@Article{lin:tbe04,
author = {Gang Lin and C.\ V.\ Stewart and B.\ Roysam and K.\
Fritzsche and Gehua Yang and H.\ L.\ Tanenbaum},
title = {Predictive scheduling algorithms for real-time
feature extraction and spatial referencing:
application to retinal image sequences},
journal = {Biomedical Engineering, IEEE Transactions on},
year = 2004,
volume = 51,
number = 1,
pages = {115--125},
keywords = {eye, feature extraction, image registration, image
sampling, image sequences, medical image processing,
scheduling, Pentium Xeon processor, digital video
stream, hypothesized landmark correspondences,
initial transformations, invariant indexing, laser
photocoagulation, perimetry, predictive scheduling
algorithms, quadratic spatial transformation,
real-time feature extraction, real-time spatial
referencing, retinal image sequences, retinal
vasculature, spatial map, spatial referencing,
spatially aware ophthalmic instrumentation, tracing
computation},
abstract = {Real-time spatial referencing is an important
alternative to tracking for designing spatially
aware ophthalmic instrumentation for procedures such
as laser photocoagulation and perimetry. It requires
independent, fast registration of each image frame
from a digital video stream (1024 /spl times/ 1024
pixels) to a spatial map of the retina. Recently, we
have introduced a spatial referencing algorithm that
works in three primary steps: 1) tracing the retinal
vasculature to extract image feature (landmarks); 2)
invariant indexing to generate hypothesized landmark
correspondences and initial transformations; and 3)
alignment and verification steps to robustly
estimate a 12-parameter quadratic spatial
transformation between the image frame and the
map. The goal of this paper is to introduce
techniques to minimize the amount of computation for
successful spatial referencing. The fundamental
driving idea is to make feature extraction
subservient to registration and, therefore, only
produce the information needed for verified,
accurate transformations. To this end, the image is
analyzed along one-dimensional, vertical and
horizontal grid lines to produce a regular sampling
of the vasculature, needed for step 3) and to
initiate step 1). Tracing of the vascular is then
prioritized hierarchically to quickly extract
landmarks and groups (constellations) of landmarks
for indexing. Finally, the tracing and spatial
referencing computations are integrated so that
landmark constellations found by tracing are tested
immediately. The resulting implementation is an
order-of-magnitude faster with the same success
rate. The average total computation time is 31.2 ms
per image on a 2.2-GHz Pentium Xeon processor.},
issn = {0018-9294},
annote = {}
}