Adaptive ACM and ASM based Tracking System

• Main Authors: Lou,Hsin-Ran, 羅欣然
• Other Authors: Sheu,Hsin-Teng
• Format: Others
• Language: zh-TW
• Published: 2004
• Online Access: http://ndltd.ncl.edu.tw/handle/42655493395696834015

碩士 === 國立臺灣科技大學 === 電機工程系 === 92 === With the rapid progress in information technology, computer is becoming more and more powerful, applications of digital image processing and machine vision are getting popular. An important field in machine vision nowadays is tracking which is a crucial function for navigation on autopilot. Our research develop a tracking system that uses Active Contour Models(ACM) with adaptable search direction and search range combined with Active Shape Models(ASM).We test our method against various objects including people and car etc. under a variety of environments such as low contrast image, complicated surrounding and bumpy road surface on which the observer car moves. Experiments indicate that, with the introduction of adaptive search direction and search range, the tracking is not only converging much faster but also robust from the interferences around the surroundings of the object to be tracked.