| 主权项 |
1. A method for optimizing video-based tracking of an object of interest, comprising:
acquiring, from a fixed position video camera having a wide-view lens, a video of a regularized motion environment comprising a plurality of video frames, the regularized motion environment having a stationary scene background; retrieving a set of rules of the regularized motion environment, the rules governing movement of an object within the regularized motion environment including at least two of a speed limit, a size restriction, a traffic flow, and/or a location in the regularized motion environment wherein an object of interest can be located or a location in the regularized motion environment wherein an object of interest cannot be located; detecting an initial instance of at least one object of interest in the plurality of video frames including a location thereof in accordance with the retrieved set of regularized motion environment rules; estimating both an expected size and an expected orientation of the at least one object of interest as a function of the location and a geometric mapping function of the wide-view lens of the fixed position video camera acquiring the video; and localizing the at least one object of interest in at least one subsequent video frame responsive to the estimated size and estimated orientation, wherein at least one of the acquiring, detecting, generating, determining, and localizing is performed by a computer processor. |
