Establishing Plane Hypotheses from 3D Contours for Scene Recognition of Visual Intelligence

Attentive Visual Recognition for Scene Exploration

Vision is an active process where behaviorally important information is selectively gathered. We present a model of scene exploration in which the high-resolution fovea is deployed to interesting regions by selective attention processes. The system switches between exploratory and recognition modes such that in exploration mode, regions of interest are investigated and in recognition mode, a gi...

A Global Hypotheses Verification Method for 3D Object Recognition

We propose a novel approach for verifying model hypotheses in cluttered and heavily occluded 3D scenes. Instead of verifying one hypothesis at a time, as done by most state-of-the-art 3D object recognition methods, we determine object and pose instances according to a global optimization stage based on a cost function which encompasses geometrical cues. Peculiar to our approach is the inherent ...

Scene recognition by semantic visual words

In this paper we propose a novel approach to introduce semantic relations into the bag-of-words framework. We use the latent semantic models, such as LSA and pLSA, in order to define semantically-rich features and embed the visual features into a semantic space. The semantic features used in LSA technique are derived from the low-rank approximation of word-image occurrence matrix by SVD. Simila...

A 2D visual language for rapid 3D scene design

Automatic recognition and digitization of the features found in raster images of 2D topographic maps has a long research history. Very little such work has focused on creating and working with alternatives to the classic isoline-based topographic map.This thesis presents a system that generates 3D scenes from a 2D diagram format designed for user friendliness; with more geometric expressiveness...

Representations and Techniques for 3D Object Recognition and Scene Interpretation