Toward emotional recognition during HCI using marker-based automated video trackingShow others and affiliations
2019 (English)In: Proceedings of the 31st european conference on cognitive ergonomics: Design for cognition / [ed] Maurice Mulvenna, Raymond Bond, Association for Computing Machinery (ACM), 2019, p. 49-52Conference paper, Published paper (Refereed)
Abstract [en]
Postural movement of a seated person, as determined by lateral aspect video analysis, can be used to estimate learning-relevant emotions. In this article the motion of a person interacting with a computer is automatically extracted from a video by detecting the position of motion-tracking markers on the person’s body. The detection is done by detecting candidate areas for marker with a Convolutional Neural Network and the correct candidate areas are found by template matching. Several markers are detected in more than 99 % of the video frames while one is detected in only approximate to 80,2 % of the frames. The template matching can also detect the correct template in approximate to 80 of the frames. This means that almost always when the correct candidates are extracted, the template matching is successful. Suggestions for how the performance can be improved are given along with possible use of the marker positions for estimating sagittal plane motion.
Place, publisher, year, edition, pages
Association for Computing Machinery (ACM), 2019. p. 49-52
Keywords [en]
Engagement, NIMI, Non-Instrumental Movement Inhibition, Motion Tracking, Video analysis, Fast R-CNN, Viterbi algorithm, Template matching
National Category
Applied Mechanics
Research subject
Machine Design
Identifiers
URN: urn:nbn:se:ltu:diva-81641DOI: 10.1145/3335082.3335103ISI: 000587608600014Scopus ID: 2-s2.0-85073154053OAI: oai:DiVA.org:ltu-81641DiVA, id: diva2:1503939
Conference
31st European Conference on Cognitive Ergonomics (ECCE 2019), Belfast, UK, September 10-13, 2019
Note
ISBN för värdpublikation: 978-1-4503-7166-7
2020-11-262020-11-262023-09-05Bibliographically approved