| Summary: | 碩士 === 國立成功大學 === 資訊工程學系碩博士班 === 101 === Background subtraction is widely used in multimedia applications, such as traffic monitoring, video surveillance, and object tracking. Because background subtraction methods have long been the subject of research, several methods which have different advantages in different applications, have been proposed. The advent of cloud computing has made possible the combination of various background subtraction techniques and the processing of large amounts of images; therefore, developing an integrated algorithm for background subtraction is necessary.
In this thesis, an integrated algorithm for background subtraction is implemented and analyzed. The proposed AdaBoost algorithm combined weak classifiers: pixel-based background subtraction methods, and block-based background subtraction methods. After training, the program adjusts the weight of each weak classifier. The program is accelerated using Hadoop cloud-computing architecture. Using a MapReduce framework, this work can be parallelized on many computers, thus reducing computing time. When the program completes its task, the user can see the combined results on the user interface and can subsequently choose the preferred result. The system can obtain user feedback and tune the combination mechanism.
|
|---|
