Emre Baseski

Learn More
Skeletal trees are commonly used in order to express geometric properties of the shape. Accordingly, tree edit distance is used to compute a dissimilarity between two given shapes. We present a new tree edit based shape matching method which uses a recent coarse skeleton representation. The coarse skeleton representation allows us to represent both shapes(More)
We develop means of learning and representing object grasp af-fordances probabilistically. By grasp affordance, we refer to an entity that is able to assess whether a given relative object-gripper configuration will yield a stable grasp. These affordances are represented with grasp densities, continuous probability density functions defined on the space of(More)
We describe a system for autonomous learning of visual object representations and their grasp affordances on a robot-vision system. It segments objects by grasping and moving 3D scene features, and creates probabilistic visual representations for object detection, recognition and pose estimation, which are then augmented by continuous characterizations of(More)
Keywords: Cognitive vision Contour representation 3D contours Contour relations Perceptual relations 3D reasoning Driver assistance Grasping a b s t r a c t In this work, we make use of 3D contours and relations between them (namely, coplanarity, cocolority, distance and angle) for four different applications in the area of computer vision and vision-based(More)
In this work, we address the problem of road interpretation for driver assistance based on an early cognitive vision system. The structure of a road and the relevant traffic are interpreted in terms of ego-motion estimation of the car, independently moving objects on the road, lane markers and large scale maps of the road. We make use of temporal and(More)
We introduce one module in a cognitive system that learns the shape of objects by active exploration. More specifically, we propose a feature tracking scheme that makes use of the knowledge of a robotic arm motion to: 1) segment the object currently grasped by the robotic arm from the rest of the visible scene, and 2) learn a representation of the 3D shape(More)
We introduce a lane marker detection algorithm that integrates 3D attributes as well as 3D relations between local edges and semi-global contours in a Bayesian framework. The algorithm is parameter free and does not make use of any heuristic assumptions. The reasoning is based on the complete conditional probabilities of the different cues which are(More)