Visual saliency model for robot cameras

TitleVisual saliency model for robot cameras
Publication TypeConference Paper
Year of Publication2008
AuthorsButko, N, Zhang, L, Cottrell, G, Movellan, J
Conference NameIEEE International Conference on Robotics and Automation, 2008. ICRA 2008
Date Published05/2008
Conference LocationPasadena, CA
ISBN Number978-1-4244-1646-2
Accession Number10014787
KeywordsApplication software, approximation theory, Bayes methods, Bayesian methods, Bayesian model, camera control, Cameras, Central Processing Unit, Computational efficiency, Computational modeling, Explosions, fast approximation, human visual attention, Humans, Open loop systems, robot cameras, robot vision, Robot vision systems, robotic application, task free conditions, visual saliency model

Recent years have seen an explosion of research on the computational modeling of human visual attention in task free conditions, i.e., given an image predict where humans are likely to look. This area of research could potentially provide general purpose mechanisms for robots to orient their cameras. One difficulty is that most current models of visual saliency are computationally very expensive and not suited to real time implementations needed for robotic applications. Here we propose a fast approximation to a Bayesian model of visual saliency recently proposed in the literature. The approximation can run in real time on current computers at very little computational cost, leaving plenty of CPU cycles for other tasks. We empirically evaluate the saliency model in the domain of controlling saccades of a camera in social robotics situations. The goal was to orient a camera as quickly as possible toward human faces. We found that this simple general purpose saliency model doubled the success rate of the camera: it captured images of people 70% of the time, when compared to a 35% success rate when the camera was controlled using an open-loop scheme. After 3 saccades (camera movements), the robot was 96% likely to capture at least one person. The results suggest that visual saliency models may provide a useful front end for camera control in robotics applications.