The Community for Technology Leaders
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Las Vegas, NV, United States
June 27, 2016 to June 30, 2016
ISSN: 1063-6919
ISBN: 978-1-4673-8851-1
pp: 4058-4066
ABSTRACT
We present an approach to dense depth estimation from a single monocular camera that is moving through a dynamic scene. The approach produces a dense depth map from two consecutive frames. Moving objects are reconstructed along with the surrounding environment. We provide a novel motion segmentation algorithm that segments the optical flow field into a set of motion models, each with its own epipolar geometry. We then show that the scene can be reconstructed based on these motion models by optimizing a convex program. The optimization jointly reasons about the scales of different objects and assembles the scene in a common coordinate frame, determined up to a global scale. Experimental results demonstrate that the presented approach outperforms prior methods for monocular depth estimation in dynamic scenes.
INDEX TERMS
Motion segmentation, Cameras, Computer vision, Estimation, Optical imaging, Image reconstruction, Vehicle dynamics
CITATION

R. Ranftl, V. Vineet, Q. Chen and V. Koltun, "Dense Monocular Depth Estimation in Complex Dynamic Scenes," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, United States, 2016, pp. 4058-4066.
doi:10.1109/CVPR.2016.440
95 ms
(Ver 3.3 (11022016))