MLESAC: a new robust estimator with application to estimating image geometry
Computer Vision and Image Understanding - Special issue on robusst statistical techniques in image understanding
A Flexible New Technique for Camera Calibration
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Optimal Global Mosaic Generation from Retinal Images
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Automatic Panoramic Image Stitching using Invariant Features
International Journal of Computer Vision
Homography-based 2D Visual Tracking and Servoing
International Journal of Robotics Research
Retina mosaicing using local features
MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II
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
A robust mosaicing method with super-resolution for optical medical images
MIAR'10 Proceedings of the 5th international conference on Medical imaging and augmented reality
Hi-index | 0.00 |
Recent developments in bio-photonics have called for the need of bringing cellular and molecular imaging modalities to an in vivo --- in situ setting to allow for real-time tissue characterization and functional assessment. Before such techniques can be used effectively in routine clinical environments, it is necessary to address the visualization requirement for linking point based optical biopsy to large area tissue visualization. This paper presents a novel approach for fibered endoscopic video mosaicing that permits wide region tissue visualization. A feature-based registration method is used to register the frames of the endoscopic video sequence by taking into account the characteristics of fibroscopic imaging such as non-linear lens distortion and high-frequency fiber optic facet pattern. The registration is combined with an efficient optimization scheme in order to align all input frames in a globally consistent way. An evaluation on phantom and ex vivotissue images allowing free-hand camera motion is presented.