Eye movement predictions on natural videos

We analyze the predictability of eye movements of observers viewing dynamic scenes. We first assess the effectiveness of model-based prediction. The model is divided into inter-saccade prediction, which is based on a limited history of attended locations, and saccade prediction, which is based on a list of salient locations. The quality of the predictions and of the underlying saliency maps is tested on a large set of eye movement data recorded on high-resolution real-world video sequences. In addition, frequently fixated locations are used to predict individual eye movements to obtain a reference for model-based predictions. Key words: Eye movement prediction; saccade prediction; scan-path; saliency maps

• Type: Journal
• Year: 2006
• Where: IJON
• Authors: Martin Böhme, Michael Dorr, Christopher Krause, Thomas Martinetz, Erhardt Barth
• Keywords: Eye Movement, IJON 2006, Model-based Predictions, Prediction