Depth-Weighted Detection of Behaviours of Risk in People with Dementia using Cameras

2024-08-28

arXiv.org

AI Summary

Existing video-based monitoring systems for detecting high-risk behaviors (e.g., agitation, aggression) in dementia patients within nursing homes suffer from high false-positive rates across varying distances and poor generalizability of fixed detection thresholds. Method: We propose a lightweight, camera-agnostic video analysis framework comprising: (i) a novel depth-weighted loss function that explicitly balances semantic importance between near- and far-field events; (ii) an anomaly-sample-driven adaptive thresholding mechanism; and (iii) a unified pipeline integrating depth-aware representation learning, unsupervised anomaly detection, and ROC-curve optimization to enable cross-camera, inter-individual, and gender-specific evaluation. Results: Evaluated on real-world multi-view nursing home data, our method achieves AUCs of 0.852, 0.810, and 0.768 across three camera views, with significantly reduced false alarm rates—demonstrating strong clinical validity and robustness in practical caregiving environments.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Multiagent Systems: Adversarial Agents
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The behavioural and psychological symptoms of dementia, such as agitation and aggression, present a significant health and safety risk in residential care settings. Many care facilities have video cameras in place for digital monitoring of public spaces, which can be leveraged to develop an automated behaviours of risk detection system that can alert the staff to enable timely intervention and prevent the situation from escalating. However, one of the challenges in our previous study was the presence of false alarms due to disparate importance of events based on distance. To address this issue, we proposed a novel depth-weighted loss to enforce equivalent importance to the events happening both near and far from the cameras; thus, helping to reduce false alarms. We further propose to utilize the training outliers to determine the anomaly threshold. The data from nine dementia participants across three cameras in a specialized dementia unit were used for training. The proposed approach obtained the best area under receiver operating characteristic curve performance of 0.852, 0.81 and 0.768, respectively, for the three cameras. Ablation analysis was conducted for the individual components of the proposed approach and effect of frame size and frame rate. The performance of the proposed approach was investigated for cross-camera, participant-specific and sex-specific behaviours of risk detection. The proposed approach performed reasonably well in reducing false alarms. This motivates further research to make the system more suitable for deployment in care facilities.

Problem

• Dementia Patient Safety
• Automated Surveillance System
• False Alarm Reduction

Innovation

• anomaly detection
• dementia care
• camera-based monitoring