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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

To promote training efficiency and the realization of tactical analysis, in recent years, there has been a move to introduce information processing/analytical technology into sports competition. The visual tracking of moving objects is one of the most important issues for computer vision research. Recent applications have been developed to illuminate tactics and improve their construction levels for sporting events 1)~3). However, to achieve practical applications, various challenges must be mitigated, including the detection of such multiple objects as players and balls that move quickly and anomalously by images captured in large-scale spaces. In this paper, using multiple images, we focus on detecting and stably tracking objects that move quickly and anomalously. As a tracking target, we focus on a badminton shuttlecock (hereafter called "shuttle"), since it conspicuously presents the above problems. A shuttle is composed of feathers that are adhesively attached to a hemispheric cork. Since it is lighter than the balls used for other sports, attaching a transmitter or a marker for position sensing is too difficult. Tracking a shuttle presents an additional problem. Due to its structure, during a badminton rally, its moving velocity is inconsistent and is drastically altered by air resistance 4). When an object moves quickly, its image is observed with a motion blur, as shown in Fig. 2 (b) and (c). Utilizing information provided by the motion blurs, we successfully developed a visual tracking method for an object that erratically and drastically changes its moving speed (Fig. 1) 5). However, when the shuttle has just been returned, its speed becomes maximum and it moves anomalously (Fig. 2 (a)). As a result, since accurate ellipsoidal regression, which is needed for estimating the motion blur shape, is impossible, it is difficult to accurately estimate its position and speed by our conventional method. In this paper, we focus on observing a target object (when it moves very fast), as one curved-line by motion blur; we then propose a Abstract This paper introduces a method that uses multiple-view videos to estimate the 3D position of a badminton shuttle that moves quickly and anomalously. When an object moves quickly, it is observed with a motion blur effect. By utilizing the information provided by the shape of the motion blur region, we propose a visual tracking method for objects that have an erratic and drastically changing moving speed. When the speed increases tremendously, we propose another method, which applies the shape-from-silhouette technique, to estimate the 3D position of a moving shuttlecock using unsynchronized multiple-view videos. We confirmed the effectiveness of our proposed technique using video sequences and a CG simulation image set.

[Paper] Visual Tracking Method of a Quick and Anomalously Moving Badminton Shuttlecock