Sietse Dijkstra

Learn More
Global features are commonly used to describe the image content. The problem with this approach is that these features cannot capture all parts of the image having different characteristics. Therefore, local computation of image information is necessary. By using salient points to represent local information, more discriminative features can be computed.(More)
Recently, a lot of research has been done on the matching of images and their structures. Although the approaches are very different, most methods use some kind of point selection from which descriptors or a hierarchy are derived. We focus here on the methods that are related to the detection of points and regions that can be detected in an affine invariant(More)
In then extf ew decades one of the main problems to deal with in WesternE uropei st he agingo ft he population. The healthcare sector will face rising costsand increasing workload.Telemonitoring and networks of professional and voluntaryh ealth workers arep romising solution directions to deal with both thec osta nd workload challenges.I nthis paper astudyo(More)
This paper describes work in progress on the assessment of scaleable database architectures for CDR analysis 1. First, the scientific and industrial state-of-the-art of scaleable database architectures is presented. This is followed by a detailed description of experiments carried out on two promising architectures: NUMA and NT-clusters. The paper concludes(More)
In the next few decades one of the main problems to deal with in Western Europe is the aging of the population. More people will need healthcare services, while there are fewer people to provide these services. Telehomecare services like telemonitoring can provide a cost-effective means to save valuable healthcare service time by monitoring body functions(More)
This paper describes the final results of an assessment of the scalability of the NUMA architecture for very large CDR databases 1. First a description of the experiment case and experiment set up is given. Next the results of the experiments are described. The paper ends with a conclusion on the applicability of the NUMA architecture for very large CDR(More)
We introduce a resource allocation algorithm for a multi agent-based data fusion network. This network is called a Distributed Perception network in literature. The resource allocation algorithm is based on the cumulative absolute entropy change in the beliefs at the root of the data fusion network. Our algorithm can be efficiently computed locally at the(More)
  • 1