semantic Information and Deep Matching for Optical Flow [article]

Min Bai, Wenjie Luo, Kaustav Kundu, Raquel Urtasun
2016 arXiv   pre-print
We tackle the problem of estimating optical flow from a monocular camera in the context of autonomous driving. We build on the observation that the scene is typically composed of a static background, as well as a relatively small number of traffic participants which move rigidly in 3D. We propose to estimate the traffic participants using instance-level segmentation. For each traffic participant, we use the epipolar constraints that govern each independent motion for faster and more accurate
more » ... imation. Our second contribution is a new convolutional net that learns to perform flow matching, and is able to estimate the uncertainty of its matches. This is a core element of our flow estimation pipeline. We demonstrate the effectiveness of our approach in the challenging KITTI 2015 flow benchmark, and show that our approach outperforms published approaches by a large margin.
arXiv:1604.01827v2 fatcat:l6ikg4y2gncchpjyl5zlz4ma6u