Simultaneous shape and camera-projector parameter estimation for 3D endoscopic system using CNN-based grid-oneshot scan
Simultaneous shape and camera-projector parameter estimation for 3D endoscopic system using CNN-based grid-oneshot scan
复制标题
DOI：
10.1049/htl.2019.0070
复制
发表时间：
2019-12-01
影响因子：
2.1
通讯作者：
Kawasaki, Hiroshi
中科院分区：
文献类型：
--
作者：
Furukawa, Ryo;Nagamatsu, Genki;Kawasaki, Hiroshi
对于有效的原位内窥镜诊断和治疗，测量息肉大小是重要的。为此，已经研究了3D内窥镜系统。在这样的系统中，主动立体声技术，它投影一个特殊的模式，其中每个特征被编码，是一个有前途的方法，因为简单和高精度。然而，这种方法的以前的作品有问题。首先，三维重建的质量取决于从内窥镜摄像机捕获的图像中提取特征的稳定性。第二，由于图案投影面积有限，重建区域相对较小。在这封信中，作者提出了一种基于学习的技术，使用卷积神经网络来解决第一个问题，并提出了一种扩展的光束法平差技术，将多个形状集成到一个一致的单一形状中，以解决第二个问题。与以前的技术相比，所提出的技术的有效性进行了实验评估。
For effective in situ endoscopic diagnosis and treatment, measurement of polyp sizes is important. For this purpose, 3D endoscopic systems have been researched. Among such systems, an active stereo technique, which projects a special pattern wherein each feature is coded, is a promising approach because of simplicity and high precision. However, previous works of this approach have problems. First, the quality of 3D reconstruction depended on the stabilities of feature extraction from the images captured by the endoscope camera. Second, due to the limited pattern projection area, the reconstructed region was relatively small. In this Letter, the authors propose a learning-based technique using convolutional neural networks to solve the first problem and an extended bundle adjustment technique, which integrates multiple shapes into a consistent single shape, to address the second. The effectiveness of the proposed techniques compared to previous techniques was evaluated experimentally.