publication . Other literature type . Conference object . 2010

Cascade object detection with deformable part models

Pedro F. Felzenszwalb; Ross B. Girshick; David McAllester;
  • Published: 01 Jun 2010
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We describe a general method for building cascade classifiers from part-based deformable models such as pictorial structures. We focus primarily on the case of star-structured models and show how a simple algorithm based on partial hypothesis pruning can speed up object detection by more than one order of magnitude without sacrificing detection accuracy. In our algorithm, partial hypotheses are pruned with a sequence of thresholds. In analogy to probably approximately correct (PAC) learning, we introduce the notion of probably approximately admissible (PAA) thresholds. Such thresholds provide theoretical guarantees on the performance of the cascade method and ca...
Subjects
free text keywords: Probability distribution, Dynamic programming, SIMPLE algorithm, Pattern recognition, Cascade, Computer vision, Recursion, Probably approximately correct learning, Image segmentation, Computer science, Artificial intelligence, business.industry, business, Object detection
Related Organizations
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue