Appearance-based gaze estimation using deep features and random forest regression

Conventional appearance-based gaze estimation methods employ local or global features as eye gaze appearance descriptor. But these methods don’t work well under natural light with free head movement. To solve this problem, we present an appearance-based gaze estimation method using deep feature representation and feature forest regression. The deep feature is learned through hierarchical extraction of deep Convolutional Neural Network (CNN). And random forest regression with cluster-to-classify node splitting rules is used to take advantage of data distribution in sparse feature space. Experimental results demonstrate that the deep feature has a better performance than local features on calibrated gaze regression. The combination of deep features and random forest regression provides an effective solution for gaze estimation in a natural environment.