| Tracking refers to estimating target’s trajectory in the subsequent image sequences by a given initial state of target in the first frame(e.g.position and scope)from successive image sequence.Object tracking is a hot topic in computer vision.Thanks to the booming of the very high resolution(VHR)remote sensing techniques,it is now possible to track targets of interests in satellite videos.However,since the targets in the satellite videos are usually too small compared with the entire image,and too similar with the background,most state-of-the-art natural video object tracking algorithms failed to track the target in satellite videos with a satisfactory accuracy.Optical flow method can extract object movement information by calculating optical vectors of slightly moving pixels.Background subtraction can segment the target from the background by background modeling.Due to the fact that optical flow and background subtraction show a great potential to detect the slight movement of the targets,we proposed a multi-frame optical flow tracker(MOFT)and a background subtraction satellite tracker(BSST)for object tracking from satellite videos.(1)In the MOFT algorithm,the Lucas-Kanade optical flow method was fused with the HSV color system and the integral image to track the targets in the satellite videos,while multi-frame difference method was utilized in the MOFT algorithm for a better interpretation.(2)In the BSST algorithm,the background subtraction method based on Gaussian mixture model and the integral image are combined,and multi-frame technology is used for improving tracking performance.The experiments with five VHR remote sensing satellite video datasets indicate that compared with state-of-the-art object tracking algorithms,the proposed methods can track the target more accurately.Between the proposed algorithms,the background subtraction satellite tracker(BSST)can achieve higher accuracy than multi-frame optical flow trakcer(MOFT). |
PDF Full Text Request