English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Determining a waterline in images recorded in canoe sprint training is animportant component for the kinematic parameter analysis to assess an athlete'sperformance. Here, we propose an approach for the automated waterlinedetection. First, we utilized a pre-trained Mask R-CNN by means of transferlearning for canoe segmentation. Second, we developed a multi-stage approach toestimate a waterline from the outline of the segments. It consists of twolinear regression stages and the systematic selection of canoe parts. We thenintroduced a parameterization of the waterline as a basis for furtherevaluations. Next, we conducted a study among several experts to estimate theground truth waterlines. This not only included an average waterline drawn fromthe individual experts annotations but, more importantly, a measure for theuncertainty between individual results. Finally, we assessed our method withrespect to the question whether the predicted waterlines are in accordance withthe experts annotations. Our method demonstrated a high performance andprovides opportunities for new applications in the field of automated videoanalysis in canoe sprint.

Utilizing Mask R-CNN for Waterline Detection in Canoe Sprint Video Analysis