Self-Stimulatory Behaviours in the Wild for Autism Diagnosis

Abstract

Autism Spectrum Disorders (ASD), often referred to as autism, are neurological disorders characterised by deficits in cognitive skills, social and communicative behaviours. A common way of diagnosing ASD is by studying behavioural cues expressed by the children. We introduce a new publicly-available dataset of children videos exhibiting self-stimulatory (stimming) behaviours commonly used for autism diagnosis. These videos, posted by parents/caregivers in public domain websites, are collected and annotated for the stimming behaviours. These videos are extremely challenging for automatic behaviour analysis as they are recorded in uncontrolled natural settings. The dataset contains 75 videos with an average duration of 90 seconds per video, grouped under three categories of stimming behaviours: arm flapping, head banging and spinning. We also provide baseline results of tests conducted on this dataset using a standard bag of words approach for human action recognition. To the best of our knowledge, this is the first attempt in publicly making available a SelfStimulatory Behaviour Dataset (SSBD) of children videos recorded in natural settings.

Computer vision in autism spectrum disorder research: a systematic review of published studies from 2009 to 2019

“…Also known as 'stimming behaviours', these behaviours are often manifested when a person with autism engages in actions like rocking, pacing or hand flapping. Researchers [100][101][102] have introduced a dataset with stimming behaviours and used computer vision to determine if these behaviours exist in a video stream. Another quantified behaviour is social interaction and communication among individuals with ASD.…”

“…Due to the lack of a database containing self-stimulatory behaviours, Rajagopalan et al 101 searched for and collected videos on public domain websites and video portals (e.g. YouTube).…”

Realizing Active Inference in Variational Message Passing: The Outcome-Blind Certainty Seeker

“…Additionally, some of these patterns do not seem obviously connected to rewarding or punishing outcomes. For example, those with autism can exhibit very stereotyped repetitive behavior: for example, hand flapping, hand clapping, or rocking (Gabriels et al, 2005), which is often described as stimming (Sundar Rajagopalan, Dhall, & Goecke, 2013). These repetitive and ritualistic behaviors (Lam, 2007) suggest an objective to avoid exploration and the associated uncertainty.…”

Computer Vision Techniques for Autism Symptoms Detection and Recognition: A Survey.

“…Self-hurt: Behaviors like eye-jabbing, skin-picking, head-banging, and hand-gnawing. Among these repetitive behaviors that reveal autism disorder in young children; self-stimulatory or stereotypy behavior, which is a repeated movement of body parts or items [22], is one of the significant indicators of autism. Stereotypical behaviors limit the development of learning and social abilities in autistics [23].…”

“…Accordingly, these behaviors can be recognized from recorded videos especially because it almost follows some pattern; however, it is not straightforward process specifically in uncontrolled environment. Researchers in [22] have conducted and annotated a dataset (SSBD) of self-stimulatory behaviors videos in children to be used in further research. The dataset contains three stereotypy behavior which are arm fluttering, head banging and body rolling.…”