Markerless analysis of front crawl swimming

Ceseracciu, Elena; Sawacha, Z.; Fantozzi, Silvia; Cortesi, Matteo; Gatta, Giorgio; Corazza, Stefano; Cobelli, Claudio

doi:10.1016/j.jbiomech.2011.06.003

Cited by 60 publications

(46 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Video recordings made with underwater cameras have been traditionally used for this type of analysis, both with a marker (Ceccon et al, 2013;Cortesi, Fantozzi, & Gatta, 2012;Gourgoulis et al, 2008;McCabe & Sanders, 2012;Yanai, Hay, & Miller, 2000) and a markerless approach (Ceseracciu et al, 2011). However, that kind of analysis requires timeconsuming installation, calibration/computational procedures, and allows the examination of only the underwater phases of the movement and few stroke cycles.…”

Section: Introductionmentioning

confidence: 99%

Assessment of three-dimensional joint kinematics of the upper limb during simulated swimming using wearable inertial-magnetic measurement units

Fantozzi

Giovanardi

Magalhães

et al. 2015

Journal of Sports Sciences

Self Cite

View full text Add to dashboard Cite

The analysis of the joint kinematics during swimming plays a fundamental role both in sports conditioning and in clinical contexts. Contrary to the traditional video analysis, wearable inertial-magnetic measurements units (IMMUs) allow to analyse both the underwater and aerial phases of the swimming stroke over the whole length of the swimming pool. Furthermore, the rapid calibration and short data processing required by IMMUs provide coaches and athletes with an immediate feedback on swimming kinematics during training. This study aimed to develop a protocol to assess the three-dimensional kinematics of the upper limbs during swimming using IMMUs. Kinematics were evaluated during simulated dry-land swimming trials performed in the laboratory by eight swimmers. A stereo-photogrammetric system was used as the gold standard. The results showed high coefficient of multiple correlation (CMC) values, with median (first-third quartile) of 0.97 (0.93-0.95) and 0.99 (0.97-0.99) for simulated front-crawl and breaststroke, respectively. Furthermore, the joint angles were estimated with an accuracy increasing from distal to proximal joints, with wrist indices showing median CMC values always higher than 0.90. The present findings represent an important step towards the practical use of technology based on IMMUs for the kinematic analysis of swimming in applied contexts.

show abstract

Section: Introductionmentioning

confidence: 99%

Assessment of three-dimensional joint kinematics of the upper limb during simulated swimming using wearable inertial-magnetic measurement units

Fantozzi

Giovanardi

Magalhães

et al. 2015

Journal of Sports Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…1 These frame rates are reflected in the extant literature although some examples of higher values such as 125 Hz and 200 Hz can be found. 33,46 Various solutions have been developed to record underwater motion, including placing the camera in a waterproof housing; 25,47,53 using an underwater viewing window 24,31,46 or alternatively a periscope system 38,45 ( Figure 4). Although periscope systems were frequently used in the past, [55][56][57][58] waterproof camera housings would appear to now be the most popular choice and offer flexibility in positioning but have short camera to interface distances (the distance between the camera lens and the glass of the waterproof housing) which can result in reconstruction errors ( Figure 5).…”

Section: Camera Selection and Setupmentioning

confidence: 99%

“…24,25 Marker-less systems have an advantage over other techniques for swimming applications, as form and drag caused by markers are central concerns. 73 The results of initial investigations suggest that this method shows similar reliability to manual digitisation approaches, but further investigation of system reliability has been suggested.…”

Section: Marker-less Analysismentioning

confidence: 99%

“…94 As with any new methodology, additional investigation will be required to fully assess the merits and feasibility of any new approach for applied settings. For instance, the system described by Ceseracciu, et al 25 was tested for one arm only and for front-crawl swimming, and it remains to be seen if the same level of accuracy would be achieved for whole body kinematic analysis and for other swimming strokes. This trend towards automated procedures is likely to lead to increases in quantitative analysis practices as the time constraints associated with digitization are reduced.…”

Section: Marker-less Analysismentioning

confidence: 99%

See 1 more Smart Citation

Application of Video-Based Methods for Competitive Swimming Analysis: A Systematic Review

Quinlan

Laighin²,

Mooney³

et al. 2015

Sport Exerc Med Open J

View full text Add to dashboard Cite

This paper explores the application of video-based methods for the analysis of competitive swimming performance. A systematic search of the existing literature was conducted using the following keywords: swim*, performance, analysis, quantitative, qualitative, camera, video on studies published in the last five years, in the electronic databases ISI Web of Knowledge, PubMed, Science Direct, Scopus and SPORT discus. Of the 384 number of records initially identified, 30 articles were fully reviewed and their outcome measures were analysed and categorised according to (i) the processes involved, (ii) the application of video for technical analysis of swimming performance and (iii) emerging advances in video technology. Results showed that video is one of the most common methods used to gather data for analysing performance in swimming. The process of using video in aquatic settings is complex, with little consensus amongst coaches regarding a best-practice approach, potentially hindering usage and effectiveness. Different methodologies were assessed and recommendations for coaches, sport scientists and clinicians are provided. Video is an extremely versatile tool. In addition to providing a visual record, it can be used for qualitative and quantitative analysis and is used in both training and competition settings. Cameras can be positioned to gather images both above and below the water. Ongoing advances in automation of video processing techniques and the integration of video with other analysis tools suggest that video analysis will continue to remain central to the preparation of elite swimmers.

show abstract

“…Marker-free techniques for analysis of movement in 3D often apply a Visual Hull [14], which uses silhouettestypically extracted digitally-from a number of camera views to reconstruct a volume of interest [15][16][17][18][19][20]. Corazza et al [17] tracked walking trials and gymnastic flips, and concluded that Visual Hull-based approaches for tracking human movements require at least eight cameras.…”

Section: Introductionmentioning

confidence: 99%

Single view silhouette fitting techniques for estimating tennis racket position

et al. 2017

View full text Add to dashboard Cite

Stereo camera systems have been used to track markers attached to a racket, allowing its position to be obtained in three-dimensional (3D) space. Typically, markers are manually selected on the image plane, but this can be time-consuming. A markerless system based on one stationary camera estimating 3D racket position data is desirable for research and play. The markerless method presented in this paper relies on a set of racket silhouette views in a common reference frame captured with a calibrated camera and a silhouette of a racket captured with a camera whose relative pose is outside the common reference frame. The aim of this paper is to provide validation of these single view fitting techniques to estimate the pose of a tennis racket. This includes the development of a calibration method to provide the relative pose of a stationary camera with respect to a racket. Mean static racket position was reconstructed to within ±2 mm. Computer generated camera poses and silhouette views of a full size racket model were used to demonstrate the potential of the method to estimate 3D racket position during a simplified serve scenario. From a camera distance of 14 m, 3D racket position was estimated providing a spatial accuracy of 1.9 ± 0.14 mm, similar to recent 3D video marker tracking studies of tennis.

show abstract

Markerless analysis of front crawl swimming

Cited by 60 publications

References 21 publications

Assessment of three-dimensional joint kinematics of the upper limb during simulated swimming using wearable inertial-magnetic measurement units

Assessment of three-dimensional joint kinematics of the upper limb during simulated swimming using wearable inertial-magnetic measurement units

Application of Video-Based Methods for Competitive Swimming Analysis: A Systematic Review

Single view silhouette fitting techniques for estimating tennis racket position

Contact Info

Product

Resources

About