Pedestrian Detection Based on Deep Neural Network in Video Surveillance

Abstract

Pedestrian detection is an essential and challenging problem in machine vision and video surveillance signal processing. To handle the high cost of training-specific discriminative classifier for pedestrian detection, we focus on the learning of suitable features for pedestrian detection representation. A deep neural network is presented in this paper to resolve the above issue. Our pedestrian detection method has several appealing properties. First, the learning of features is much more efficient under the configuration of the proposed framework due to the reduction of training classifier. Second, a K-Nearest Neighbor (KNN) method is adopted to solve the comparison between the regions of interest and the templates. Third, due to the less dependency of the classifier, the performance across different datasets overcomes most traditional ones. Finally, we perform extensive comparison across different public datasets and compared with corresponding benchmarks.