Tracking a moving target of interests from a space-borne satellite video is really a difficulty, since the target usually occupies only a few pixels in each frame of satellite video. Even it is a long train. Most state-of-the-art tracking algorithms mainly rely on luminance or color features, failing to handle this video tracking problem due to the extremely inadequate quality of targets features. To overcome this difficulty, we propose a velocity correlation filter (VCF), employing velocity feature and inertia mechanism to construct a kernel correlation filter for satellite video targets tracking. The velocity feature has a high discriminative ability to detect moving targets in satellite videos and the inertia mechanism can prevent model drift adaptively. Experimental results on three real satellite video datasets show our proposed approach outperforms state-of-the-art tracking methods with a more than 100 frames per second. © 2018 IEEE.