Extending 3D Body Pose Estimation for Robotic-Assistive Therapies of Autistic Children

Robotic-assistive therapy has demonstrated very encouraging results for children with Autism. Accurate estimation of the child's pose is essential both for human-robot interaction and for therapy assessment purposes. Non-intrusive methods are the sole viable option since these children are sensitive to touch. While depth cameras have been used extensively, existing methods face two major limitations: (i) they are usually trained with adult-only data and do not correctly estimate a child's pose, and (ii) they fail in scenarios with a high number of occlusions. Therefore, our goal was to develop a 3D pose estimator for children, by adapting an existing state-of-the-art 3D body modelling method and incorporating a linear regression model to fine-tune one of its inputs (the focal length), thereby correcting the pose of children's 3D meshes. In controlled environments, our method maintains an error under 0.3m, which is deemed acceptable for this application. Additionally, it achieves lower error rates than current state-of-the-art methods while being more computationally efficient in terms of processed frames per second. In real-world scenarios, the proposed model performs comparably to a Kinect depth camera and successfully estimates 3D body poses in a significantly higher number of frames.