Semantic Motion Segmentation using Dense CRF Formulation

N.Dinesh Reddy1   Prateek Singhal1   K Madhava Krishna1  
Indian Conference on Computer Vision, Graphics and Image Processing(ICVGIP) 2014, Banglore, India

Download Video (MP4,720p, 3 MB)

Abstract

While the literature has been fairly dense in the areas of scene understanding and semantic labeling there have been few works that make use of motion cues to embellish semantic performance and vice versa. In this paper, we address the problem of semantic motion segmentation, and show how semantic and motion priors augments performance. We propose an algorithm that jointly infers the semantic class and motion labels of an object. Integrating semantic, geometric and optical ow based constraints into a dense CRF model we infer both the object class as well as motion class, for each pixel. We found improvement in performance using a fully connected CRF as compared to a standard clique-based CRFs. For inference, we use a Mean Field approximation based algorithm. Our method outperforms recently proposed motion detection algorithms and also improves the semantic labeling compared to the state-of-the-art Automatic Labeling Environment algorithm on the challenging KITTI dataset especially for object classes such as pedestrians and cars that are critical to an outdoor robotic navigation scenario

Downloads


Citation

BibTeX, 1 KB

@inproceedings{reddy2014semantic,
  title={Semantic Motion Segmentation Using Dense CRF Formulation},
  author={Reddy, N Dinesh and Singhal, Prateek and Krishna, K Madhava},
  booktitle={Proceedings of the 2014 Indian Conference on Computer Vision Graphics and Image Processing},
  pages={56},
  year={2014},
  organization={ACM}
}
	

Contact

N.Dinesh Reddy
dineshreddy.n@research.iiit.ac.in

This page is Zotero translator friendly. Page last updated 03-Jun-2015. .