PCPP: A MATLAB application for abnormal infant movement detection from video

Abstract PCPP is an application developed in MATLAB, for the detection of abnormal infant movements associated with cerebral palsy. This system uses 2D skeletal data extracted from videos, and consists a full pipeline providing pre-processing, normalization, feature extraction classification. Evaluation metrics, such as accuracy, sensitivity, specificity, F1 score Matthews Correlation Coefficient (MCC), are computed to facilitate assessment performance allow comparison other methods literature. These evaluations conducted on MINI-RGBD RVI-38 datasets using code provided.