Moving Object and face detection using FPGA
Author(s):
Hrishikesh R, Hemanth P, Gajaraj B Patil, Mahesh Kumar M, Anuradha V Rao
Keywords:
HAAR, LL band, VHDL, adaptive threshold, system generator
Abstract
Surveillance plays an important role in the present digital world. The advent of new technologies is making the computational process much faster than the existing ones. FPGA implementation of the moving object and face detection enhances the surveillance system by providing the results using the concept of adaptive threshold. The concept of adaptive threshold is used, so that the input comparison is done many times to produce an efficient and clear output. FPGA works at a greater speed (high clock speed) compared to other technologies for implementation. The input images are passed through the Gaussian filter. The HAAR Transform is applied on Gaussian filter’s outputs and considered only LL band for further processing to detect object/face. The modified background subtraction algorithm is applied on LL bands of input images. The adaptive threshold is calculated using LL-band of reference image and object is detected through modified background subtraction algorithm. The detected object is again passed through the second Gaussian filter to get final good quality object. The face detection can be performed using an additional matching unit along with object detection unit. The reference image is replaced by face database images in the face detection. Moving object and face detection system is designed using Xilinx Spartan 6 LX45 FPGA kit. Using FPGA for object and face detection increases the speed of computation and makes the system more efficient. It has applications in various fields such as traffic systems, hospitals, banks
Article Details
Unique Paper ID: 152556

Publication Volume & Issue: Volume 8, Issue 3

Page(s): 746 - 753
Article Preview & Download


Share This Article

Conference Alert

ICM - STEP

International conference on Management, Science, Technology, Engineering, Pharmact and Humanities.

Latest Publication

Go To Issue



Call For Paper

Volume 8 Issue 4

Last Date 25 September 2021

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies

Important Links

Browse Rsearch papers