Stable Wave Detector for Precise and Fast Detection of Blobs in the Image

Stable Wave Detector (SWD) is a new multiscale landmark detector in the intensity image. The target landmarks are blobs which correspond to local maxima/minima of intensity (positive and negative peaks). SWD belongs to a group of interestpoint-like operators aiming at detecting repeatedly distinguished entities without considering their semantics. SWD is practically motivated by a 3D natural scene reconstruction task from a videosequence captured by a low cost stereo camera rig. Precision, robustness and speed are main issues. The detector is based on the phase of the first harmonic wave in the moving window. The localization is a result of an integral transformation rather than a derivative. Thus, the blob detector is inherently robust to noise and blur in the image. The SWD provides subpixel localization of blobs together with the estimate of its precision, the measure of the strength/significance and the estimate of the size/scale for each blob. Detected blobs are further hierarchically decomposed according to scale. Blobs at each hierarchy level have some minimal distance given by the period of the detector. Both grouping of landmarks and their minimal mutual distance can facilitate matching of corresponding scene points.