Zagazig University Digital Repository
Home
Thesis & Publications
All Contents
Publications
Thesis
Graduation Projects
Research Area
Research Area Reports
Search by Research Area
Universities Thesis
ACADEMIC Links
ACADEMIC RESEARCH
Zagazig University Authors
Africa Research Statistics
Google Scholar
Research Gate
Researcher ID
CrossRef
An Efficient Intensity Correction Algorithm for High Definition Video Surveillance Applications
Faculty
Not Specified
Year:
2011
Type of Publication:
Article
Pages:
1622-1630
Authors:
Sayed, Mohammed S, Delva, Justin G. R
DOI:
10.1109/TCSVT.2011.2130290
Journal:
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Volume:
21
Research Area:
Engineering
ISSN
ISI:000296471100007
Keywords :
High definition video surveillance, intensity correction, video analysis on resource-limited systems, video analytics
Abstract:
The video surveillance market is increasingly moving toward cheaper, efficient, portable, and high resolution systems. A typical video surveillance system consists of several cameras, which issue warnings or initiate smart reactions according to the analysis results of the captured video data. Many algorithms in video surveillance systems assume fixed lighting conditions for the monitored area. The performance of these algorithms is severely affected by the illumination changes of the monitored area. This paper presents an efficient intensity correction algorithm for high definition video surveillance applications. The new algorithm corrects both the global and the local intensity changes. It uses an apparent gain factor to correct the global intensity changes. In addition it corrects the local intensity changes using the local intensity mean and standard deviation. The proposed algorithm shows a promising performance when compared with other intensity correction algorithms. It has a low computational cost that makes it a suitable choice for real-time hardware implementation. This paper also presents a hardware implementation of the proposed algorithm using Xilinx Spartan3A digital signal processor (DSP) XC3SD3400A device. The targeted resolution is 1920x1080 at 30 f/s. The hardware prototype utilizes 17\% of the slices, 21\% of the block random access memories, and 24\% of the DSP48As available in Spartan3A DSP XC3SD3400A device.
Online
PDF
جامعة المنصورة
جامعة الاسكندرية
جامعة القاهرة
جامعة سوهاج
جامعة الفيوم
جامعة بنها
جامعة دمياط
جامعة بورسعيد
جامعة حلوان
جامعة السويس
شراقوة
جامعة المنيا
جامعة دمنهور
جامعة المنوفية
جامعة أسوان
جامعة جنوب الوادى
جامعة قناة السويس
جامعة عين شمس
جامعة أسيوط
جامعة كفر الشيخ
جامعة السادات
جامعة طنطا
جامعة بنى سويف