Skip to content
Research Article Open access CC BY 4.0

Moving Object Detection Algorithm Based on Gaussian Mixture Model and HSV Space

Xuegang Hu, Cheng He

Current Journal of Applied Science and Technology · pp. 1–8 · Published 5 Mar 2016

10.9734/BJAST/2016/24249

Abstract

Aiming at the traditional Gaussian mixture model has poor adaptability to the complex scenes, we proposes an improved moving object detection algorithm based on Gaussian mixture model and HSV space. The motion region is first extracted by the improved three-frame difference method. With the matching results, region segmentation of current frame is realized. Then different regions adopt different update strategy that improves the ability to reflect the illumination and scenes change. Next, utilizing characteristics of HSV color space and image first-order gradient achieve shadow detection. It effectively reduces interference of shadows, especially the pixels of foreground which has similar brightness properties with background. Experimental results show that the algorithm has good robustness and real-time performance.

Gaussian mixture model moving object detection three-frame difference method HSV space shadow detection

References (17)

  1. 1 Adaptive background mixture models for real-time tracking [DOI]
  2. 2 Computer vision and pattern recognition [DOI]
  3. 3 Improved adaptive Gaussian mixture model for background subtraction [DOI]
  4. 4 Improved Adaptive Gaussian Mixture Model for Background Subtraction
  5. 5 Dual U-Net with Resnet Encoder for Segmentation of Medical Images [DOI]
  6. 6 A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications [DOI]
  7. 7 Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey [DOI]
  8. 8 Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey [DOI]
  9. 9 Shadow detection for moving objects based on texture analysis [DOI]
  10. 10 Moving Cast Shadow Detection from a Gaussian Mixture Shadow Model [DOI]
  11. 11 Evaluation report of integrated background modeling based on spatio-temporal features [DOI]
  12. 12 Real-time robust background subtraction under rapidly changing illumination conditions [DOI]
  13. 13 Detecting people carrying objects based on an optical flow motion model [DOI]
  14. 14 Shadow Suppression using RGB and HSV Color Space in Moving Object Detection [DOI]
  15. 15 Adaptive Background Modeling Based on Mixture Gaussian Model and Frame Subtraction
  16. 16 An improved Gaussian mixture background model with real-time adjustment of learning rate [DOI]
  17. 17 Moving Objects Detection of Adaptive Gaussian Mixture Models on HSV

Cited by 12

HSV Color Space Based Automated Chemical Titrator

Zhang Bingjie, Song Qing, Xu Lujian · 2024 6th International Conference on Industrial Artificial Intelligence (IAI) · 2024

People Detection and Finding Attractive Areas by the use of Movement Detection Analysis and Deep Learning Approach

Ebrahim Najafi Kajabad, Sergey V. Ivanov · Procedia Computer Science · 2019

A Study on Flame and Smoke Detection Algorithm Using Convolutional Neural Network Based on Deep Learning

Jinkyu Ryu, Dongkurl Kwak · Journal of the Korean Society of Hazard Mitigation · 2020

Road and Vehicles Detection System Using HSV Color Space for Autonomous Vehicle

Bhakti Yudho Suprapto, Aulia Ghaida, Hera Hikmarika · Jurnal Ilmiah Teknik Elektro Komputer dan Informatika · 2020

Multiple Vehicle Tracking using Adaptive Gaussian Mixture Model and Kalman Filter

Fandy Setyo Utomo · American Journal of Applied Sciences · 2016

An Improved Gaussian Mixture Model Motion Target Detection Algorithm for Complex Backgrounds

Weibo Yu, Shuxian Zhao, Aiguo Zhao · 2024 39th Youth Academic Annual Conference of Chinese Association of Automation (YAC) · 2024

Showing 6 of 12 known citations — external sources report more than can currently be individually listed.

Related research

Article metrics

Real usage data collected on this platform.

28

Page views

0

PDF downloads

4

Outbound clicks

12

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.