Font Size: a A A

Research On Tracking Algorithms Of Moving Bojects In Video Sequence

Posted on:2009-07-22Degree:MasterType:Thesis
Country:ChinaCandidate:X W TianFull Text:PDF
GTID:2178360242975433Subject:Computer software and theory
Abstract/Summary:PDF Full Text Request
For a visual tracking system, the core includes two parts: one part is moving object detection and extraction, and the other is moving object tracking. Moving object extraction is the most important part.For moving object detection,three methods,including'differential between adjacent frames','background subtraction'and'optical flow',are discussed. According to the characteristic of video images,the thesis studies the tracking algorithm'differential between adjacent frames'and'background subtraction',and proposed a improved method based on the first two results. It makes use of strong correlations in serial images. For the first method,Pre-processing such as filtering,noise reduction and smoothing must be made before differencing,then differencing method on two sequential frames is implemented. And Using threshold value to transform the gray level picture into two bleak-and-white value picture, then images including moving information are filtered by morphological filtering to eliminate background noise,lastly the object contour is abstracted. It is high-speed.For moving object tracking,the accuracy and stability of objects tracking depend on moving objects tracking algorithm to great extent. In the paper, using based on eight-connection-edge tracking algorithms get the object edge and using the labeling algorithms label each object. Through obtain the object's histogram characteristic,boundary characteristic and veins characteristic to distinguish from multi-objects. Researched two kind of calculating object shape-center methods. .By using of Visual C++ Programming and the law of Projection, The object's position is computed according to Formula method The results of experiments indicate that the Proposed algorithms are effective.
Keywords/Search Tags:object tracking, threshold segmentation, morphological filtering, inter-frame difference
PDF Full Text Request
Related items