<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>2680</id>
    <completedYear/>
    <publishedYear>2019</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>4225</pageFirst>
    <pageLast>4230</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Human Work Activity Recognition for Working Cells in Industrial Production Contexts</title>
    <abstract language="eng">Collaboration between robots and humans requires communicative skills on both sides. The robot has to understand the conscious and unconscious activities of human workers. Many state-of-the-art activity recognition algorithms with high performance rates on existing benchmark datasets are available for this task. This paper re-evaluates appropriate architectures in light of human work activity recognition for working cells in industrial production contexts. The specific constraints of such a domain is elaborated and used as prior knowledge. We utilize state-of-the-art algorithms as spatiotemporal feature encoders and search for appropriate classification and fusion strategies. Furthermore, we combine keypoint-based with appearance-based approaches to a multi-stream recognition system. Due to data protection rules and the high effort of data annotation within industrial domains only small datasets are available that reflect production aspects. Therefore, we use transfer learning approaches to reduce the dependency on data volume and variance in the target domain. The resulting recognition system achieves high performance for both singular person action and human-object interaction.</abstract>
    <parentTitle language="eng">2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), 6-9 Oct. 2019, Bari, Italy</parentTitle>
    <identifier type="doi">10.1109/SMC.2019.8913873</identifier>
    <enrichment key="opus.import.date">2022-02-04T08:58:18+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Clemens Pohlt</author>
    <author>Thomas Schlegl</author>
    <author>Sven Wachsmuth</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Activity recognition</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Pose estimation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Robots</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Task analysis</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Three-dimensional displays</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Two dimensional displays</value>
    </subject>
    <collection role="institutes" number="FakEI">Fakultät Elektro- und Informationstechnik</collection>
    <collection role="institutes" number="FAKMB">Fakultät Maschinenbau</collection>
    <collection role="othforschungsschwerpunkt" number="16316">Produktion und Systeme</collection>
    <collection role="institutes" number="">Mechatronics Research Unit (MRU)</collection>
  </doc>
</export-example>
