Real-time pedestrian detection in urban scenarios

Author

Varga, Rastislav ; Vesa, Andreea Valeria ; Pangyu Jeong ; Nedevschi, Sergiu

Author_Institution

Tech. Univ. of Cluj Napoca, Cluj-Napoca, Romania

fYear

2014

fDate

4-6 Sept. 2014

Firstpage

113

Lastpage

118

Abstract

A real-time pedestrian detection system is presented that runs at 24 fps on standard VGA resolution input images (640×480px) using only CPU processing. The detection algorithm uses a variable sized sliding window and intelligent simplifications such as a sparse scale space and fast candidate selection to obtain the desired speed. Details are provided about the initial version of the system ported on a mobile device. We also present a new labeled pedestrian dataset that was captured from a moving car that is suitable for training and testing pedestrian detection methods in urban scenarios.

Keywords

image resolution; mobile computing; object detection; pedestrians; CPU processing; detection algorithm; fast candidate selection; intelligent simplification; labeled pedestrian dataset; mobile device; moving car; real-time pedestrian detection system; sparse scale space; standard VGA resolution input images; urban scenario; variable sized sliding window; Androids; Detection algorithms; Feature extraction; Histograms; Humanoid robots; Mobile handsets; Training; Pedestrian detection; mobile devices; object recognition; region of interest selection;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computer Communication and Processing (ICCP), 2014 IEEE International Conference on

Conference_Location

Cluj Napoca

Print_ISBN

978-1-4799-6568-7

Type

conf

DOI

10.1109/ICCP.2014.6936962

Filename

6936962