Temporal Shift -- Multi-Objective Loss Function for Improved Anomaly Fall Detection

TL;DR

This paper introduces Temporal Shift, a multi-objective loss function for autoencoders that enhances video-based fall detection by predicting future and reconstructed frames, significantly improving anomaly detection accuracy across multiple models.

Contribution

The paper proposes a novel multi-objective loss function called Temporal Shift that improves autoencoder-based fall detection by incorporating future frame prediction.

Findings

Significant AUC ROC improvements across models

Enhanced detection accuracy with Temporal Shift loss

Effective on multi-modal and single-camera setups

Abstract

Falls are a major cause of injuries and deaths among older adults worldwide. Accurate fall detection can help reduce potential injuries and additional health complications. Different types of video modalities can be used in a home setting to detect falls, including RGB, Infrared, and Thermal cameras. Anomaly detection frameworks using autoencoders and their variants can be used for fall detection due to the data imbalance that arises from the rarity and diversity of falls. However, the use of reconstruction error in autoencoders can limit the application of networks' structures that propagate information. In this paper, we propose a new multi-objective loss function called Temporal Shift, which aims to predict both future and reconstructed frames within a window of sequential frames. The proposed loss function is evaluated on a semi-naturalistic fall detection dataset containing multiple camera modalities. The autoencoders were trained on normal activities of daily living (ADL) performed by older adults and tested on ADLs and falls performed by young adults. Temporal shift shows significant improvement to a baseline 3D Convolutional autoencoder, an attention U-Net CAE, and a multi-modal neural network. The greatest improvement was observed in an attention U-Net model improving by 0.20 AUC ROC for a single camera when compared to reconstruction alone. With significant improvement across different models, this approach has the potential to be widely adopted and improve anomaly detection capabilities in other settings besides fall detection.