Phs. Torr et A. Zissermann, PERFORMANCE CHARACTERIZATION OF FUNDAMENTAL MATRIX ESTIMATION UNDER IMAGE DEGRADATION, Machine vision and applications, 9(5-6), 1997, pp. 321-333
Citations number
30
Categorie Soggetti
Controlo Theory & Cybernetics","Computer Sciences, Special Topics","Computer Sciences","Engineering, Eletrical & Electronic","Computer Science Cybernetics
The fundamental matrix represents the epipolar geometry between two im
ages. We describe an algorithm for simultaneously estimating the funda
mental matrix and corresponding points automatically from the two imag
es. The performance of this algorithm is then assessed as the images a
re degraded by JPEG lossy compression. A number of performance measure
s are proposed and evaluated over image pairs corresponding to differe
nt camera motions and scene types.