Vision-Based Activity Recognition in Children with Autism-Related Behaviors

TL;DR

This paper presents a vision-based system using advanced deep learning models to analyze autism-related behaviors in children from videos, achieving high accuracy and enabling potential deployment on embedded devices.

Contribution

It introduces a region-based computer vision approach with enhanced datasets and models, including lightweight solutions, for autism behavior analysis in uncontrolled environments.

Findings

Achieved 0.83 Weighted F1-score with Inflated 3D Convnet and TCNs.

Proposed a lightweight ESNet-based model with 0.71 F1-score.

Outperformed existing methods in autism-related action classification.

Abstract

Advances in machine learning and contactless sensors have enabled the understanding complex human behaviors in a healthcare setting. In particular, several deep learning systems have been introduced to enable comprehensive analysis of neuro-developmental conditions such as Autism Spectrum Disorder (ASD). This condition affects children from their early developmental stages onwards, and diagnosis relies entirely on observing the child's behavior and detecting behavioral cues. However, the diagnosis process is time-consuming as it requires long-term behavior observation, and the scarce availability of specialists. We demonstrate the effect of a region-based computer vision system to help clinicians and parents analyze a child's behavior. For this purpose, we adopt and enhance a dataset for analyzing autism-related actions using videos of children captured in uncontrolled environments (e.g. videos collected with consumer-grade cameras, in varied environments). The data is pre-processed by detecting the target child in the video to reduce the impact of background noise. Motivated by the effectiveness of temporal convolutional models, we propose both light-weight and conventional models capable of extracting action features from video frames and classifying autism-related behaviors by analyzing the relationships between frames in a video. Through extensive evaluations on the feature extraction and learning strategies, we demonstrate that the best performance is achieved with an Inflated 3D Convnet and Multi-Stage Temporal Convolutional Networks, achieving a 0.83 Weighted F1-score for classification of the three autism-related actions, outperforming existing methods. We also propose a light-weight solution by employing the ESNet backbone within the same system, achieving competitive results of 0.71 Weighted F1-score, and enabling potential deployment on embedded systems.