A Novel Pedestrian Detector on Low-Resolution Images: Gradient LBP Using Patterns of Oriented Edges

Abstract

SUMMARYThis paper introduces a simple algorithm for pedestrian detection on low resolution images. The main objective is to create a successful means for real-time pedestrian detection. While the framework of the system consists of edge orientations combined with the local binary patterns (LBP) feature extractor, a novel way of selecting the threshold is introduced. Using the mean-variance of the background examples this threshold improves significantly the detection rate as well as the processing time. Furthermore, it makes the system robust to uniformly cluttered backgrounds, noise and light variations. The test data is the INRIA pedestrian dataset and for the classification, a support vector machine with a radial basis function (RBF) kernel is used. The system performs at state-of-the-art detection rates while being intuitive as well as very fast which leaves sufficient processing time for further operations such as tracking and danger estimation.

Similarity Estimation for Large-Scale Human Action Video Data on Spark

“…Discriminative robust local binary pattern and discriminative robust ternary pattern in [26] are proposed for tackling the issue of differentiating a bright object from a dark background. Boudissa et al [27] proposed an algorithm and a framework for real-time pedestrian detection regarding to low-resolution images, and they introduced a novel threshold selection way using the mean-variance of the background samples. However, their proposed method can only tackle partially the problems of edge-based methods.…”