In this paper we propose a head detection method using range data from a stereo camera. The method is based on a technique that has been introduced in the domain of voxel data. For application in stereo cameras, the technique is extended (1) to be applicable to stereo data, and (2) to be robust with regard to noise and variation in environmental settings. The method consists of foreground selection, head detection, and blob separation, and, to improve results in case of misdetections, incorporates a means for people tracking. It is tested in experiments with actual stereo data, gathered from three distinct real-life scenarios. Experimental results show that the proposed method performs well in terms of both precision and recall. In addition, the method was shown to perform well in highly crowded situations. From our results, we may conclude that the proposed method provides a strong basis for head detection in applications that utilise stereo cameras.
MULTIFILE
The aim of this dissertation is to examine how adult learners with a spoken language background who are acquiring a signed language, learn how to use the space in front of the body to express grammatical and topographical relations. Moreover, it aims at investigating the effectiveness of different types of instruction, in particular instruction that focuses the learner's attention on the agreement verb paradigm. To that end, existing data from a learner corpus (Boers-Visker, Hammer, Deijn, Kielstra & Van den Bogaerde, 2016) were analyzed, and two novel experimental studies were designed and carried out. These studies are described in detail in Chapters 3–6. Each chapter has been submitted to a scientific journal, and accordingly, can be read independently.1 Yet, the order of the chapters follows the chronological order in which the studies were carried out, and the reader will notice that each study served as a basis to inform the next study. As such, some overlap in the sections describing the theoretical background of each study was unavoidable.
MULTIFILE
Het project Veiligheid op de Werkvloer kijkt naar de industriële werkomgevingen de veiligheidsrisico’s die daar kunnen optreden. Doel van het project is ommet behulp van slimme ambient technologie de veiligheid te verhogen. Binnendit project is een roadmap ontwikkeld om zicht te krijgen op mogelijke toekomstigeontwikkelingen. Door daarop aan te haken kunnen we onderzoeksvragenaanscherpen.Om tot een technologieroadmap te komen hebben we een standaard proces doorlopen.Een belangrijke stap daarin was de brainstorm en discussie met een panelvan externe deskundigen. We hebben belangrijke trends benoemd, waardoor hetmogelijk was drivers te onderkennen. In twee scenarioplanningssessies hebbenwe mogelijke ontwikkelrichtingen verkend. Uiteindelijk hebben we ontwikkelingenin de technologie en vragen in de markt op elkaar afgestemd in een aantalroadmaps.
MULTIFILE
