An improved vibe algorithm to eliminate ghost quickly

Pu Zhao; Yi Wu

doi:10.1117/12.2681010

8 June 2023 An improved vibe algorithm to eliminate ghost quickly

Pu Zhao, Yi Wu

Proceedings Volume 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023); 1270747 (2023) https://doi.org/10.1117/12.2681010
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 2023, Changsha, China

Abstract

In order to solve the problem of slowly ghosts eliminate, slowly merge stationary moving targets into the background and noise in the detection of moving target. This paper presents an improved vibe algorithm. Firstly, fuse pixel average and a threshold selection method from gray-level histograms to calculate the optimal threshold, images are processed by optimal threshold, and then the obtained foreground point is secondly judged; Secondly, the edge pixels of the marked stationary targets are processed by frame difference of binarized images. And the background model samples are updated by dynamic parameters; Finally, the result is processed morphological filtering. Experimental results show that the improved algorithm can eliminate the ghost more effectively, merge stationary moving targets into the background more quickly and detect foreground target more accurately.

Citation Download Citation

Pu Zhao and Yi Wu "An improved vibe algorithm to eliminate ghost quickly", Proc. SPIE 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 1270747 (8 June 2023); https://doi.org/10.1117/12.2681010

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available