We present an efficient method within an active vision framework for rec-ognizing objects which are ambiguous from certain viewpoints. The system is allowed to reposition the camera to capture additional views and, there-fore, to resolve the classification result obtained from a single view. The ap-proach uses an appearance based object representation, namely the paramet-ric eigenspace, and augments it by probability distributions. This captures possible variations in the input images due to errors in the pre-processing chain or the imaging system. Furthermore, the use of probability distribu-tions gives us a gauge to view planning. View planning is shown to be of great use in reducing the number of images to be captured when compared to a ...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...
We present an efficient method within an active vision framework for recognizing objects which are a...
We present new test results for our active object recognition algorithms. The algorithms are used to...
We present an active object recognition strategy which combines the use of an attention mechanism fo...
We present an active object recognition strategy which combines the use of an attention mechanism fo...
We present an active object recognition strategy which combines the use of an attention mechanism fo...
One major goal of active object recognition systems is to extract useful information from multiple m...
We present a new active active recognition scheme (using an uncalibrated camera) based on a new idea...
We advance new active object recognition algorithms that classify rigid objects and estimate their p...
To recognize objects in a scene, a single view is sufficient if the scene is relatively simple consi...
Performance on visual tasks such as classification can be enhanced by employing active vision system...
In active vision, the configuration of a camera system is adapted automatically in order to acquire ...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...
We present an efficient method within an active vision framework for recognizing objects which are a...
We present new test results for our active object recognition algorithms. The algorithms are used to...
We present an active object recognition strategy which combines the use of an attention mechanism fo...
We present an active object recognition strategy which combines the use of an attention mechanism fo...
We present an active object recognition strategy which combines the use of an attention mechanism fo...
One major goal of active object recognition systems is to extract useful information from multiple m...
We present a new active active recognition scheme (using an uncalibrated camera) based on a new idea...
We advance new active object recognition algorithms that classify rigid objects and estimate their p...
To recognize objects in a scene, a single view is sufficient if the scene is relatively simple consi...
Performance on visual tasks such as classification can be enhanced by employing active vision system...
In active vision, the configuration of a camera system is adapted automatically in order to acquire ...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...
Active vision models can simplify visual tasks, provided that they can select sensible actions given...