Sciweavers

20 search results - page 2 / 4
» Pedestrian detection using boosted features over many frames
Sort
View
NIPS
2001
13 years 7 months ago
Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade
This paper develops a new approach for extremely fast detection in domains where the distribution of positive and negative examples is highly skewed (e.g. face detection or databa...
Paul A. Viola, Michael J. Jones
ICPR
2010
IEEE
13 years 3 months ago
Improving Classification Accuracy by Comparing Local Features through Canonical Correlations
Classifying images using features extracted from densely sampled local patches has enjoyed significant success in many detection and recognition tasks. It is also well known that ...
Mert Dikmen, Thomas S. Huang
BMVC
2010
13 years 3 months ago
The Fastest Pedestrian Detector in the West
We demonstrate a multiscale pedestrian detector operating in near real time (5 fps on 640x480 images) with state-of-the-art detection performance. The computational bottleneck of ...
Piotr Dollár, Serge Belongie, Pietro Perona
ICPR
2010
IEEE
13 years 5 months ago
Spatiotemporal-Boosted DCT Features for Head and Face Gesture Analysis
Automatic analysis of head gestures and facial expressions is a challenging research area and it has significant applications in humancomputer interfaces. In this study, facial la...
Hatice Çinar Akakin, Bülent Sankur
PAMI
2008
220views more  PAMI 2008»
13 years 5 months ago
Pedestrian Detection via Classification on Riemannian Manifolds
Detecting different categories of objects in image and video content is one of the fundamental tasks in computer vision research. The success of many applications such as visual s...
Oncel Tuzel, Fatih Porikli, Peter Meer