摘要
内窥镜被广泛用于器官和体腔内部的诊断成像,尽管采集到的内窥镜视频中包含着丰富的信息,但是由于内窥镜的成像范围受到探头太小的限制,图像的放大倍数与视野范围不能兼得,且视频不能将个体二维图像与三维器官形态关联起来,大部分具有巨大数据潜力的内窥镜视频仅用于医师实时指导,并在收集后丢弃。提出基于序列内窥镜视频图像的膀胱三维场景重建的方法。先提取前后两幅序列图像中相对应的多个特征点,基于特征点采用运动恢复结构算法计算得到膀胱模型三维点云。然后,采用泊松曲面重建算法对各三维点进行网格化,并完成场景的三维重建。实验结果表明所提出的算法是可行的。
Endoscopes are widely used for diagnostic imaging inside organs and body cavities.Although the acquired endoscopic video contains rich of information,the scope of the endoscope is limited by the small size of the probe,image magnification and field of vision cannot be obtained simultaneously,and the video cannot associate individual two-dimensional images with three dimensional organ morphology.Most endoscopic video with huge potential data is only used by doctors for real-time guidance and discarded after collection.A three dimensional reconstruction method of bladder based was proposed on serial endoscopic video images.Firstly,the corresponding multiple feature points in two sequence images were extracted before and after the three dimensional point cloud of the bladder model was calculated based on the feature points using the motion recovery structure algorithm.Then,the three-dimensional points were meshed with the Poisson surface reconstruction algorithm,and the three-dimensional reconstruction of the scene was completed.Experimental results show that the proposed algorithm is feasible.
作者
衡怡伶
王玉
王明泉
路晓冬
HENG Yi-ling;WANG Yu;WANG Ming-quan;LU Xiao-dong(School of Information and Communication Engineering,North University of China,Taiyuan 030051,China)
出处
《科学技术与工程》
北大核心
2018年第27期152-156,共5页
Science Technology and Engineering
基金
国家自然科学基金(61171177)
国家重大科学仪器设备开发专项(2013YQ240803)
山西省中青年拔尖人才项目
山西省研究生教育创新资助
关键词
膀胱内窥镜图像
运动恢复结构
网格模型
三维场景重建
bladder endoscopic image
structure from motion
mesh model
three-dimensional scene reconstruction