Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Modelling and Simulation of Neuromorphic Datasets for Anomaly Detection in Computer Vision

Mike Middleton, Teymoor Ali, Hakan Kayan, Basabdatta Sen Bhattacharya, Charith Perera, Oliver Rhodes, Elena Gheorghiu, Mark Vousden, Martin A. Trefzer

TL;DR

The Anomalous Neuromorphic Tool for Shapes (ANTShapes), a novel dataset simulation framework, 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.

Abstract

Limitations on the availability of Dynamic Vision Sensors (DVS) 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 (ANTShapes), 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.

Modelling and Simulation of Neuromorphic Datasets for Anomaly Detection in Computer Vision

TL;DR

The Anomalous Neuromorphic Tool for Shapes (ANTShapes), a novel dataset simulation framework, 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.

Abstract

Limitations on the availability of Dynamic Vision Sensors (DVS) 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 (ANTShapes), 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.
Paper Structure (8 sections, 7 equations, 3 figures)

This paper contains 8 sections, 7 equations, 3 figures.

Table of Contents

  1. Background
  2. Definition of Anomalies
  3. Crowd Behaviour
  4. Dataset Generation with ANTShapes
  5. Object Properties
  6. Event Generation
  7. Summary & Further Work
  8. Data Availability

Figures (3)

  • Figure 1: A screenshot of ANTShapes. The colour of an object indicates its P-value and the likelihood of its existence in the scene by extension. Blue objects occur relatively frequently, with greener objects being increasingly rarer. Agents that cross the threshold into anomalies are coloured red. Here, anomalies are defined based on position.
  • Figure 2: Event representation of the scene in Figure \ref{['fig:antshapes']}. Anomalies are defined on the distance of agents from the center of the scene, which are are masked in red. Each agent is rotating by an equal value on all three axes which produces spiking events.
  • Figure 3: Frame- and event-views from two different temporal moments within a complex scene populated by many shapes with randomised behaviours. Anomalies were defined as fast-moving objects to produce this example.