Learn More
In this paper we investigate the possibilities to combine several computer vision methods to detect humans into a new detection method that outperforms all the other detection methods individually. To accomplish this, a combination of statistical methods and knowledge about the distance of human body parts will be used. We present experimental results of(More)
The contribution of this paper is a search engine that recognizes and describes 48 human actions in realistic videos. The core algorithms have been published recently, from the early visual processing (omitted for review, 2012), recognition (omitted for review, 2012) and description (omitted for review, 2012) of 48 human actions. We summarize the key(More)
In this report we show our improvements to the eMotion application. While the goal of the original application was to measure emotion from a video stream the application has slowly evolved to something which allows the automatic extraction of face textures. In our project we focussed on improving the result of reapplying a face texture. We implemented(More)
In 1994 Karl Sims published a paper[1] about evolving virtual creatures. He combined methods from genetic algorithms and neural networks to automatically evolve virtual creatures and let them learn how to move efficiently from one location to another. In this paper we propose an experiment to prove that Genetic algorithms are not the only way to simulate(More)
  • 1