Citation

Paisitkriangkrai S, Shen C, Zhang J. IEEE Trans. Circ. Syst. Video Tech. 2008; 18(8): 1140-1151.

Copyright

(Copyright © 2008, IEEE Circuits and Systems Society)

DOI

10.1109/TCSVT.2008.928213

PMID

unavailable

Abstract

Efficiently and accurately detecting pedestrians plays a very important role in many computer vision applications such as video surveillance and smart cars. In order to find the right feature for this task, we first present a comprehensive experimental study on pedestrian detection using state-of-the- art locally extracted features (local receptive fields, histogram of oriented gradients and region covariance). Building upon the findings of our experiments, we propose a new, simpler pedestrian detector using the covariance features. Unlike the work in (1), where the feature selection and weak classifier training are performed on the Riemannian manifold, we select features and train weak classifiers in the Euclidean space for faster computation. To this end, AdaBoost with weighted Fisher linear discriminant analysis based weak classifiers are designed. A cascaded classifier structure is constructed for effi- ciency in the detection phase. Experiments on different datasets prove that the new pedestrian detector is not only comparable to the state-of-the-art pedestrian detectors but it also performs at a faster speed. To further accelerate the detection, we adopt a faster strategy--multiple layer boosting with heterogeneous features-- to exploit the efficiency of the Haar feature and the discriminative power of the covariance feature. Experiments show that by combining the Haar and covariance features, we speed up the original covariance feature detector (1) by up to an order of magnitude in detection time with a slight drop in detection performance. detection in still images is one of the most difficult examples of generic object detection. The challenges are due to a wide range of poses that human can adopt, large variations in clothing, as well as cluttered backgrounds and environmental conditions. Pattern classification approaches have been shown to achieve successful results in many areas of object detec- tions. These approaches can be decomposed into two key components: feature extraction and classifier construction. In feature extraction, dominant features are extracted from a large number of training samples. These features are then used to train a classifier. During testing, the trained classifier scanned the entire input image to look for particular object patterns. This general approach has shown to work very well in detection of many different objects, e.g., face (2) and car number plate (9), etc.