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 · 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.
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}
}
EUVIMED