发明名称 |
Systems and methods for tracking with discrete texture traces |
摘要 |
An active set of discrete texture traces to a target point is determined in a first video frame and is applied to a second video frame to detect the target location in a second video frame. An estimate is made of the target location in the second video frame. A score map is computed of an area of locations. A location with a highest score in the score map is the new target location. If a threshold value is not met the active set of texture traces is stored. A score map for each of stored active sets is computed to determine the target location. If no score meets the threshold the target location in a previous video frame is made the current target location and a new active set of discrete texture traces is determined. Systems that implement the steps of the methods are also provided. |
申请公布号 |
US9014486(B2) |
申请公布日期 |
2015.04.21 |
申请号 |
US201213682796 |
申请日期 |
2012.11.21 |
申请人 |
Siemens Aktiengesellschaft |
发明人 |
Ernst Jan;Singh Maneesh Kumar |
分类号 |
G06K9/00;H04N5/225;G06K9/62;G06K9/46;G06T7/20 |
主分类号 |
G06K9/00 |
代理机构 |
|
代理人 |
|
主权项 |
1. A method for tracking an image of an object in a plurality of video frames, comprising:
a processor determining in a first video frame in the plurality of video frames a set of discrete texture traces to a target location in a patch in the object in the first video frame to establish a reference model, the patch being generated by the set of discrete texture traces that connect to the target location from locations in a finite support region defined by a discrete trace length of a predetermined length n and a neighborhood relation scale and each discrete texture trace is a finite sequence of n quantized descriptions, wherein each quantized description includes a quantized description of a first location in the finite support region and a quantized description of a relation between the first location and a second location in the finite support region; and the processor detecting the target location in a second video frame by maximizing a score based on the reference model. |
地址 |
Munich DE |