Automated and scalable Computerized Assessment of Motor Imitation (CAMI) in children with Autism Spectrum Disorder using a single 2D camera: A pilot study.
A free phone app scores full-body imitation as well as lab-grade cameras.
01Research in Context
What this study did
Adams et al. (2021) built a free phone app that scores full-body imitation. Kids watched a short video and copied the moves. A single 2-D camera tracked 18 body points with OpenPose software.
The team compared the cheap 2-D scores to expensive 3-D cameras and to human raters. They tested both autistic and typically developing children.
What they found
The 2-D camera scores matched the 3-D camera and the human coders. Autistic children scored lower than peers, and the gap was large. The tool separated the two groups with big effect sizes.
How this fits with other research
Tassé et al. (2013) used a tablet and motion markers to show autistic teens copied object size less accurately. CAMI drops the markers and still finds a clear autism gap, so the deficit holds across setups.
Shaban et al. (2026) shrank an eye-tracking autism screener from 10 min to 4 min. CAMI does the same for motor imitation: both teams cut cost and time while keeping strong accuracy.
Chetcuti et al. (2019) found motor demand, not social warmth, drove imitation errors. CAMI’s body-score metric now gives you an easy way to track that motor demand in real time.
Why it matters
You can now measure motor imitation with the phone in your pocket. No markers, no 3-D camera, no grad student coding video overnight. Run a quick baseline, check progress weekly, or screen new referrals during intake. The tool is free, fast, and ready for Monday morning.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Download OpenPose, film a 30-second imitation clip, and compare the joint-angle report to your checklist score.
02At a glance
03Original abstract
BACKGROUND: Motor imitation difficulties are pervasive in children with Autism Spectrum Disorder (ASD). Previous research demonstrated the validity and reliability of an algorithm called Computerized Assessment of Motor Imitation (CAMI) using 3D depth cameras. However, incorporating CAMI into serious games and making it accessible in clinic and home settings requires a more scalable approach that uses "off-the-shelf" 2D cameras. METHOD: In a brief (one-minute) task, children (23 ASD, 17 typically developing [TD]) imitated a model's dance movements while simultaneously being recorded using Kinect Xbox motion tracking technology (Kinect 3D) and a single 2D camera. Pose-estimation software (OpenPose 2D) was used on the 2D camera video to fit a skeleton to the imitating child. Motor imitation scores computed from the fully automated OpenPose 2D CAMI method were compared to scores computed from the Kinect 3D CAMI and Human Observation Coding (HOC) methods. RESULTS: Motor imitation scores obtained from the OpenPose 2D CAMI method were significantly correlated with scores obtained from the Kinect 3D CAMI method (r 40 = 0.82, p < 0.001) and the HOC method (r 40 = 0.80, p < 0.001). Both 2D and 3D CAMI methods showed better discriminative ability than the HOC, with the Kinect 3D CAMI method outperforming the OpenPose 2D CAMI method (area under ROC curve (AUC): AUCHOC = 0.799, AUC2D-CAMI = 0.876, AUC3D-CAMI = 0.94). Finally, all motor imitation scores were significantly associated with the social-communication impairment (all p ≤ 0.003). CONCLUSIONS: This pilot-study demonstrated that motor imitation can be automatically quantified using a single 2D camera.
Research in autism spectrum disorders, 2021 · doi:10.1109/TNSRE.2015.2475724