Because better detections are still possible: Multi-aspect Object Detection with Boosted Hough Forest

Abstract

In the last few years, many adaptations of the Hough Forest (HF) [2] approach for object detection have been proposed. In this work, we proceed to deconstruct the HF learning model to investigate whether a considerable better performance can be obtained detecting multi-aspect objects. Inspired by [4], we introduce the Boosted Hough Forest (BHF). Essentially… (More)
DOI: 10.5244/C.29.63

Topics

  • Presentations referencing similar topics