Pedestrian Detection Via Classification on Riemannian Manifolds
| Citation: | * Tuzel, O.; Porikli, F.; Meer, P., "Pedestrian Detection via Classification on Riemannian Manifolds", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), ISSN: 0162-8828, Vol. 30, Issue 10, pp. 1713-1727, October 2008 (IEEE Xplore) |
| MERL Report: | TR2008-037 |
| MERL Contacts: | Oncel Tuzel, Fatih Porikli |
Black dots are the modes generated by mean shift smoothing, and the ellipses are average detection window sizes. There are extremely few false positives and negatives.
We present a new algorithm to detect pedestrians in still images utilizing covariance matrices as object descriptors. Since the descriptors do not form a vector space, well-known machine learning techniques are not well suited to learn the classifiers. The space of d-dimensional nonsingular covariance matrices can be represented as a connected Riemannian manifold. The main contribution of the paper is a novel approach for classifying points lying on a connected Riemannian manifold using the geometry of the space. The algorithm is tested on the INRIA and DaimlerChrysler pedestrian data sets where superior detection rates are observed over the previous approaches.
 | Read the full technical report (PDF: 1.1 MB) |