N-best maximal decoders for part models
Authors:
- 1 November 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 2627-2634
Abstract
We describe a method for generating N-best configurations from part-based models, ensuring that they do not overlap according to some user-provided definition of overlap. We extend previous N-best algorithms from the speech community to incorporate non-maximal suppression cues, such that pixel-shifted copies of a single configuration are not returned. We use approximate algorithms that perform nearly identical to their exact counterparts, but are orders of magnitude faster. Our approach outperforms standard methods for generating multiple object configurations in an image. We use our method to generate multiple pose hypotheses for the problem of human pose estimation from video sequences. We present quantitative results that demonstrate that our framework significantly improves the accuracy of a state-of-the-art pose estimation algorithm.Keywords
This publication has 21 references indexed in Scilit:
- On Detection of Multiple Object Instances Using Hough TransformsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Discriminative models for multi-class object layout2009
- People-tracking-by-detection and people-detection-by-tracking2008
- Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcasts2008
- Tracking People by Learning Their AppearanceIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Pictorial Structures for Object RecognitionInternational Journal of Computer Vision, 2005
- Betterk-best parsing2005
- Real-time object detection for "smart" vehicles1999
- An efficient algorithm for finding the M most probable configurationsin probabilistic expert systemsStatistics and Computing, 1998