Enhancing Abandoned Object Detection with Dual Background Models and Yolo-NAS

Authors

  • Saluky Electrical and Informatics Engineering, ITB, Indonesia.
  • Gusti Baskara Nugraha Electrical and Informatics Engineering, ITB, Indonesia.
  • Suhono Harso Supangkat Electrical and Informatics Engineering, ITB, Indonesia.

Keywords:

Dual background model, YOLO-NAS, Abandoned Object

Abstract

The rapid advancement of computer vision technology has paved the way for many surveillance, security, and public safety applications. Abandoned object detection, a critical component in video surveillance systems, plays an essential role in identifying potential security threats and ensuring the safety of public spaces. This paper proposes a new approach for abandoned object detection that combines a dual background model with YOLO-NAS (You Only Look Once Neural Architecture Search), a state-of-the-art object detection framework. The proposed method utilizes two background models with different learning rates, one based on fast background subtraction and one using slower background modeling. The dual background model is verified with YOLO-NAS to improve the accuracy and robustness of abandoned object detection. This model can perform better in low light conditions and changes in illumination. Incorporating YOLO-NAS into the framework enables real-time object detection and tracking, enabling efficient and accurate identification of abandoned objects. YOLO-NAS improves detection speed and maintains high precision, making it an ideal candidate for real-time surveillance applications. Our experimental results, conducted on diverse video sequences, demonstrate the superiority of the proposed approach over existing methods. The dual background model combined with YOLO-NAS consistently outperforms other abandoned object detection algorithms regarding accuracy and speed. The proposed method is robust in challenging scenarios, including dense environments and varying lighting conditions. This paper presents a new abandoned object detection system that leverages the dual background model and YOLO-NAS to achieve state-of-the-art accuracy, speed, and robustness performance. The proposed approach promises to improve security and surveillance systems in public spaces, transportation hubs, and critical infrastructure, thereby contributing to increased public safety and threat prevention.

Downloads

Download data is not yet available.

References

Y. Yang, Z. Fu, and S.M. Naqvi, "Abnormal event detection for video surveillance using an enhanced two-stream fusion method," Neurocomputing , vol. 553, p. 126561, Oct. 2023, doi: 10.1016/j.neucom.2023.126561.

Mohd. A. Ansari, DK Singh, and VP Singh, "Detecting abnormal behavior in megastores for crime prevention using a deep neural architecture," Int. J. Multimed. Inf. Retr. , vol. 12, no. 2, p. 25, Dec. 2023, doi: 10.1007/s13735-023-00289-2.

RS Amshavalli and J. Kalaivani, "Real-time institutional video data analysis using fog computing and adaptive background subtraction," J. Real-Time Image Process. , vol. 20, no. 5, p. 96, Oct. 2023, doi: 10.1007/s11554-023-01350-3.

J. Albusac, D. Vallejo, J. J. Castro-Schez, S. Sanchez-Sobrino, and C. Gomez-Portes, "Multi-analysis surveillance and dynamic distribution of computational resources: Towards extensible, robust, and efficient monitoring of environments," Expert Syst. Appl. , vol. 175, p. 114692, Aug. 2021, doi: 10.1016/j.eswa.2021.114692.

J. Isern et al. , "A Cyber-Physical System for Integrated Remote Control and Protection of Smart Grid Critical Infrastructures," J. Signal Process. Syst. , Feb. 2023, doi: 10.1007/s11265-023-01842-2.

S. Saeed, SA Suayyid, MS Al-Ghamdi, H. Al-Muhaisen, and AM Almuhaideb, "A Systematic Literature Review on Cyber Threat Intelligence for Organizational Cybersecurity Resilience," Sensors , vol. 23, no. 16, p. 7273, Aug. 2023, doi: 10.3390/s23167273.

K. Lin, S.-C. Chen, C.-S. Chen, D.-T. Lin, and Y.-P. Hung, "Abandoned Object Detection via Temporal Consistency Modeling and Back-Tracing Verification for Visual Surveillance," IEEE Trans. Inf. Forensics Security. , vol. 10, no. 7, pp. 1359–1370, Jul. 2015, doi: 10.1109/TIFS.2015.2408263.

W. Liu, P. Liu, C. Xiao, and R. Hu, "General-purpose Abandoned Object Detection Method without Background Modeling," in 2021 IEEE International Conference on Imaging Systems and Techniques (IST) , Kaohsiung, Taiwan : IEEE, Aug. 2021, pp. 1–5. doi: 10.1109/IST50367.2021.9651400.

H. Park, S. Park, and Y. Joo, "Detection of Abandoned and Stolen Objects Based on Dual Background Model and Mask R-CNN," IEEE Access , vol. 8, pp. 80010–80019, 2020, doi: 10.1109/ACCESS.2020.2990618.

H. Su, W. Wang, and S. Wang, "A robust all-weather abandoned objects detection algorithm based on dual background and gradient operators," Multimed. Tools Appl. , vol. 82, no. 19, pp. 29477–29499, Aug. 2023, doi: 10.1007/s11042-023-14632-6.

YD Teja, "Static object detection for video surveillance," Multimed. Tools Appl. , vol. 82, no. 14, pp. 21627–21639, Jun. 2023, doi: 10.1007/s11042-023-14696-4.

M. Chen, X. Wei, Q. Yang, Q. Li, G. Wang, and M.-H. Yang, "Spatiotemporal GMM for Background Subtraction with Superpixel Hierarchy," IEEE Trans. Anal Patterns. Mach. Intel. , vol. 40, no. 6, pp. 1518–1525, June. 2018, doi: 10.1109/TPAMI.2017.2717828.

S. Saluky, SH Supangkat, and IB Nugraha, "Abandoned Object Detection Method Using Convolutional Neural Network," in 2020 International Conference on ICT for Smart Society (ICISS) , Bandung, Indonesia: IEEE, Nov. 2020, pp. 1–4. doi: 10.1109/ICISS50791.2020.9307547.

D. Sharma and Z.A. Jaffery, "Multiple object localization and tracking based on boosted efficient binary local image descriptor," MethodsX , vol. 11, p. 102354, Dec. 2023, doi: 10.1016/j.mex.2023.102354.

U. Sirisha, SP Praveen, PN Srinivasu, P. Barsocchi, and AK Bhoi, "Statistical Analysis of Design Aspects of Various YOLO-Based Deep Learning Models for Object Detection," Int . J. Comput. Intel. Syst. , vol. 16, no. 1, p. 126, Aug. 2023, doi: 10.1007/s44196-023-00302-w.

T. Diwan, G. Anirudh, and JV Tembhurne, "Object detection using YOLO: challenges, architectural successors, datasets and applications," Multimed. Tools Appl. , vol. 82, no. 6, pp. 9243–9275, March. 2023, doi: 10.1007/s11042-022-13644-y.

LH Jadhav and BF Momin, "Detection and identification of unattended/removed objects in video surveillance," in 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT) , Bangalore, India: IEEE, May 2016 , pp. 1770–1773. doi: 10.1109/RTEICT.2016.7808138.

L. Geng and Z. Xiao, "Real Time Foreground-Background Segmentation Using Two-Layer Codebook Model," in 2011 International Conference on Control, Automation and Systems Engineering (CASE) , Singapore: IEEE, Jul. 2011, pp. 1–5. doi: 10.1109/ICCASE.2011.5997546.

İ. Delibaşoğlu, "Moving object detection method with motion regions tracking in background subtraction," Signal Image Video Process. , vol. 17, no. 5, pp. 2415–2423, Jul. 2023, doi: 10.1007/s11760-022-02458-y.

W. Nebili, B. Farou, and H. Seridi, "Background subtraction using Artificial Immune Recognition System and Single Gaussian (AIRS-SG)," Multimed. Tools Appl. , vol. 79, no. 35–36, pp. 26099–26121, Sept. 2020, doi: 10.1007/s11042-020-08935-1.

Md. S. Arman, Md. M. Hasan, F. Sadia, AK Shakir, K. Sarker, and F.A. Himu, "Detection and Classification of Road Damage Using R-CNN and Faster R-CNN: A Deep Learning Approach," in Cyber Security and Computer Science , vol . 325, T. Bhuiyan, Md. M. Rahman, and Md. A. Ali, Eds., in Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol. 325. , Cham: Springer International Publishing, 2020, pp. 730–741. doi: 10.1007/978-3-030-52856-0_58.

W. Liu et al. , "SSD: Single Shot MultiBox Detector," in Computer Vision – ECCV 2016 , vol. 9905, B. Leibe, J. Matas, N. Sebe, and M. Welling, Eds., in Lecture Notes in Computer Science, vol. 9905. , Cham: Springer International Publishing, 2016, pp. 21–37. doi: 10.1007/978-3-319-46448-0_2.

E. Casas, L. Ramos, E. Bendek, and F. Rivas-Echeverría, "Assessing the Effectiveness of YOLO Architectures for Smoke and Wildfire Detection," IEEE Access , vol. 11, pp. 96554–96583, 2023, doi: 10.1109/ACCESS.2023.3312217.

DECI, "YOLO-NAS." 2023. [Online]. Available: https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md

S. Sahoo and PK Nanda, "Adaptive Feature Fusion and Spatio-Temporal Background Modeling in KDE Framework for Object Detection and Shadow Removal," IEEE Trans. Circuits Syst. Video Technol. , vol. 32, no. 3, pp. 1103–1118, March. 2022, doi: 10.1109/TCSVT.2021.3074143.

C.-R. Huang, W.-Y. Huang, Y.-S. Liao, C.-C. Lee, and Y.-W. Yeh, "A Content-Adaptive Resizing Framework for Boosting Computation Speed of Background Modeling Methods," IEEE Trans. Syst. Cyber Man. Syst. , vol. 52, no. 2, pp. 1192–1204, Feb. 2022, doi: 10.1109/TSMC.2020.3018872.

S. Kalli, T. Suresh, A. Prasanth, T. Muthumanickam, and K. Mohanram, "An effective motion object detection using adaptive background modeling mechanism in video surveillance system," J. Intell. Fuzzy Syst. , vol. 41, no. 1, pp. 1777–1789, Aug. 2021, doi: 10.3233/JIFS-210563.

SK Mohanty and S. Rup, "An adaptive background modeling for foreground detection using spatio-temporal features," Multimed. Tools Appl. , vol. 80, no. 1, pp. 1311–1341, Jan. 2021, doi: 10.1007/s11042-020-09552-8.

Junxian Wang, G. Bebis, and R. Miller, "Overtaking Vehicle Detection Using Dynamic and Quasi-Static Background Modeling," in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops , San Diego, CA, USA: IEEE, 2005, pp. 64–64. doi: 10.1109/CVPR.2005.506.

H. Chen, G. Cheng, T. Shen, Y. Liu, Y. Fang, and BKP Horn, "A Method to Extract Overall Trajectory Information from Frame Sequence of Fixed Background without Object Tracking," in 2018 4th International Conference on Universal Village (UV) , Boston, MA, USA: IEEE, Oct. 2018, pp. 1–4. doi: 10.1109/UV.2018.8642123.

MS Devi and R. Suguna, "Dynamic Abandoned Object Detector Through Camera Surveillance System," J. Comput. Theor. Nanosci. , vol. 15, no. 11, pp. 3405–3411, Nov. 2018, doi: 10.1166/jctn.2018.7633.

P. Spagnolo, A. Caroppo, M. Leo, T. Martiriggiano, and T. D'Orazio, "An Abandoned/Removed Objects Detection Algorithm and Its Evaluation on PETS Datasets," in 2006 IEEE International Conference on Video and Signal Based Surveillance , Sydney, Australia: IEEE, Nov. 2006, pp. 17–17. doi: 10.1109/AVSS.2006.18.

M. Bhargava, C.-C. Chen, MS Ryoo, and JK Aggarwal, "Detection of object abandonment using temporal logic," Mach. Vis. Appl. , vol. 20, no. 5, pp. 271–281, Jul. 2009, doi: 10.1007/s00138-008-0181-8.

N. Menejes Palomino and G. Cámara Chávez, "Abnormal Event Detection in Video Using Motion and Appearance Information," in Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications , vol. 10657, M. Mendoza and S. Velastín, Eds., in Lecture Notes in Computer Science, vol. 10657. , Cham: Springer International Publishing, 2018, pp. 382–390. doi: 10.1007/978-3-319-75193-1_46.

F. Porikli, Y. Ivanov, and T. Haga, "Robust Abandoned Object Detection Using Dual Foregrounds," EURASIP J. Adv. Signal Process. , vol. 2008, no. 1, p. 197875, Dec. 2007, doi: 10.1155/2008/197875.

H. Park, Seungchul Park, and Youngbok, "Robust Real-time Detection of Abandoned Objects using a Dual Background Model," KSII Trans. Internet Inf. Syst. , vol. 14, no. 2, Feb. 2020, doi: 10.3837/tiis.2020.02.017.

Downloads

Published

25.12.2023

How to Cite

Saluky, S., Nugraha, G. B. ., & Supangkat, S. H. . (2023). Enhancing Abandoned Object Detection with Dual Background Models and Yolo-NAS. International Journal of Intelligent Systems and Applications in Engineering, 12(2), 547–554. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/4298

Issue

Section

Research Article