Adaptive Object Detection Using Fuzzy System for Environment Change

• Main Authors: Cheng-Yu Weng, 翁正宇
• Other Authors: Shuenn-Shyang Wang
• Format: Others
• Language: en_US
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/02499255369925203153

碩士 === 大同大學 === 通訊工程研究所 === 101 === Background subtraction is an essential technique for automatic video analysis. To improve the accuracy of background subtraction in the dark environment and the light illumination changing environment, a new algorithm of adaptive background building and foreground detection based on fuzzy system has been proposed in the thesis. We apply fuzzy rules to classify the input image to 5 classes and then set the appropriate image weight for each class. In this way, the image information between bright and dusky environment will do not interfere with each other. The proposed texture feature is based on local binary pattern (LBP), while the color feature is represented by HSI color space. The experimental results show that the proposed algorithm can correctly detect the foreground in dark environment and light illumination changing environment.