对比度阈值自适应的SIFT图像拼接算法  

Image Mosaic Based on Contract Threshold Adaptive SIFT Algorithm

作　　者：李尊 申小萌 苗同军 

机构地区：[1]新乡学院物理与电子工程学院,河南新乡453000

出　　处：《红外技术》2017年第10期946-950,共5页Infrared Technology

基　　金：河南省高等学校重点科研项目(17A470013)

摘　　要：图像拼接技术主要由3部分构成:采集、匹配和融合,其中匹配最为关键,决定拼接质量。针对SIFT图像拼接算法的特征点数目局部过高或过低情况,采用对比度阈值自适应的SIFT图像拼接算法,可得到合理数目的特征点。此方法保证特征点数目在150~300之间,过高或过低时,可自适应调节数目,进行有效控制。实验证明:改进的算法保证拼接效果的基础上,提高运算效率,具有实用价值。An image mosaic consists of three parts： acquisition, image-matching, and image fusion. Image-matching is the key part, determining the image mosaic quality. For cases where in the feature point number is too high or too low, we propose an image mosaic based on the contract threshold adaptive SIFT algorithm. The proposed method adaptively and effectively controls the feature point number when it is too high or too low, ensuring a value between 150 and 300. Experimental results show that this method, which has practical value, can improve computational efficiency based on mosaic effects.

关 键 词：图像拼接 SIFT算法 对比度阈值 自适应 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]