Petr Chmelar

Learn More
In this paper we describe our experiments in all task of TRECVid 2008. This year, we have concentrated mainly on the local (affine covariant) image features and its transformation into a search-able form for the Content-based copy detection pilot together with the indexing and search techniques for the Search task and a practical test of the background(More)
This paper describes the video summarization system built for the TRECVID 2007 evaluation by the Brno team. Motivations for the system design and its overall structure are described followed by more detailed description of the critical parts of the system, which are feature extraction and clustering of frames (shots, sub-shots) in time domain. Many ideas(More)
1. The runs: • A_brU_1 – features extracted from each frame; SVM per-frame classifier trained on frames in each shot; simple decision tree judging shots based on per-frame results • A_brV_2 – same as A_brU_1, but SVM trained on all training data (the first run divided the training data to training and cross-validation datasets), with SVM configured from the(More)
In this paper, we propose a framework for interactive, iterative, and intuitive mining of multilevel association, characterization and classification rules on data organized in multilevel conceptual hierarchies. This framework is called OLAM SE (Self Explaining OnLine Analytical Mining) and it is proposed as an extension of OLAP or as an alternative to(More)
The paper deals with a solution for visual surveillance metadata management. Data coming from many cameras is annotated using computer vision units to produce metadata representing moving objects in their states. It is assumed that the data is often uncertain, noisy and some states are missing. The solution consists of the following three layers: (a) data(More)
In this paper, we propose a framework, internally called OLAM SE (Self Explaining On-Line Analytical Mining), for iterative, interactive, and intuitive mining of multilevel association, characterization and classification rules. This framework is proposed as an extension of OLAP or an alternative to Han’s OLAM. OLAM processes high structured data sets. The(More)
In the paper, we describe our experiments in the interactive surveillance event detection pilot (SED) of the 2009 TRECVid evaluation. Our approach inherits functionality of the Surveillance Network Augmented by Retrieval (SUNAR) system, which is an information retrieval based wide area (video) surveillance system being developed at FIT, Brno University of(More)
There are huge amounts of data stored in databases, but it is very difficult to make decisions based on this data. We propose the OLAM SE system (Self Explaining On-Line Analytical Mining) that is similar to the Han’s OLAM [5] in the idea of interactive data mining. The contribution is to simplify on-line analytical data mining to professionals, who(More)