NED University Journal of Research
ISSN 2304-716X
E-ISSN 2706-5758




PROPOSED REAL-TIME FEATURE EXTRACTION ON FIELD PROGRAMMABLE GATE ARRAY FOR HUMAN DETECTION

Author(s): Amjad Mahmood1, Muhammad Obaid Ullah2, Muhammad Haroon Yousaf3
1 Research Scholar, Department of Electrical Engineering, University of Engineering and Technology, Taxila, Pakistan, Ph. +92(301)5744904, Email: engineer_amjad@yahoo.com.

2 Assistant Professor, Department of Electronics Engineering, University of Engineering and Technology, Taxila, Pakistan, Ph. +92(51)9047726, Fax: +92(51)9047420, Email: obaid.ullah@uettaxila.edu.pk.

3 Associate Professor, Department of Computer Engineering, University of Engineering and Technology, Taxila, Pakistan, Ph. +92(51)9047574, Fax: +92(51)9047420, Email: haroon.yousaf@uettaxila.edu.pk.

Volume: XIV

No. 2

Pages: 47 - 59

Date: March 2017

Abstract:
Hardware based human detection plays a key role in several applications such as smart vehicles, robotics and surveillance. In this paper, an efficient scheme for combined histogram of oriented gradients (HOG) and local binary pattern (LBP) feature extraction on field programmable gate array (FPGA) is presented. HOG and LBP computations for each pixel value of 3 × 3 pixels, 8 × 8 pixels and 16 × 16 pixels regions were performed for the input images. HOG-LBP feature extraction was implemented using both the shape and texture information for more robust human detection in the presence of partial occlusion and background clutter. The proposed scheme uses 793 lookup tables (LUTs) on Virtex-5 FPGA to achieve 82.118 MHz clock frequency. The scheme can be employed for real-time human detection with low power consumption, low cost and real-time performance.

Full Paper | Close Window      X |