Conference Paper

Reconstruction of Image Structure in Presence of Specular Reflections

DOI: 10.1007/3-540-45404-7_8 Conference: Pattern Recognition, 23rd DAGM-Symposium, Munich, Germany, September 12-14, 2001, Proceedings
Source: DBLP


This paper deals with the reconstruction of original image structure in the presence of local disturbances such as specular re∞ec- tions. It presents two novel schemes for their elimination with respect to the local image structure: an e-cient linear interpolation scheme and an iterative fllling-in approach employing anisotropic difiusion. The al- gorithms are evaluated on images of the heart surface and are suited to support tracking of natural landmarks on the beating heart.

Full-text preview

Available from:
  • Source
    • "Reconstruction of the underlying structure by detection of specularities was proposed by (Groger et al., 2001), based on structural tensor interpolation and a diffusion scheme. The method uses a greyscale value as a threshold value to detect the specular reflection and the filling-in information from the neighbouring regions. "

    Preview · Article · Jul 2013 · American Journal of Applied Sciences
  • Source
    • "Another approach for dense 3D depth recovery was proposed by Stoyanov et al. [43] where a piecewise bilinear mapping is applied for modeling soft-tissue deformation. A challenge when using these methods is the handling of specular highlights which requires additional preprocessing [14]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Minimally invasive robotic surgery has gained wide acceptance recently. Computer-aided features to assist the surgeon during these interventions may help to develop safer, faster, and more accurate procedures. Especially physiological motion compensation of the beating heart and online soft tissue modelling are promising features that were developed recently. This paper presents the integration of these new features into the minimally invasive robotic surgery platform MiroSurge. A central aim of this research platform is to enable evaluation and comparison of new functionalities for minimally invasive robotic surgery. The system structure of MiroSurge is presented as well as the interfaces for the new functionalities. Some details about the modules for motion tracking and for soft tissue simulation are given. Results are shown with an experimental setup that includes a heart motion simulator and dedicated silicone organ models. Both features are integrated seamlessly and work reliably in the chosen setup. The MiroSurge platform thus shows the potential to provide valuable results in evaluating new functionalities for minimally invasive robotic surgery.
    Preview · Article · Jan 2011 · Applied Bionics and Biomechanics
  • Source
    • "For calibrating the surgical camera, it is typical to use an offline procedure before the imaging device is inserted into the patient. The calibration method based on homographies [13] is usually adapted for this task using a planar calibration target. "
    [Show abstract] [Hide abstract]
    ABSTRACT: For robotic assisted minimally invasive surgery, recovering the 3D soft-tissue shape and morphology in vivo is important for providing image-guidance, motion compensation and applying dynamic active constraints. In this paper, we propose a practical method for calibrating the illumination source position in monocular and stereoscopic laparoscopes. The method relies on using the geometric constraints from specular reflections obtained during the laparoscope camera calibration process. By estimating the light source position, the method forgoes the common assumption of coincidence with the camera centre and can be used to obtain constraints on the normal of the surface geometry during surgery from specularities. We demonstrate the effectiveness of the proposed approach with numerical simulations and by qualitative analysis of real stereo-laparoscopic calibrations.
    Full-text · Conference Paper · Nov 2009
Show more