Recurrent Convolutional Neural Network Regression for Continuous Pain Intensity Estimation in Video

TL;DR

This paper introduces a real-time recurrent convolutional neural network framework for continuous pain intensity estimation from video, improving stability and accuracy over traditional static methods.

Contribution

It presents a novel end-to-end regression model that leverages historical frame data for more stable and accurate pain intensity estimation in videos.

Findings

Achieves promising accuracy on UNBC-McMaster database.

Provides real-time performance suitable for healthcare applications.

Outperforms static frame-based methods in stability and consistency.

Abstract

Automatic pain intensity estimation possesses a significant position in healthcare and medical field. Traditional static methods prefer to extract features from frames separately in a video, which would result in unstable changes and peaks among adjacent frames. To overcome this problem, we propose a real-time regression framework based on the recurrent convolutional neural network for automatic frame-level pain intensity estimation. Given vector sequences of AAM-warped facial images, we used a sliding-window strategy to obtain fixed-length input samples for the recurrent network. We then carefully design the architecture of the recurrent network to output continuous-valued pain intensity. The proposed end-to-end pain intensity regression framework can predict the pain intensity of each frame by considering a sufficiently large historical frames while limiting the scale of the parameters within the model. Our method achieves promising results regarding both accuracy and running speed on the published UNBC-McMaster Shoulder Pain Expression Archive Database.