A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2013; you can also visit <a rel="external noopener" href="http://www.comsys.rwth-aachen.de/fileadmin/papers/2012/2012-bitsch-IPIN-navigation-on-wheels.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ru5eun5j6vglnfjj62fe77yeam" style="color: black;">2012 International Conference on Indoor Positioning and Indoor Navigation (IPIN)</a>
While indoor navigation in unfamiliar surroundings is challenging for pedestrians, it is even more so for persons bound to a wheelchair. Additionally, the necessary Wi-Fi infrastructure for fine grained RF fingerprinting-based indoor positioning is often unavailable. We propose a system completely self-contained within current smartphones, that allows people, wheelchair bound and others, to find their way in a building. Building on top of our previous work, where we designed and implemented a<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ipin.2012.6418931">doi:10.1109/ipin.2012.6418931</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ipin/LinkGSW12.html">dblp:conf/ipin/LinkGSW12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gokb7tdmb5fizhet5cotkpzapu">fatcat:gokb7tdmb5fizhet5cotkpzapu</a> </span>
more »... stem based on step detection and path matching, we extend the system for use on wheelchairs, where a smartphone-based step detection mechanism is impossible. We detect user speed by analyzing the optical flow encoded in the motion vectors of a live H.263 video stream recorded from the smartphone's video camera. As the phone makes use of specialized hardware for motion estimation, we show that this process happens in real time and is very efficient. While previously we only guided the user along a single path, we now extend this for the case when a user departs from the initial route, either voluntarily or because she is lost. For this, we follow several candidate paths, where we model each distinct position as a state and vary the transition between these states based on the current bearing of the user. Combining these approaches, we show the potential of smartphone-based indoor navigation, resulting in an average error (ALE) of less than 3 m, independent of the length of the overall path and without the need for additional infrastructure.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20130108010018/http://www.comsys.rwth-aachen.de/fileadmin/papers/2012/2012-bitsch-IPIN-navigation-on-wheels.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/89/e3/89e3ec3ee12bed9da398a36a1552e09c81eeb6fd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ipin.2012.6418931"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>