Pedestrian Detection Based on Sparse and Low-Rank Matrix Decomposition

Abstract

This article puts forward a novel system for pedestrian detection tasks, which proposing a model with sparse and low-rank matrix decomposition, jointly alternating direction method to solve the convex relaxation problem. We present an efficient pedestrian detection system using mixing features with sparse and low-rank matrix decomposition to combine into a Kernel classifier. Results presented on our data set show competitive accuracy and robust performance of our system outperforms current state-of-the-art work.

DOI : http://dx.doi.org/10.11591/telkomnika.v12i2.3859