Gabriel Tsechpenakis

Learn More
Intelligent video analysis is a problem of great importance for applications such as surveillance and automatic annotation. We present, in this paper, a hybrid, knowledge – based approach for object recognition in video sequences. Objects are modelled, in the signal level, through the visual descriptors defined by MPEG-7, the ISO standard for description of(More)
We present the Cumulative Sum (CUSUM) stopping rule, applied to Computer Vision problems, to automatically detect changes in either parametric or nonparametric distributions, online or off-line. Our approach is based on using the previously received data of the sequence to detect a change in data that are to be received. We assume that no significant change(More)
We have built a high resolution towed digital imaging system (ISIIS) capable of imaging water volumes sufficient to accurately quantify even rare plankton (e.g. larval fish) in situ. This imaging system produces very high resolution imagery at very high data rates necessitating automated image analysis. As we are interested in the identification and(More)
Advanced Heuristics in Transportation and Logistics “Advanced Heuristics in Transportation and Logistics” [Guest Editors’ Introduction], Christos D. Tarantilis, Diomidis Spinellis, and Michel Gendreau, July/ Aug., pp. 16–18. “Case Study: An Intelligent Decision-Support System,” Zbigniew Michalewicz, Martin Schmidt, Matthew Michalewicz, and Constantin(More)
The problem of estimating three dimensional motion and structure of objects from monoc ular image sequences has drawn particular attention since the past decade The extraction of structure from motion emerges in research elds such us computer vision video coding biomedical engineering and human computer interaction Present work focuses on the algorithmic(More)
In computer vision, the acquisition of sufficient labeled data for training is often time-consuming. However, unlabeled data are conveniently available. The key problem is to discover and incorporate those informative and confidently predicted unlabeled data into the training set for improved learning. In this paper, we discover such unlabeled data by(More)
— We have built a high resolution towed digital imaging system (ISIIS) capable of imaging water volumes sufficient to accurately quantify even rare plankton (e.g. larval fish) in situ. This imaging system produces very high resolution imagery at very high data rates necessitating automated image analysis. As we are interested in the identification and(More)
Main mobile object localization is a task that emerges in research fields such us video understanding, object-based coding and various related applications, such as contentbased retrieval, remote surveillance and object recognition. The present work revisits mobile object localization in the context of content-based retrieval schemes and the related MPEG-7(More)
Two-dimensional motion estimation is a task that emerges in several elds of research such as coding and compression, content-based video retrieval and computer vision. The problem has been tackled by several authors and various algorithms can be found in the literature focusing either on accuracy or low computational cost. Present work investigates the e(More)
  • 1