Detection and characterization of surfing events with smartphones’ embedded sensors

Gomes, Diana; Moreira, Dinis; Madureira, João Lopo

doi:10.1109/icsenst.2018.8603656

Cited by 2 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results indicate that wave detection is more accurate when the algorithm uses both data sources (inertial and positioning sensors). This finding is consistent with that of our previous work [17], which tested this premise under more demanding circumstances and with a significantly bigger dataset. The addition of inertial sensors also improved their definition of wave boundaries.…”

Section: Related Worksupporting

confidence: 93%

“…In [17], Gomes et al investigated the pros and cons of using different sensors for wave detection, finally concluding that the combination of both GPS and IMU sensor data was the overall better approach. This approach was, therefore, selected for the subsequent work reflected in this manuscript.…”

Section: Methodsmentioning

confidence: 99%

“…The first implementation corresponds to the paddle detection algorithm detailed in [17], in which, upon finishing a laying event, data would proceed to a next block responsible for determining if paddle occurred in that timeframe. The acceleration of gravity measured in the X -axis was considered the most appropriate signal to support this identification.…”

Section: Methodsmentioning

confidence: 99%

“…This is extremely relevant in the context of a surf session, since these solutions may not be suitable for computing performance-related metrics with the validity and reliability that surf practitioners need. These limitations could be mitigated by combining the use of GPS with a secondary source of data, namely inertial sensors [6,7,10,16,17,18]. Indeed, Chambers et al [6] stated that, in sport performance analytics, speed and distance calculations are frequently performed using GPS, but sport-specific movements are identified and characterised using inertial sensors.…”

Section: Introductionmentioning

confidence: 99%

“…This context motivated the development of a new algorithm for the detection and characterisation of surf session events from intermediate to advanced level surfers, combining both IMU and GPS data sources to achieve the most reliable outcome possible. In this sense, this manuscript presents an extension of the work reported in [17], with an extended validation of the entire surf session profiling algorithm, namely concerning wave detection performance, with an improved dataset comprising approximately 7.5 h of annotated data and featuring a total of 327 waves, and an additional contribution:…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Surf Session Events’ Profiling Using Smartphones’ Embedded Sensors

Gomes

Moreira

Costa

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

The increasing popularity of water sports—surfing, in particular—has been raising attention to its yet immature technology market. While several available solutions aim to characterise surf session events, this can still be considered an open issue, due to the low performance, unavailability, obtrusiveness and/or lack of validation of existing systems. In this work, we propose a novel method for wave, paddle, sprint paddle, dive, lay, and sit events detection in the context of a surf session, which enables its entire profiling with 88.1% accuracy for the combined detection of all events. In particular, waves, the most important surf event, were detected with second precision with an accuracy of 90.3%. When measuring the number of missed and misdetected wave events, out of the entire universe of 327 annotated waves, wave detection performance achieved 97.5% precision and 94.2% recall. These findings verify the precision, validity and thoroughness of the proposed solution in constituting a complete surf session profiling system, suitable for real-time implementation and with market potential.

show abstract

Section: Related Worksupporting

confidence: 93%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%