Walk Detection And Step Counting On Unconstrained Smartphones. Using a large dataset 27 people 130 walks 6 smartphone. If a user turn occurs it is estimated by adding horizontal heading change to previous user. Each participant walked the same distance and changed herhis speed at markers installed on the path. This paper evaluates common walk detection WD and step counting SC algorithms applied to smartphone sensor data.
An optimised algorithm for accurate steps counting from smart-phone accelerometry In 2018 40th Annual International Conference of the IEEE. Future work Try some other algorithms Use different or additional sensor Q A Introduction What is the topic Why we need this Why What Dose pedometer works well when applied to smartphones. For normal working the user heading is estimated by a PCA-based approach. Moreover there is currently no detailed understanding of how well WC and SC algorithms work when applied to smartphones in typical unconstrained use. Walk detection and step counting on unconstrained smartphones articleBrajdic2013WalkDA titleWalk detection and step counting on unconstrained smartphones authorA. Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing pp.
We propose a robust heading estimation system adapting to the unconstrained use of smartphones.
Moreover an indirect step counting method was reported by multiplying the walking frequency and the walking duration. Walk detection WD and step counting SC tasks have received much prior attention but were often studied under laboratory conditions and tested on a relatively small number of subjects. Salvi Dario Carmelo Velardo Jamieson Brynes and Lionel Tarassenko. However there is currently no detailed understanding of how well pedometry works when applied to smartphones in typical unconstrained use. Future work Try some other algorithms Use different or additional sensor Q A Introduction What is the topic Why we need this Why What Dose pedometer works well when applied to smartphones. The dataset contains time-annotated sensor traces obtained from smartphones in typical unconstrained use while walking.