Topological Data Analysis for Anomaly Detection in Video Surveillance
- 20 August 2026
- book chapter
- Published by IGI Global Scientific Publishing
- p. 285-318
Abstract
Video anomaly detection remains challenging because abnormal events are scarce, context-dependent, and operationally sensitive. The objective of this chapter is to develop and evaluate an unsupervised TDA-based framework for modeling surveillance windows without relying on reconstruction error. Trajectories are encoded as weighted spatio-temporal point clouds. Vietoris–Rips persistent homology yields H0 and H1 signatures, persistence images, Betti curves, and interpretable scalar descriptors. Models trained solely on normal data are evaluated across six controlled event classes. Isolation Forest achieved a ROC-AUC of 0.967 and average precision of 0.959, while the Mapper graph separated normal regions from anomaly-dense nodes. Results show that global connectivity and loop structure provide stable, privacy-aware support for explainable surveillance analytics and establish a reproducible bridge between mathematical topology and deployable computer vision.Keywords
This publication has 25 references indexed in Scilit:
- Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning2024
- Navigating the metric maze: a taxonomy of evaluation metrics for anomaly detection in time seriesData Mining and Knowledge Discovery, 2023
- ByteTrack: Multi-object Tracking by Associating Every Detection Box2022
- Persistent-homology-based machine learning: a survey and a comparative studyArtificial Intelligence Review, 2022
- Emerging Properties in Self-Supervised Vision Transformers2021
- Ripser: efficient computation of Vietoris–Rips persistence barcodesJournal of Applied and Computational Topology, 2021
- Anomaly Detection in Video via Self-Supervised and Multi-Task Learning2021
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow2020
- The Structure and Stability of Persistence Modules2016
- Stability of Persistence DiagramsDiscrete & Computational Geometry, 2006