Semantically-driven automatic creation of training sets for object recognition

Semantically-driven automatic creation of training sets for object recognition

In the object recognition community, much effort has been spent on devising expressive object representations and powerful learning strategies for designing effective classifiers, capable of achieving high accuracy and generalization. In this scenario, the focus on the training sets has been historically weak; by and large, training sets have been generated with a substantial human intervention...

Semantically Driven Automatic Hyperlinking

Automatic Hierarchical Object Decomposition for Object Recognition

Industrial applications of 2D object recognition such as quality control often demand robustness, highest accuracy, and real-time computation from the object recognition approach. Simultaneously fulfilling all of these demands is a hard problem and has recently drawn considerable attention within the research community of close-range photogrammetry and computer vision. The problem is complicate...

Automatic Creation of Environment Models via Training

Model checking suffers not only from the state-space explosion problem, but also from the environment modeling problem: how can one create an accurate enough model of the environment to enable precise yet efficient model checking? We present a novel approach to the automatic creation of environment models via training. The idea of training is to take several programs that use a common API and a...

Automatic Creation of Object Hierarchies for Radiosity Clustering

Using object clusters for hierarchical radiosity greatly improves the efficiency and thus usability of radiosity computations. By eliminating the quadratic starting phase very large scenes containing about 100k polygons can be handled efficiently. Although the main algorithm extends rather easily to using object clusters, the creation of ’good’ object hierarchies is a difficult task both in ter...