Swimmer detection and pose estimation for continuous stroke-rate determination

Zecha, Dan; Greif, Thomas; Lienhart, Rainer

doi:10.1117/12.908309

Cited by 15 publications

(12 citation statements)

References 6 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparing our approach with other system is difficult: To our knowledge, the detection of key-poses in repetitive motion of athletes with the intension of retrieving the stroke frequency and inner cyclic intervals has not been researched directly. The only comparable approach [23] trains complete object detectors on segments of a swimming cycle. The stroke rate is then extracted by counting the occurrences of an interval in a video.…”

Section: Resultsmentioning

confidence: 99%

Key-Pose Prediction in Cyclic Human Motion

Zecha

Lienhart

2015

2015 IEEE Winter Conference on Applications of Computer Vision

Self Cite

View full text Add to dashboard Cite

In this paper we study the problem of estimating innercyclic time intervals within repetitive motion sequences of top-class swimmers in a swimming channel. Interval limits are given by temporal occurrences of key-poses, i.e. distinctive postures of the body. A key-pose is defined by means of only one or two specific features of the complete posture. It is often difficult to detect such subtle features directly. We therefore propose the following method: Given that we observe the swimmer from the side, we build a pictorial structure of poselets to robustly identify random support poses within the regular motion of a swimmer. We formulate a maximum likelihood model which predicts a key-pose given the occurrences of multiple support poses within one stroke. The maximum likelihood can be extended with prior knowledge about the temporal location of a key-pose in order to improve the prediction recall. We experimentally show that our models reliably and robustly detect key-poses with a high precision and that their performance can be improved by extending the framework with additional camera views.

show abstract

Section: Resultsmentioning

confidence: 99%

Key-Pose Prediction in Cyclic Human Motion

Zecha

Lienhart

2015

2015 IEEE Winter Conference on Applications of Computer Vision

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the situations when cameras are moving, these methods can be replaced by some object detection based method in human subject tracking. Zecha et al [24] presented a method to estimate the stroke rate from video by dividing a swimming cycle of each stroke into several intervals. Object detectors are trained for each pose (intervals) and then, the stroke rate can be computed by the occurrence of those poses.…”

Section: Related Workmentioning

confidence: 99%

Swimmer Localization from a Moving Camera

Sha

Lucey

Morgan³

et al. 2013

2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

View full text Add to dashboard Cite

At the highest level of competitive sport, nearly all performances of athletes (both training and competitive) are chronicled using video. Video is then often viewed by expert coaches/analysts who then manually label important performance indicators to gauge performance. Stroke-rate and pacing are important performance measures in swimming, and these are previously digitised manually by a human. This is problematic as annotating large volumes of video can be costly, and timeconsuming. Further, since it is difficult to accurately estimate the position of the swimmer at each frame, measures such as stroke rate are generally aggregated over an entire swimming lap. Vision-based techniques which can automatically, objectively and reliably track the swimmer and their location can potentially solve these issues and allow for large-scale analysis of a swimmer across many videos. However, the aquatic environment is challenging due to fluctuations in scene from splashes, reflections and because swimmers are frequently submerged at different points in a race. In this paper, we temporally segment races into distinct and sequential states, and propose a multimodal approach which employs individual detectors tuned to each race state. Our approach allows the swimmer to be located and tracked smoothly in each frame despite a diverse range of constraints. We test our approach on a video dataset compiled at the 2012 Australian Short Course Swimming Championships.

show abstract

“…As a method of stroke analysis related to this work, Zecha et al [7] presented a method to detect body parts and estimate stroke rate which divides the swimming cycle of each stroke into several intervals and specific object detectors are trained for each pose interval. Then, the stroke rate was computed using the frequency of these pose intervals.…”

Section: Stroke Estimationmentioning

confidence: 99%

Swimmer's Stroke Estimation Using CNN and MultiLSTM

Hakozaki

Kato

Tanabiki

et al. 2018

Journal of Signal Processing

View full text Add to dashboard Cite

Many methods of sports video analysis have been proposed in the computer vision field. However, the analysis of swimming videos is a challenging task. This is because there is a lot of noise, such as water splashes, making it difficult to see the swimmer's motion and detect body parts. Thus, it is difficult to automatically estimate a swimmer's motion, especially the stroke. In this paper, we introduce a novel approach to automatically estimating the stroke in such situations. Firstly, we detect the swimmer from a swimming video using a projective transformation, background subtraction, and a Kalman filter. We next create a model that learns a mapping from a window of frames to a point on a onedimensioned(1D) target signal, which represents a swimmer's stroke (we call a 'stroke signal'). We use a convolutional neural network (CNN) and multi long short-term memory (Multi-LSTM) which is an expanded model of LSTM. Finally , we estimate swimmer's stroke from the stroke signal. In a dataset including various environments, the outputs of our system showed higher accuracy than previous ones.

show abstract

Swimmer detection and pose estimation for continuous stroke-rate determination

Cited by 15 publications

References 6 publications

Key-Pose Prediction in Cyclic Human Motion

Key-Pose Prediction in Cyclic Human Motion

Swimmer Localization from a Moving Camera

Swimmer's Stroke Estimation Using CNN and MultiLSTM

Contact Info

Product

Resources

About