| Summary: | 碩士 === 國立交通大學 === 電控工程研究所 === 103 === In this thesis, we implement an automatic human tracking system that combines face detection and upper outer garment tracking in the light changing environment. Face detection can detect each person in the screen; upper outer garment tracking can track each person’s location by upper outer garment’s color.
We use Haar cascade classifier and skin color detection for human face detection, which can locate the human face region correctly. Then, relative position with respect to a face founded will be used to locate one’s body region, and in the sequel hue-saturation color histogram model for upper garment is generated. We use CamShift algorithm to track person’s position. For better accuracy, we check the light change for each image frame and rebuild color model to adapt to the large enough light change in the environment.
|
|---|
