This paper addresses the problem of single-target tracker performance evaluation. A novel ranking-based methodology was developed that addresses tracker equivalence in terms of statistical significance and practical differences and novel theoretical analysis was introduced to study performance analysis measures from the perspective of hidden state estimators. A fully-annotated dataset with per-frame annotations with several visual attributes is introduced. The diversity of its visual properties is maximized in a novel way by clustering a large number of videos according to their visual attributes. This makes it the most sophistically constructed and annotated dataset to date. A multiplatform evaluation system allowing easy integration of third-party trackers is presented as well. The proposed evaluation methodology was tested on the VOT2014 challenge on the new dataset and 38 trackers, making it the largest benchmark to date. The performance evaluation methodology developed in this paper was used in the last three Visual object tracking challenges, that were carried out in conjunction with ICCV2013, ECCV2014 and ICCV2015. The IEEE TPAMI is the top journal in the field of computer vision.
COBISS.SI-ID: 1536872643
In this paper, we summarise and evaluate research in the field of cognitive systems that we have been conducting in collaboration with partners from several countries for several years. The goal of the research is development of an intelligent robot capable of learning representations of objects and their properties in a natural dialogue with a human teacher. We present representations and mechanisms that facilitate continuous learning of visual concepts in dialogue with a tutor and show as well as evaluate the implemented robot system. We present how beliefs about the world are created by processing visual and linguistic information and show how they are used for planning system behaviour with the aim of satisfying its internal drive to extend its knowledge. The system facilitates different kinds of learning initiated by the human tutor or by the system itself. We demonstrate and experimentally evaluate these principles in the case of a robot capable of learning about object visual properties.
COBISS.SI-ID: 1536908227
A significant rise of interest in visual tracking has resulted in a huge variety of performance measures, and there is no consensus about which measures should be used. This makes the cross-paper tracker comparison difficult. In this paper we revisit the popular basic performance measures and tracker performance visualizations and analyze them theoretically and experimentally. We show that several measures are equivalent from the point of information they provide for tracker comparison and, crucially, that some are more brittle than the others. Based on our analysis we narrow down the set of potential measures to only two complementary ones, describing accuracy and robustness, thus pushing towards homogenization of the tracker evaluation methodology. These two measures can be intuitively interpreted and visualized, and have been employed by the recent Visual Object Tracking (VOT) challenges as the foundation for their performance ranking methodology.
COBISS.SI-ID: 1536812739
Accurate prediction of aircraft position is becoming more and more important for the future of air traffic. Currently, the lack of information about flights prevents us to fulfill future demands for the needed accuracy in 4D trajectory prediction. Until we get the necessary information from aircraft and until new more accurate methods are implemented and used, we propose an alternative method for predicting aircraft performances using machine learning from historical data about past flights collected in a multidimensional database. In that way, we can improve existing applications by providing them better inputs for their trajectory calculations. Our method uses flight plan data to predict performance values, which are suited individually for each flight. The results show that based on recorded past aircraft performances and related flight data we can effectively predict performances for future flights based on how similar flights behaved in the past.
COBISS.SI-ID: 1537269187
Object class recognition is among the most fundamental problems in computer vision and thus has been researched intensively over the years. This chapter in the robotics handbook is mostly concerned with the recognition and detection of basic level object classes such as cars, persons, chairs, or dogs. We review the state of the art and in particular discuss the most promising methods available today.
COBISS.SI-ID: 1537376963