| 摘要 |
An adaptive cross-camera cross-target tracking method and system, the method comprising: fixing a size of a tracking<b/>window and using a pre-established tracking model to obtain the location of a target object of a current video frame, transforming the size of the tracking widow at the obtained location, using the tracking model to obtain a dimension of the target object, and updating the tracking model online according to the obtained dimension of the target object; according to the updated tracking model, performing a log-polar transformation for an image of the target object of the current video frame, performing a Gaussian mixture model process on the log-polar transformed image of the target object, measuring a center offset and transformation degree of the target object, and determining whether the target object has disappeared. |
