Climbing Activity Recognition and Measurement with Sensor Data Analysis
Authors:
Open Access
- 25 October 2020
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 245-249
Abstract
The automatic detection of climbers activities can be the basis of software systems able to support trainers to assess the climbers performance and to define more effective training programs. We propose an initial building block of such a system, for the unobtrusive identification of the activity of someone pulling a rope after finishing the ascent. We use a novel type of quickdraw, augmented with a tri-axial accelerometer sensor. The acceleration data generated by the quickdraw during the climbs are used by a Machine Learning classifier for detecting the rope pulling activity. The obtained results show that this activity can be detected automatically with high accuracy, particularly by a Random Forest classifier. Moreover, we show that data acquired by the quickdraw sensor, as well as the detected rope pulling, can also be used to benchmark climbers.Keywords
Funding Information
- EFRE-FESR programme 2014-2020 (CUP: I56C19000110009)
This publication has 7 references indexed in Scilit:
- Automated Recognition and Difficulty Assessment of Boulder Routes2018
- Automatic Sensor-Based Detection and Classification of Climbing ActivitiesIEEE Sensors Journal, 2015
- ClimbSense2015
- Climbing Skill and Complexity of Climbing Wall Design: Assessment of Jerk as a Novel Indicator of Performance FluencyJournal of Applied Biomechanics, 2014
- ClimbAX2013
- Activity identification using body-mounted sensors—a review of classification techniquesPhysiological Measurement, 2009
- ClimBSN: Climber performance monitoring with BSN2008