摘要
给出连续图像帧差分和二次帧差分改进的图像HSI差分模型,采用自适应分割算法能在任意条件下自动提取运动目标区域。定义运动目标的特征分析和计算,通过特征匹配判断,识别所需识别目标的区域。实验结果表明该方法是有效的,且有良好的鲁棒性。
It has been focused in compute vision research fields. A improved HSI image difference model based on sequences image difference and second image difference is presented. An adaptive segmentation method is adopted to extract the moving objects in any background. The feature analysis and compute of moving objects are definited. The area of objects are recognized by the feature matched. Experimental results show that the proposed approach is effective and robust.
出处
《计算技术与自动化》
2007年第3期78-80,99,共4页
Computing Technology and Automation
关键词
目标检测与识别
HSI差分模型
自适应分割
特征匹配
object detection and recognition
HSI image difference model
self-adaptive segmentation
feature matching
