Authors : Ramneet Singh Chadha; Hargun Singh Hunjan

Volume/Issue : Volume 11 - 2026, Issue 4 - April

---

Google Scholar : https://tinyurl.com/47sj3xpn

Scribd : https://tinyurl.com/2wsczdkw

DOI : https://doi.org/10.38124/ijisrt/26apr1807

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : This paper describes the design and deployment of a two-phase real-time surveillance pipeline that integrates pretrained object detection, identity recognition, and rule-based event reasoning for indoor monitoring. In Phase 1, MobileNetSSD performs static image detection across 21 VOC object classes, establishing a detection baseline. Phase 2 replaces this with YOLOv8n operating in persistent tracking mode, augmented by the VGG-Face model from the DeepFace library for zero-shot face matching against a local reference database. No custom model training was carried out at any stage. The pipeline maintains per-person object inventories, detects left-behind items using a centroid-stationarity criterion, and applies a bag-mediated suppression rule at exit to reduce false alerts.

Keywords : Abandoned Object Detection, DeepFace, MobileNetSSD, Object Tracking, Person-Object Association, Real-Time Surveillance, VGG-Face, YOLOv8.

References :

1. N. H. Mackworth, “The breakdown of vigilance during prolonged visual search,” Quarterly Journal of Experimental Psychology, 1948.
2. W. Liu et al., “SSD: Single Shot MultiBox Detector,” in Proc. ECCV, 2016.
3. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proc. IEEE CVPR, 2016.
4. Y. Taigman et al., “DeepFace: Closing the Gap to Human-Level Performance in Face Verification,” in Proc. IEEE CVPR, 2014.
5. F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” in Proc. IEEE CVPR, 2015.
6. S. Serengil and A. Ozpinar, “DeepFace: A Lightweight Face Recognition Framework for Python,” in Proc. IEEE ASYU, 2020.
7. A. Bewley et al., “Simple Online and Realtime Tracking,” in Proc. IEEE ICIP, 2016.
8. N. Wojke et al., “Simple Online and Realtime Tracking with a Deep Association Metric,” in Proc. IEEE ICIP, 2017.
9. Z. Zhang et al., “ByteTrack: Multi-Object Tracking by Associating Every Detection Box,” in Proc. ECCV, 2022.
10. G. Sreenu and M. A. Saleem Durai, “Intelligent Video Surveillance: A Review Using Deep Learning Techniques,” Journal of Big Data, 2019.
11. F. Porikli et al., “Detection of Temporarily Static Regions,” in Proc. IEEE AVSS, 2006.
12. G. B. Huang et al., “Labeled Faces in the Wild,” University of Massachusetts, Tech. Rep., 2008.