CSDL Home C CVPR 2001 Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
Frame-Rate Spatial Referencing Based on Invariant Indexing and Alignment with Application to Laser Retinal Surgery
Kauai, HI, USA
Dec. 8, 2001 to Dec. 14, 2001
Hong Shen , Rensselaer Poly. Inst.
C.V. Stewart , Rensselaer Poly. Inst.
B. Roysam , Rensselaer Poly. Inst.
G. Lin , Rensselaer Poly. Inst.
H.L. Tanenbaum , The Center for Sight
This paper describes a fast feature-based algorithm for accurately estimating the absolute location of a surgical tool (a laser), pointed at the curved human retina, from a series of image frames. The method is capable of a 91% success rate with just a third of the feature extraction computation, taking 37 ms overall per image on a 900MHz Pentium III. The success rate approaches 100% when the feature extraction is allowed to run to completion. The median error is 0.92 pixels with 512x512 8-bit image frames.<div></div> Making a significant break from prior incremental tracking-based efforts, we propose a framework that involves extensive off-line precomputation to build a "spatial map" and high-speed on-line "spatial referencing" to rapidly register each surgical image with this spatial map. The spatial referencing technique is designed around the idea of quasi-invariant indexing. Similarity invariants, locally valid despite the curved nature of the retina, are computed from constellations of vascular landmarks. These are detected using a high-speed algorithm that recursively traces the blood vessel structure. Invariant indexing establishes initial correspondences between landmarks from the on-line image and landmarks stored in the spatial map. Alignment and verification steps gradually extend the similarity transformation computed from these initial correspondences to a global, high-order transformation. The spatial map is pre-computed to contain mosaics, distance maps and an invariant database, all designed to make these spatial referencing computations extremely fast.
Hong Shen, C.V. Stewart, B. Roysam, G. Lin, H.L. Tanenbaum, "Frame-Rate Spatial Referencing Based on Invariant Indexing and Alignment with Application to Laser Retinal Surgery", CVPR, 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 2001, pp. 79, doi:10.1109/CVPR.2001.990459