Abstract and Applied Analysis

Analysis of Feature Fusion Based on HIK SVM and Its Application for Pedestrian Detection

Song-Zhi Su and Shu-Yuan Chen

Full-text: Open access

Abstract

This work presents the fusion of integral channel features to improve the effectiveness and efficiency of pedestrian detection. The proposed method combines the histogram of oriented gradient (HOG) and local binary pattern (LBP) features by a concatenated fusion method. Although neural network (NN) is an efficient tool for classification, the time complexity is heavy. Hence, we choose support vector machine (SVM) with the histogram intersection kernel (HIK) as a classifier. On the other hand, although many datasets have been collected for pedestrian detection, few are designed to detect pedestrians in low-resolution visual images and at night time. This work collects two new pedestrian datasets—one for low-resolution visual images and one for near-infrared images—to evaluate detection performance on various image types and at different times. The proposed fusion method uses only images from the INRIA dataset for training but works on the two newly collected datasets, thereby avoiding the training overhead for cross-datasets. The experimental results verify that the proposed method has high detection accuracies even in the variations of image types and time slots.

Article information

Source
Abstr. Appl. Anal., Volume 2013, Special Issue (2013), Article ID 436062, 11 pages.

Dates
First available in Project Euclid: 26 February 2014

Permanent link to this document
https://projecteuclid.org/euclid.aaa/1393450356

Digital Object Identifier
doi:10.1155/2013/436062

Citation

Su, Song-Zhi; Chen, Shu-Yuan. Analysis of Feature Fusion Based on HIK SVM and Its Application for Pedestrian Detection. Abstr. Appl. Anal. 2013, Special Issue (2013), Article ID 436062, 11 pages. doi:10.1155/2013/436062. https://projecteuclid.org/euclid.aaa/1393450356


Export citation