Motion and Region Aware Adversarial Learning for Fall Detection with Thermal Imaging
This addresses privacy concerns in home-based fall detection for elderly or at-risk individuals, though it is incremental as it builds on existing adversarial and anomaly detection methods.
The paper tackled fall detection using thermal imaging to preserve privacy and handle class imbalance by framing it as anomaly detection within an adversarial framework, achieving superior results on a public dataset compared to standard baselines.
Automatic fall detection is a vital technology for ensuring the health and safety of people. Home-based camera systems for fall detection often put people's privacy at risk. Thermal cameras can partially or fully obfuscate facial features, thus preserving the privacy of a person. Another challenge is the less occurrence of falls in comparison to the normal activities of daily living. As fall occurs rarely, it is non-trivial to learn algorithms due to class imbalance. To handle these problems, we formulate fall detection as an anomaly detection within an adversarial framework using thermal imaging. We present a novel adversarial network that comprises of two-channel 3D convolutional autoencoders which reconstructs the thermal data and the optical flow input sequences respectively. We introduce a technique to track the region of interest, a region-based difference constraint, and a joint discriminator to compute the reconstruction error. A larger reconstruction error indicates the occurrence of a fall. The experiments on a publicly available thermal fall dataset show the superior results obtained compared to the standard baseline.