An Extreme Learning Machine-based pedestrian detection method

Author

Kai Yang ; Du, Eliza Y. ; Delp, Edward J. ; Pingge Jiang ; Feng Jiang ; Yaobin Chen ; Sherony, Rini ; Takahashi, Hiroki

Author_Institution

Dept. of Electr. & Comput. Eng., Indiana Univ.-Purdue Univ. Indianapolis, Indianapolis, IN, USA

fYear

2013

fDate

23-26 June 2013

Firstpage

1404

Lastpage

1409

Abstract

Pedestrian detection is a challenging task due to the high variance of pedestrians and fast changing background, especially for a single in-car camera system. Traditional HOG+SVM methods have two challenges: (1) false positives and (2) processing speed. In this paper, a new pedestrian detection method using multimodal HOG for pedestrian feature extraction and kernel based Extreme Learning Machine (ELM) for classification is presented. The experimental results using our naturalistic driving dataset show that the proposed method outperforms the traditional HOG+SVM method in both recognition accuracy and processing speed.

Keywords

image classification; learning (artificial intelligence); object detection; pedestrians; traffic engineering computing; ELM; HOG+SVM methods; extreme learning machine-based pedestrian detection method; kernel based extreme learning machine; pedestrian feature extraction; single in-car camera system; Detectors; Histograms; Image edge detection; Kernel; Shape; Support vector machines; Training; Extreme Learning Machine (ELM); Multimodal HOG; Naturalistic Driving; Pedestrian Detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Vehicles Symposium (IV), 2013 IEEE

Conference_Location

Gold Coast, QLD

ISSN

1931-0587

Print_ISBN

978-1-4673-2754-1

Type

conf

DOI

10.1109/IVS.2013.6629663

Filename

6629663