Provided is an image processing device including an eye-gaze direction detection unit configured to detect an eye-gaze direction of a user toward an image, an estimation unit configured to estimate a gaze area in the image on the basis of the eye-gaze direction and the image, the eye-gaze direction being detected by the eye-gaze direction detection unit, a chased object detection unit configured to detect a chased object being eye-chased by the user in the image, on the basis of the time-series gaze areas estimated by the estimation unit, a tracking unit configured to search for and track the chased object detected by the chased object detection unit, and an image control unit configured to control an image of the chased object tracked by the tracking unit.