Fusion of spatial and visual information for object tracking on iPhone

In this work, a novel object tracking system is proposed which tracks visual objects on Apple iPhone 4 platform in real-time. The system utilizes the color space of the frames provided by iPhone camera, in parallel with the motion data provided by iPhone motion sensors, to cancel the effect of iPhone movements during matching different candidate tracks. The proposed system also adapts to changes in target appearance and size, thus leading to a robust tracking. Several experiments conducted on actual video sequences are used to illustrate the functionality of the proposed approach.