| 摘要 |
A camera (10) produces a sequence of images (12) processed by a point of interest search algorithm (14) that is parameterizable with a detection threshold (τ) such that the number (N) of points of interest detected in the image varies as a function of the threshold level. The characteristic giving the number (N) of detected points of interest as a function of the threshold (τ) is modelled by a square root decreasing exponential function, which is dynamically parameterizable with values linked to the image to be analysed. The method comprises the steps of: a) determining (18) values of parameterization of the decreasing exponential function for the current image; b) predicting (18), for this current image, an optimum value of the threshold by using the modelled characteristic, parameterized with the values determined at step a); and c) applying (14), for at least one later image, the point of interest search algorithm with the optimum threshold value (τ) computed at step b). |
