An onset detector is described based on the most successful onset detector for non-pitched percussive audio events from an earlier comparative study (Collins, 2005a). The detection function is an adaptation of the log intensity difference change discrimination originally introduced by Anssi Klapuri (Klapuri, 1999). A novel peak picking method is used based on scoring the most salient peaks with...

Airport detection in synthetic aperture radar (SAR) images has attracted much concern the field of remote sensing. Affected by other salient objects with geometrical features similar to those airports, traditional methods often generate false detections. In order produce airports and suppress influence irrelevant objects, we propose a novel method for airport SAR images. First, line segment det...

We propose a novel approach for detection of salient image points and estimation of their intrinsic scales based on the fractional Brownian image model. Under this model images are realisations of a Gaussian random process on the plane. We define salient points as points that have a locally unique image structure. Such points are usually sparsely distributed in images and carry important inform...

In this paper we design a smoothing filter for texture+depth images based on anisotropic diffusion. Our proposed filter is linear and allows to generate a scale space of the texture image which preserves internal image structure (i.e. it does not smooth through object boundaries). Moreover, we show experimentally that our filter demonstrates better stability under camera position changes in suc...

Custom operators, working at custom precisions, are a key ingredient to fully exploit the FPGA flexibility advantage for high-performance computing. Unfortunately, such operators are costly to design, and application designers tend to rely on less efficient off-the-shelf operators. To address this issue, an open-source architecture generator framework is introduced. Its salient features are an ...

Recent object recognition methods propose to represent objects by collections of local appearance descriptors in several interest points. For recognition, this representation is matched to image data. Interest points (candidates for matching) are usually selected from images in a purely bottom-up manner. However, in many situations, there is a limited number of objects to search for, and some i...

Interest point detection is essential process for many computer vision applications, which must provide invariant points to several image variations, such as, rotation, zoom, blur, illumination variation and change of viewpoints. Harris-Affine detector is considered as one of the most effective interest point detectors, although it still presents vulnerability to some image. This paper proposes...