Embedded system for real-time human motion detection

Author

Mayya, Mohammad ; Zarka, Nizar ; Alkadi, Mhd Soubhi

Author_Institution

Higher Inst. for Appl. Sci. & Technol., Syria

fYear

2010

fDate

7-10 July 2010

Firstpage

523

Lastpage

528

Abstract

This paper describes an embedded system for real-time human motion detection using a fixed camera. A modified version of the Codebook algorithm is developed to detect moving objects. This algorithm provides fast background modelling and subtraction with small storage memory requirements. Then, the system detects humans using a simplified Skeletonization algorithm, which uses the individual human shape and does not need a model comparison. Functional and timing simulations are applied by using MATLAB and Visual Studio on PC. Finally, the system is installed on ALTERA Cyclone™ II DSP development board and implemented using the Nios II processor and some hardware accelerators.

Keywords

cameras; embedded systems; mathematics computing; motion estimation; object detection; shape recognition; ALTERA Cyclone™ II DSP development board; MATLAB; Nios II processor; Visual Studio; codebook algorithm; embedded system; fast background modelling; fast background subtraction; fixed camera; hardware accelerator; moving object detection; real time human motion detection; simplified skeletonization algorithm; storage memory requirement; Adaptation model; Field programmable gate arrays; Humans; Mathematical model; Pixel; Random access memory; System-on-a-chip; Codebook; FPGAs; Nios II processor; Skeletonization; background subtraction; human motion; real-time system;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing Theory Tools and Applications (IPTA), 2010 2nd International Conference on

Conference_Location

Paris

ISSN

2154-5111

Print_ISBN

978-1-4244-7247-5

Type

conf

DOI

10.1109/IPTA.2010.5586727

Filename

5586727