Using Photo-Consistency to Register 2D Optical Images of the Human Face to a 3D Surface Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
Towards 3D Reconstruction of Endoscope Images using Shape from Shading
SIBGRAPI '00 Proceedings of the 13th Brazilian Symposium on Computer Graphics and Image Processing
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
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)
Parallel Tracking and Mapping for Small AR Workspaces
ISMAR '07 Proceedings of the 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality
Endoscopic Feature Tracking and Scale-Invariant Estimation of Soft-Tissue Structures
IEICE - Transactions on Information and Systems
A probabilistic framework for tracking deformable soft tissue in minimally invasive surgery
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Real-time stereo reconstruction in robotically assisted minimally invasive surgery
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Simultaneous stereoscope localization and soft-tissue mapping for minimal invasive surgery
MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
| Hi-index | 0.00 |
Image-guided surgery needs an effective and efficient registration between 2D video images of the surgical scene and a preoperative model of a patient from 3D MRI or CT scans. Such an alignment process is difficult due to the lack of robustly trackable features on the operative surface as well as tissue deformation and specularity. In this paper, we propose a novel approach to perform the registration using PTAM camera tracking and colour-consistency. PTAM provides a set of video images with the corresponding camera positions. Registration of the 3D model to the video images can then be achieved by maximization of colour-consistency between all 2D pixels corresponding to a given 3D surface point. An improved algorithm for calculation of visible surface points is provided. It is hoped that PTAM camera tracking using a reduced set of points can be combined with colour-consistency to provide a robust registration. A ground truth simulation test bed has been developed for validating the proposed algorithm and empirical studies have shown that the approach is feasible, with ground truth simulation data providing a capture range of ±9mm/° with a TRE less than 2mm. Our intended application is robot-assisted laparoscopic prostatectomy.