摘要
在实现图像拼接过程中,ORB算法能够较好地解决运行实时性问题,但是在机器人与实际环境之间的距离变化,导致图像尺寸发生改变,或运动过程中抖动导致的图像模糊时,该算法匹配效率和准确度较差。针对该问题,提出一种改进的ORB特征提取与匹配算法。首先提取具有尺度不变性的特征点,然后利用汉明距离对特征点进行分类、匹配,最后利用改进的RANSAC算法,有效消除误匹配点。实验结果表明:改进算法在提升了匹配的效率和准确度的同时可以满足实时性的要求。
In the process of realizing image Mosaic,ORB algorithm can solve the real-time problem of operation well. However,due to the distance change between the robot and the actual environment,results in change of image size or the image is blurred jittering in the process of movement,the matching efficiency and accuracy of algorithm are poor. To solve this problem,an improved ORB feature extraction and matching algorithm is proposed. Firstly,feature points with scale invariance are extracted,then the feature points are classified and matched by Hamming distance,and finally,the mismatched points are effectively eliminated by the improved RANSAC algorithm.Experimental results show that the improved algorithm can improve the matching efficiency and accuracy and meet the real-time requirements,at the same time.
作者
董永峰
雷晓辉
董瑶
李炜
杨琛
张泽伟
DONG Yongfeng;LEI Xiaohui;DONG Yao;LI Wei;YANG Chen;ZHANG Zewei(School of Artificial Intelligence,Hebei University of Technology,Tianjin 300401,China;Hebei Province Key Laboratory of Big Data Calculation,Tianjin 300401,China)
出处
《传感器与微系统》
CSCD
2020年第4期59-62,共4页
Transducer and Microsystem Technologies
基金
天津市科技计划资助项目(14ZCDGSF00124)
天津市自然科学基金资助项目(16JCYBJC15600)。
