Towards human-level performance on automatic pose estimation of infant spontaneous movements

Abstract

Assessment of spontaneous movements can predict the long-term developmental outcomes in highrisk infants. In order to develop algorithms for automated prediction of later function based on early motor repertoire, high-precision tracking of segments and joints are required. Four types of convolutional neural networks were investigated on a novel infant pose dataset, covering the large variation in 1 424 videos from a clinical international community. The precision level of the networks was evaluated as the deviation between the estimated keypoint positions and human expert annotations. The computational efficiency was also assessed to determine the feasibility of the neural networks in clinical practice. The study shows that the precision of the best performing infant motion tracker is similar to the inter-rater error of human experts, while still operating efficiently. In conclusion, the proposed tracking of infant movements can pave the way for early detection of motor disorders in children with perinatal brain injuries by quantifying infant movements from video recordings with human precision.

Deep-Learning for Automated Markerless Tracking of Infants General Movements

“…Automated motion capture offers a low-cost, practical alternative to track and analyze anatomical movements effectively. Automated neonatal GM tracking and analysis has been explored by different research teams using various techniques [13], including utilization of wearable biotech [14,15], 3D motion capture [16,17], wearable accelerometers [18], 3D RGB-D camera recordings [19], and conventional video recordings [20][21][22][23][24][25], and another deep-learning markerless pose estimation algorithm [30]. Commercial 3D motion capture systems (e.g., Vicon [26]) provide goldstandard spatial and temporal accuracies under laboratory settings but are impractically expensive and immobile.…”