EUVIMEDEUVIMED entdecken
Crossref

A Centroid-Based Pose Estimation Framework for Real-Time Abnormal Activity Detection Using Adaptive KNN

Mahesh Dhande Mahesh Dhande, Snehal Chavan Snehal Chavan, Vaishnavi Surwade Vaishnavi Surwade, Bhakti Kokate Bhakti Kokate, Snehal Mathure Snehal Mathure

International Journal of Creative and Open Research in Engineering and Management · 06.06.2026 · 02 (06) · 1-4

DOI: 10.55041/ijcope.v2i6.068 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Creative and Open Research in Engineering and Management, online erschienen am 06.06.2026. Verfasst von Mahesh Dhande Mahesh Dhande und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time abnormal activity detection in surveil-lance systems requires a balance between accuracy, computa-tional efficiency, and privacy preservation. This paper presents a lightweight and efficient framework for detecting human activities using skeletal pose estimation on standard consumer-grade hardware. The proposed system extracts 33 human body landmarks and converts them into normalized spatial feature vectors using a centroid-based approach to achieve translation and scale invariance. For classification, a K-Nearest Neighbors (KNN) model is employed with a visibility-weighted Manhattan (L1) distance metric to improve robustness against noisy or partially occluded landmarks. Additionally, an adaptive distance threshold derived from intra-class variations and a temporal smoothing mechanism are introduced to enhance prediction stability and reduce false detections. The system supports multi-person detection using region-based processing and integrates an automated alert mechanism that generates real-time notifications, including snapshot capture and email transmission via SMTP. Experimental results demonstrate that the proposed framework achieves high accuracy with low latency, making it suitable for real-time surveillance and safety-critical applications. Index Terms—Pose Estimation, K-Nearest Neighbors (KNN), Anomaly Detection, Real-time Surveillance, Multi-person Detec-tion, Edge Computing

Zitieren

APA

Dhande, M. D. M., Chavan, S. C. S., Surwade, V. S. V., Kokate, B. K. B., & Mathure, S. M. S. (2026). A Centroid-Based Pose Estimation Framework for Real-Time Abnormal Activity Detection Using Adaptive KNN. International Journal of Creative and Open Research in Engineering and Management, 02(06), 1-4. https://doi.org/10.55041/ijcope.v2i6.068

Vancouver

Dhande MDM, Chavan SCS, Surwade VSV, Kokate BKB, Mathure SMS. A Centroid-Based Pose Estimation Framework for Real-Time Abnormal Activity Detection Using Adaptive KNN. International Journal of Creative and Open Research in Engineering and Management. 2026;02(06):1-4. doi:10.55041/ijcope.v2i6.068

BibTeX
@article{Dhande2026,
  author = {Dhande, Mahesh Dhande Mahesh and Chavan, Snehal Chavan Snehal and Surwade, Vaishnavi Surwade Vaishnavi and Kokate, Bhakti Kokate Bhakti and Mathure, Snehal Mathure Snehal},
  title = {A Centroid-Based Pose Estimation Framework for Real-Time Abnormal Activity Detection Using Adaptive KNN},
  journal = {International Journal of Creative and Open Research in Engineering and Management},
  year = {2026},
  volume = {02},
  number = {06},
  pages = {1--4},
  doi = {10.55041/ijcope.v2i6.068}
}
Kostenlos starten →