Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-directional LSTM

TL;DR

This paper introduces an attention-guided Bi-directional LSTM model leveraging Mask R-CNN for accurate fall event detection in complex backgrounds, outperforming existing methods in robustness and precision.

Contribution

The paper presents a novel combination of Mask R-CNN and attention-guided Bi-directional LSTM for fall detection in complex scenes, addressing limitations of traditional background subtraction methods.

Findings

High accuracy in fall detection on public and self-built datasets

Robust performance in complex background scenarios

Outperforms state-of-the-art methods in evaluation

Abstract

Fall event detection, as one of the greatest risks to the elderly, has been a hot research issue in the solitary scene in recent years. Nevertheless, there are few researches on the fall event detection in complex background. Different from most conventional background subtraction methods which depend on background modeling, Mask R-CNN method based on deep learning technique can clearly extract the moving object in noise background. We further propose an attention guided Bi-directional LSTM model for the final fall event detection. To demonstrate the efficiency, the proposed method is verified in the public dataset and self-build dataset. Evaluation of the algorithm performances in comparison with other state-of-the-art methods indicates that the proposed design is accurate and robust, which means it is suitable for the task of fall event detection in complex situation.