Least-Squares Estimation of Transformation Parameters Between Two Point Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape and motion from image streams under orthography: a factorization method
International Journal of Computer Vision
Performance of optical flow techniques
International Journal of Computer Vision
Euclidean Shape and Motion from Multiple Perspective Views by Affine Iterations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer Vision and Image Understanding
IEEE Transactions on Pattern Analysis and Machine Intelligence
3D Reconstruction of the Operating Field for Image Overlay in 3D-Endoscopic Surgery
ISAR '01 Proceedings of the IEEE and ACM International Symposium on Augmented Reality (ISAR'01)
Robust 3D Reconstruction with Outliers Using RANSAC Based Singular Value Decomposition
IEICE - Transactions on Information and Systems
Optical Biopsy Mapping for Minimally Invasive Cancer Screening
MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part I
2D/3D registration of a preoperative model with endoscopic video using colour-consistency
AE-CAI'11 Proceedings of the 6th international conference on Augmented Environments for Computer-Assisted Interventions
| Hi-index | 0.00 |
In this study, we introduce a software pipeline to track feature points across endoscopic video frames. It deals with the common problems of low contrast and uneven illumination that afflict endoscopic imaging. In particular, irregular feature trajectories are eliminated to improve quality. The structure of soft tissue is determined by an iterative factorization method based on collection of tracked features. A shape updating mechanism is proposed in order to yield scale-invariant structures. Experimental results show that the tracking method produced good tracking performance and increased the number of tracked feature trajectories. The real scale and structure of the target scene was successfully estimated, and the recovered structure is more accuracy than the conventional method.