发明名称 Fast Histogram-Based Object Tracking
摘要 Systems, methods, and computer readable media to rapidly identify and track an arbitrary sized object through a temporal sequence of frames is described. The object being tracked may initially be identified via a specified or otherwise known region-of-interest (ROI). A portion of that ROI can be used to generate an initial or reference histogram and luminosity measure, metrics that may be used to identify the ROI in a subsequent frame. For a frame subsequent to the initial or reference frame, a series of putative ROIs (each having its own location and size) may be identified and the “best” of the identified ROIs selected. As used here, the term “best” simply means that the more similar two frames' histograms and luminosity measures are, the better one is with respect to the other.
申请公布号 US2016358340(A1) 申请公布日期 2016.12.08
申请号 US201514869732 申请日期 2015.09.29
申请人 Apple Inc. 发明人 Zhou Jianping;Anneheim Geoffrey T.;Li Xiaoxing;Olson Benjamin M.
分类号 G06T7/20;G06T7/00;G06K9/52;H04N5/225;G06T7/60;G06K9/46;H04N7/18 主分类号 G06T7/20
代理机构 代理人
主权项 1. An object tracking method, comprising: receiving an initial frame from a temporal sequence of frames, the initial frame having an initial region-of-interest (ROI), the initial ROI having an initial location and an initial size; determining an initial histogram and an initial luminance measure based on the initial ROI; receiving a first frame from the temporal sequence of frames, the first frame arriving later in the temporal sequence of frames than the initial frame; determining a plurality of putative ROIs for the first frame, each putative ROI based on the initial histogram and the initial luminance measure; determining a plurality of quality metric values, each quality metric value corresponding to a different one of the putative ROIs; selecting one of the putative ROIs as a first ROI for the first frame based on the quality metric values; obtaining a first histogram and a first luminance measure based on the first ROI; receiving a next frame from the temporal sequence of frames, the next frame arriving later in the temporal sequence of frames than the first frame; and determining a next ROI of the next frame based on the first ROI, the first histogram, and the first luminance measure.
地址 Cupertino CA US