符号M阵列面结构光多分辨解码方法研究  

Array of symbols M noodle structured light image decoding method of multiresolution

作　　者：喻擎苍[1] 冯海明[1] 徐玉芳 

机构地区：[1]浙江理工大学,浙江杭州310018 [2]西安工程技术学院,陕西西安710065

出　　处：《计算机工程与设计》2010年第5期1100-1103,共4页Computer Engineering and Design

基　　金：国家自然科学基金项目(50575211)

摘　　要：研究了符号M阵列面结构光图像的多分辨解码方法,结合基于形心特征的标准符号的分类和识别,着重提出了多分辨解码过程中未识别区域的提取方法,并结合实际问题提出了图像标记和符号识别的特殊处理方法,如分割符号间隔、填充十字型区域等,进而实现照度不均面结构光图像解码率最大化的目的。同时该解码方法也大大提高了照度不均模式图像解码的执行效率。The array of symbols M noodle structured light image of the multi-resolution decoding method is studied, combined with the characteristics of a standard symbol classification and identification which based on the heart-shaped, the region which does not identify extraction method is focused on during a multi-resolution decoding process, and then combined with practical problems raised image signs and symbols, the specific treatment methods is identified, such as partition symbol interval; and so filled with cross-shaped region, and then realize the uneven illumination noodle structured light image decoding rate maximization purposes. At the same time, the illumination of the uneven pattern of the implementation of image decoding is improved efficiencily by the decoding method.

关 键 词：结构光 照度 符号 解码 多分辨 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]