Recursive Coarse-to-Fine Localization for Fast Object Detection

Marco Pedersoli*, Jordi Gonzalez, Andrew D. Bagdanov, Juan J. Villanueva

*Corresponding author for this work

Research output: Contribution to journalArticleResearchpeer-review

22 Citations (Scopus)

Abstract

Cascading techniques are commonly used to speed-up the scan of an image for object detection. However, cascades of detectors are slow to train clue to the high number of detectors and corresponding thresholds to learn. Furthermore, they do not use any prior knowledge about the scene structure to decide where to focus the search. To handle these problems, we propose a new way to scan an image, where we couple a recursive coarse-to-fine refinement together with spatial constraints of the object location. For doing that we split an image into a set of uniformly distributed neighborhood regions, and for each of these we apply a local greedy search over feature resolutions. The neighborhood is defined as a scanning region that only one object can occupy. Therefore the best hypothesis is obtained as the location with maximum score and no thresholds are needed. We present an implementation of our method using a pyramid of BOG features and we evaluate it on two standard databases, VOC2007 and INRIA dataset. Results show that the Recursive Coarse-to-Fine Localization (RCFL) achieves a 12x speed-up compared to standard sliding windows. Compared with a cascade of multiple resolutions approach our method has slightly better performance in speed and Average-Precision. Furthermore, in contrast to cascading approach, the speed-up is independent of image conditions, the number of detected objects and clutter.

Original languageEnglish
Pages (from-to)280-+
Number of pages2
JournalLecture Notes in Computer Science
VolumeEECV (GGS Rating A+, Class 1)
Publication statusPublished - 2010

Keywords

  • Object Detection
  • Machine Learning
  • SVM

Fingerprint

Dive into the research topics of 'Recursive Coarse-to-Fine Localization for Fast Object Detection'. Together they form a unique fingerprint.

Cite this