Method and system for automatic object detection and subsequent object tracking in accordance with the object shape

Patent type: Priority Patent Application

Patent number: WO002011023348A1

Registration date: Aug. 22, 2010


Abstract

A large number of tracking methods, in addition to further developments for object tracking, including tracking the object shape, are known. In this case, however, the orientation is calculated only within the image plane and therefore only 2-dimensionally, so the object shape cannot be matched to the actual movement of the object in three-dimensional space. In order to specify a method for automatic object detection and subsequent object tracking in digital video systems having at least one camera (K) for recording and transmitting video sequences, as well as further processing or evaluation of video data, which in addition to the localization and tracking of moving objects, is also capable of determining the object shape and thus of permitting the calculation of the orientation of an object in space with the existing measured data, patent claim 1 provides for an object detection algorithm based on a Gaussian mixture model GMM and expanded object tracking based on Mean-Shift to be combined with each other in the object detection. The object detection is expanded in accordance with a model of the background by improved removal of shadows, the binary mask (BM) generated in this way is used to create an asymmetric filter core, and then the actual algorithm for the shape-adaptive object tracking, expanded by a segmentation step for adapting the shape, is initialized, and therefore a determination at least of the object shape or object contour or the orientation of the object in space is made possible. The invention falls in the area of automatic object detection and subsequent object tracking.

Invention

Patent holder(s)