Moving object detection: a new method combining background subtraction, fuzzy entropy thresholding and differential evolution optimization

• Autorzy: Boufares Oussama , Boussif Mohamed , Saadaoui Wajdi , Miraoui Imed

Identyfikatory

DOI

10.2478/ama-2025-0013

• Języki publikacji: EN

Abstrakty

EN

Detecting moving objects in videos is an evolving area of research, with important implications in many computer vision applications. In this paper, we propose a new detection approach by combining background subtraction and multi-level image thresholding based on fuzzy entropy, powered by the differential evolution (DE) algorithm. The first step of our method is background subtraction, aiming to isolate moving objects by eliminating the static background. However, this approach can be sensitive to lighting variations and background changes, thus limiting its accuracy. To overcome these limitations, we introduce multi-level image thresholding based on fuzzy entropy. This method exploits the intrinsic variability of moving objects rather than simply differentiating against the background. By adjusting thresholds locally, our approach better adapts to changing environmental conditions. The key element of our proposal lies in the optimization of the fuzzy entropy threshold parameters using the differential evolution algorithm. We chose DE for its robustness and efficiency in handling continuous optimization problems, which makes it well-suited for complex tasks like multi-level image threshold-ing. By iteratively adjusting the thresholds, we maximize the detection of moving objects while minimizing false positives, thereby improving the robustness and accuracy of the method. Our experiments on test video sequences demonstrate the effectiveness of our approach, highlighting a significant improvement in moving object detection compared to traditional methods. This promising methodology paves the way for future advances in moving object detection, with potential applications in surveillance, robotics, and computer vision in general.

Słowa kluczowe

EN

detecting moving objects; fuzzy entropy; differential evolution; object segmentation

• Wydawca: Oficyna Wydawnicza Politechniki Białostockiej
• Czasopismo: Acta Mechanica et Automatica
• Rocznik: 2025
• Tom: Vol. 19, no. 1
• Strony: 106--116
• Opis fizyczny: Bibliogr. 33 poz., rys., tab., wykr.

Twórcy

autor

Boufares Oussama

• Faculty of sciences of Tunis, Department physics, University of Tunis El Manar, El Manar 2092

• https://orcid.org/0000-0003-2488-0666

autor

Boussif Mohamed

• Faculty of sciences of Tunis, Department physics, University of Tunis El Manar, El Manar 2092

• https://orcid.org/0000-0003-3198-7605

autor

Saadaoui Wajdi

• Faculty of sciences of Gafsa, Department electronics, University of Gafsa, Zarrok 2112

• https://orcid.org/0000-0001-8977-9652

autor

Miraoui Imed

• Faculty of sciences of Gafsa, Department electronics, University of Gafsa, Zarrok 2112

• https://orcid.org/0000-0001-5003-6683

Bibliografia

• 1. Tsai DM, Lai SC. Independent component analysis-based back-ground subtraction for indoor surveillance. IEEE Trans Image Pro-cess. 2009;18(1):158-67. Available from: https://doi.org/10.1109/tip.2008.2007558
• 2. Stauffer C, Grimson WEL. Adaptive background mixture models for real-time tracking. Proc IEEE Comput Vis Pattern Recognit. 2003;246–52. Available from: https://doi.org/10.1109/cvpr.1999.784637
• 3. Xing-ju W, Yu-wei H, Ran-hang O. Method, model and application for the conversion from vague sets to fuzzy sets. Proc Int Conf Artif Intell Comput Intell AICI. 2009;510–3. Available from: https://doi.org/10.1109/aici.2009.397
• 4. Storn R, Price K. Differential evolution—a simple and efficient heuris-tic for global optimization over continuous spaces. J Glob Optim. 1997;11:341–59. Available from: https://doi.org/10.1023/A:1008202821328
• 5. Das S, Ponnuthurai S. Differential evolution: a survey of the state-of-the-art. IEEE Trans Evol Comput. 2011;15(1):4-31. Available from: https://doi.org/10.1109/tevc.2010.2059031
• 6. Sarkar S, Paul S, Burman R, Das S, Chaudhuri S. A fuzzy entropy-level image thresholding using differential evolution. Int Conf Swarm Evol Memet Comput. 2014;386–95. Available from: https://doi.org/10.1007/978-3-319-20294-5_34
• 7. Nihal P, Ashish S, Abhishek M, Partha P, Debi D. Moving object detection using modified temporal differencing and local fuzzy thresholding. J Supercomput. 2017;73:1120–39. Available from: https://doi.org/10.1007/s11227-016-1815-7
• 8. Charansiriphaisan K, Sirapat C, Khamron S. A global multilevel thresholding using differential evolution approach. Math Probl Eng. 2014;1-23. Available from: https://doi.org/10.1155/2014/974024
• 9. Yuanyuan J, Dong Z, Wenchang Z, Li W. Multi-level thresholding image segmentation based on improved slime mould algorithm and symmetric cross-entropy. Entropy. 2023;25(1):178. Available from: https://doi.org/10.3390/e25010178
• 10. Jinzhong Z, Tan Z, Duansong W. A complex-valued encoding golden jackal optimization for multilevel thresholding image segmentation. Appl Soft Comput. 2024;165:112108. Available from: https://doi.org/10.1016/j.asoc.2024.112108
• 11. Giveki D. Robust moving object detection based on fusing At-anassov’s intuitionistic 3D fuzzy histon roughness index and texture features. Int J Approx Reason. 2021;135:1-20. Available from: https://doi.org/10.1016/j.ijar.2021.04.007
• 12. Giveki D, Montazer A, Soltanshahi A. Atanassov’s intuitionistic fuzzy histon for robust moving object detection. Int J Approx Reason. 2017;91:80-95. Available from: https://doi.org/10.1016/j.ijar.2017.08.014
• 13. Giveki D, Soltanshahi A, Yousefvand M. Proposing a new feature descriptor for moving object detection. Optik. 2020;209:164563. Available from: https://doi.org/10.1016/j.ijleo.2020.164563
• 14. Hathiram N, Ravi J. Hybridizing sine cosine algorithm with differential evolution for global optimization and object tracking. Appl Soft Com-put. 2018;62:1019-43. Available from: https://doi.org/10.1016/j.asoc.2017.09.039
• 15. Yi W, Zhiming L, Pierre-Marc J. Hybridizing sine cosine algorithm with differential evolution for global optimization and object tracking. Appl Soft Comput. 2018;62:1019-43. Available from: https://doi.org/10.1016/j.asoc.2017.09.039
• 16. Cao W, Yuan J, He Z. Fast deep neural networks with knowledge guided training and predicted regions of interests for real-time video object detection. IEEE Access. 2018;6:8990-9. Available from: https://doi.org/10.1109/access.2018.2795798
• 17. García-Aguilar I, Jorge G, Rafael M, Ezequiel L. Automated labeling of training data for improved object detection in traffic videos by fine-tuned deep convolutional neural networks. Pattern Recognit Lett. 2023;167:45 52. Available from: https://doi.org/10.1016/j.patrec.2023.01.015
• 18. Talukdar J, Gupta S, Rajpura P, Hegde R. Transfer learning for object detection using state-of-the-art deep neural networks. Int Conf Signal Process Integr Netw SPIN. 2018. Available from: https://doi.org/10.1109/spin.2018.8474198
• 19. Boufares O, Aloui N, Cherif A. Adaptive threshold for background subtraction in moving object detection using stationary wavelet trans-forms 2D. Int J Adv Comput Sci Appl. 2016;7(8). Available from: https://doi.org/10.14569/ijacsa.2016.070805
• 20. Lu G, Kudo M, Toyama J. Temporal segmentation and assignment of successive actions in a long-term video. Pattern Recognit Lett. 2013;34(15):1936 44. Available from: https://doi.org/10.1016/j.patrec.2012.10.023
• 21. Yong X, Jixiang D, Bob Z, Daoyun X. Background modeling methods in video analysis: A review and comparative evaluation. CAAI Trans Intell Technol. 2016;1(1):43 60. Available from: https://doi.org/10.1016/j.trit.2016.03.005
• 22. Carolina R, Roberto L. Unsupervised learning from videos using temporal coherency deep networks. Comput Vis Image Underst. 2019;179:79 89. Available from: https://doi.org/10.1016/j.cviu.2018.08.003
• 23. Oliver N, Rosario B, Pentland A. A Bayesian computer vision system for modeling human interactions. IEEE Trans Pattern Anal Mach Intell. 2000;22(8):831 43. Available from: https://doi.org/10.1109/34.868684
• 24. Pierre-Luc S, Guillaume B, Robert B. SUBSENSE: A universal change detection method with local adaptive sensitivity. IEEE Trans Image Process. 2015;24(1):359 73. Available from: https://doi.org/10.1109/tip.2014.2378053
• 25. Maddalena L, Petrosino A. The SOBS algorithm: What are the limits? Proc IEEE Workshop Change Detect CVPR. 2012. Availa-ble from: https://doi.org/10.1109/cvprw.2012.6238922
• 26. Zivkovic Z. Improved adaptive Gaussian mixture model for back-ground subtraction. Proc 17th Int Conf Pattern Recognit ICPR. 2004. Available from: https://doi.org/10.1109/icpr.2004.1333992
• 27. Bouwmans T, Javed S, Sultana M, Jung S. Deep neural network concepts for background subtraction: A systematic review and comparative evaluation. arXiv. 2018. Available from: https://arxiv.org/pdf/1811.05255
• 28. Wang Y, Jodoin PM, Porikli F, Konrad J, Benezeth Y, Ishwar P. CDnet 2014: An expanded change detection benchmark dataset. Proc IEEE Conf Comput Vis Pattern Recognit Workshops. 2014;387–94. Available from: https://www.opencv.org
• 29. Maddalena L, Petrosino A. Towards benchmarking scene back-ground initialization. Proc ICIAP Workshops. 2015;469 76. Availa-ble from: http://sbmi2015.na.icar.cnr.it/
• 30. Cuevas C, Yez EM, García N. Labeled dataset for integral evalua-tion of moving object detection algorithms: LASIESTA. Comput Vis Image Underst. 2016;152:103 17. Available from: https://doi.org/10.1016/j.cviu.2016.01.012
• 31. Stauffer C, Grimson WEL. Learning patterns of activity using real-time tracking. IEEE Trans Pattern Anal Mach Intell. 2000;22(8):747 57. Available from: https://doi.org/10.1109/34.868684
• 32. Berjón D, Cuevas C, Morán F, García N. Real-time non-parametric background subtraction with tracking-based foreground update. Pattern Recognit. 2018;74:156 70. Available from: https://doi.org/10.1016/j.patcog.2017.09.009
• 33. Vacavant A, Chateau T, Wilhelm A, Lequievre L. A benchmark dataset for outdoor foreground/background extraction. Proc Asian Conf Comput Vis ACCV. 2012.