Walk detection and step counting on unconstrained smartphones

By Agata Brajdic, Robert K. Harle. Ubiquitous Computing, 2013

404 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Modern WLAN Fingerprinting Indoor Positioning Methods and Deployment Challenges (2016, background): “• Walking detection [128]: Although the motion sensors can be exploited to deliver user’s motion, utilizing these sensors for long time consumes a great portion of battery.”
RoNIN: Robust Neural Inertial Navigation in the Wild: Benchmark, Evaluations, & New Methods (2019, background): “Most existing inertial navigation algorithms, such as zero speed update [7] and step counting [8], require unrealistic constraints that are incompatible with everyday smartphone † Indicates equal contribution.”
Wi-Fi Fingerprint-Based Indoor Positioning: Recent Advances and Comparisons (2016, methodology): “In recent works utilizing the pedometer [93], researchers have focused on the following three components:”
IONet: Learning to Cure the Curse of Drift in Inertial Odometry (2018, methodology): “However, dynamic step estimation is heavily influenced by sensor noise, user’s walking habits and phone attachment changes, causing unavoidable errors to the entire system (Brajdic and Harle 2013).”