Abstract

Cascading techniques are commonly used to speed-up the scan of an image for ob ject detection. However, cascades of detectors are slow to train due 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 han- dle these problems, we propose a new way to scan an image, where we couple a recursive coarse-to-fine refinement together with spatial con- straints of the ob ject 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 neighbor- hood is defined as a scanning region that only one ob ject 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 HOG 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 mul- tiple resolutions approach our method has slightly better performance in speed and Average-Precision. Furthermore, in contrast to cascading ap- proach, the speed-up is independent of image conditions, the number of detected ob jects and clutter.