Real-Time Video Streaming Application of Improved Sobel Algorithm Based on FPGA.

Saved in:

Bibliographic Details
Title:	Real-Time Video Streaming Application of Improved Sobel Algorithm Based on FPGA.
Authors:	Xu, Shichao¹ 1051754173@qq.com, Ning, Keqing² ningkq@ncut.edu.cn, Guo, Wei³ xiaoshenghameng@163.com, Wei, Bowen⁴ wbw060323@163.com, Ren, Pengyu⁵ 1179825666@qq.com
Source:	IAENG International Journal of Computer Science. Jun2026, Vol. 53 Issue 6, p2425-2434. 10p.
Subjects:	Edge detection (Image processing), Field programmable gate arrays, Image processing, Streaming media, Signal denoising
Abstract:	Real-time edge detection in video streams remains challenging due to noise interference, limited gradient directions of traditional Sobel operators, and the difficulty of selecting an appropriate global threshold. To address these issues, this paper presents a real-time edge detection architecture that integrates an adaptive median filter with an eight-direction Sobel operator on an FPGA platform. The adaptive median filter dynamically switches between 3×3 and 5×5 windows to suppress impulse noise while preserving image details. Its output is further incorporated into the adaptive threshold computation for the Sobel operator, removing the need for manual parameter adjustment. Additionally, the extension from two to eight gradient directions enhances edge continuity and robustness in complex scenes. The proposed system is implemented on an Altera Cyclone IV FPGA using a fully pipelined, modular architecture. Experimental results from MATLAB simulations and on-board verification demonstrate that the proposed design achieves clearer edges, fewer false detections, and better continuity than the traditional Sobel operator, while maintaining real-time performance for video applications. [ABSTRACT FROM AUTHOR]
	Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Real-time edge detection in video streams remains challenging due to noise interference, limited gradient directions of traditional Sobel operators, and the difficulty of selecting an appropriate global threshold. To address these issues, this paper presents a real-time edge detection architecture that integrates an adaptive median filter with an eight-direction Sobel operator on an FPGA platform. The adaptive median filter dynamically switches between 3×3 and 5×5 windows to suppress impulse noise while preserving image details. Its output is further incorporated into the adaptive threshold computation for the Sobel operator, removing the need for manual parameter adjustment. Additionally, the extension from two to eight gradient directions enhances edge continuity and robustness in complex scenes. The proposed system is implemented on an Altera Cyclone IV FPGA using a fully pipelined, modular architecture. Experimental results from MATLAB simulations and on-board verification demonstrate that the proposed design achieves clearer edges, fewer false detections, and better continuity than the traditional Sobel operator, while maintaining real-time performance for video applications. [ABSTRACT FROM AUTHOR]
ISSN:	1819656X