Real-Time Object Detection and Surveillance Using MobileNetSSD and YOLOv8 with Pretrained Face Recognition
International Journal of Innovative Science and Research Technology · 07.05.2026 · 3514
DOI: 10.38124/ijisrt/26apr1807 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 07.05.2026. Verfasst von Ramneet Singh Chadha und 1 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Chadha, R. S., & Hunjan, H. S. (2026). Real-Time Object Detection and Surveillance Using MobileNetSSD and YOLOv8 with Pretrained Face Recognition. International Journal of Innovative Science and Research Technology, 3514. https://doi.org/10.38124/ijisrt/26apr1807
Vancouver
Chadha RS, Hunjan HS. Real-Time Object Detection and Surveillance Using MobileNetSSD and YOLOv8 with Pretrained Face Recognition. International Journal of Innovative Science and Research Technology. 2026:3514. doi:10.38124/ijisrt/26apr1807
BibTeX
@article{Chadha2026,
author = {Chadha, Ramneet Singh and Hunjan, Hargun Singh},
title = {Real-Time Object Detection and Surveillance Using MobileNetSSD and YOLOv8 with Pretrained Face Recognition},
journal = {International Journal of Innovative Science and Research Technology},
year = {2026},
pages = {3514},
doi = {10.38124/ijisrt/26apr1807}
}
EUVIMED