We propose an adaptive figure-ground classification algorithm to automatically extract a foreground region using a user-provided bounding-box. The image is first over-segmented wi...
One challenge when tracking objects is to adapt the object representation depending on the scene context to account for changes in illumination, coloring, scaling, etc. Here, we p...
Ali Borji, Simone Frintrop, Dicky N. Sihite, Laure...
Abstract. This paper presents a theory for constructing and computing velocity-adapted scale-space filters for spatio-temporal image data. Starting from basic criteria in terms of ...
— A biologically inspired foveated attention system in an object detection scenario is proposed. Thereby, a highperformance active multi-focal camera system imitates visual behav...
Abstract. This paper presents a novel nonparametric clustering algorithm called evolving mean shift (EMS) algorithm. The algorithm iteratively shrinks a dataset and generates well ...