Modelling and Simulation of Neuromorphic Datasets for Anomaly Detection in Computer Vision
#neuromorphic vision #event cameras #Dynamic Vision Sensors #anomaly detection #dataset simulation #Unity engine #3D scene generation #statistical labeling #central limit theorem #computer vision #machine learning #pattern recognition
📌 Key Takeaways
- Scarcity of Dynamic Vision Sensor datasets limits neuromorphic computer‑vision research.
- ANTShapes is a novel Unity‑engine simulation framework that models abstract, configurable 3D scenes.
- Object behaviours (motion, rotation, etc.) are generated randomly and labelled for anomalies using a statistical process grounded in the central limit theorem.
- The framework can produce arbitrary dataset sizes, exporting frame data and labels with minimal parameter adjustments.
- ANTShapes supports key vision tasks such as object recognition, localisation and anomaly detection in event‑based imagery.
📖 Full Retelling
WHO: Mike Middleton and eight co‑authors – Teymoor Ali, Hakan Kayan, Basabdatta Sen Bhattacharya, Charith Perera, Oliver Rhodes, Elena Gheorghiu, Mark Vousden, and Martin A. Trefzer. WHAT: They introduce ANTShapes, a Unity‑based simulator that generates neuromorphic datasets with controllable object behaviours for anomaly detection in computer vision. WHERE: The paper was submitted to arXiv under the computer vision, artificial intelligence and machine learning categories (cs.CV, cs.AI, cs.LG). WHEN: It was submitted on 26 February 2026. WHY: The work addresses the scarcity of Dynamic Vision Sensor datasets by providing an extensible framework to create large, labelled datasets for event‑based computer‑vision research.
🏷️ Themes
Neuromorphic vision, Event‑based computer vision, Dynamic Vision Sensors, Dataset simulation, Anomaly detection, Computer vision, Artificial intelligence, Machine learning, Unity engine
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
--> Computer Science > Computer Vision and Pattern Recognition arXiv:2602.23514 [Submitted on 26 Feb 2026] Title: Modelling and Simulation of Neuromorphic Datasets for Anomaly Detection in Computer Vision Authors: Mike Middleton , Teymoor Ali , Hakan Kayan , Basabdatta Sen Bhattacharya , Charith Perera , Oliver Rhodes , Elena Gheorghiu , Mark Vousden , Martin A. Trefzer View a PDF of the paper titled Modelling and Simulation of Neuromorphic Datasets for Anomaly Detection in Computer Vision, by Mike Middleton and 8 other authors View PDF HTML Abstract: Limitations on the availability of Dynamic Vision Sensors present a fundamental challenge to researchers of neuromorphic computer vision applications. In response, datasets have been created by the research community, but often contain a limited number of samples or scenarios. To address the lack of a comprehensive simulator of neuromorphic vision datasets, we introduce the Anomalous Neuromorphic Tool for Shapes , a novel dataset simulation framework. Built in the Unity engine, ANTShapes simulates abstract, configurable 3D scenes populated by objects displaying randomly-generated behaviours describing attributes such as motion and rotation. The sampling of object behaviours, and the labelling of anomalously-acting objects, is a statistical process following central limit theorem principles. Datasets containing an arbitrary number of samples can be created and exported from ANTShapes, along with accompanying label and frame data, through the adjustment of a limited number of parameters within the software. ANTShapes addresses the limitations of data availability to researchers of event-based computer vision by allowing for the simulation of bespoke datasets to suit purposes including object recognition and localisation alongside anomaly detection. Comments: draft paper Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2602.23514 [cs.CV] (...
Read full article at source