Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera

TL;DR

This paper introduces a novel egocentric 360-degree video dataset and a new neural network architecture for detecting abnormal situations faced by visually impaired individuals, enhancing safety monitoring capabilities.

Contribution

The paper presents the first egocentric 360-degree dataset for anomaly detection and a novel FDPN architecture for identifying abnormal events and their directions.

Findings

Achieved state-of-the-art performance on VIEW360, UCF-Crime, and Shanghaitech datasets.

Demonstrated effectiveness of the FDPN in frame-level abnormal event prediction.

Provided a new resource for research on assistive safety technologies for visually impaired people.

Abstract

Recent advancements in computer vision have led to a renewed interest in developing assistive technologies for individuals with visual impairments. Although extensive research has been conducted in the field of computer vision-based assistive technologies, most of the focus has been on understanding contexts in images, rather than addressing their physical safety and security concerns. To address this challenge, we propose the first step towards detecting anomalous situations for visually impaired people by observing their entire surroundings using an egocentric 360-degree camera. We first introduce a novel egocentric 360-degree video dataset called VIEW360 (Visually Impaired Equipped with Wearable 360-degree camera), which contains abnormal activities that visually impaired individuals may encounter, such as shoulder surfing and pickpocketing. Furthermore, we propose a new architecture called the FDPN (Frame and Direction Prediction Network), which facilitates frame-level prediction of abnormal events and identifying of their directions. Finally, we evaluate our approach on our VIEW360 dataset and the publicly available UCF-Crime and Shanghaitech datasets, demonstrating state-of-the-art performance.