Research Sports Video Analysis
Swimmer detection and stroke rate estimation using swimmer’s motion intensity
The analysis of sports videos has been a heavily investigated subject in computer vision. Among sports videos, the analysis of swimming videos is very challenging because in the aquatic environment there are a lot of noise such as splashes, ripple and reflections. And they make it difficult to see the swimmer’s body and detect body parts. So, it is difficult to automatically evaluate swimmer in swimming videos. We propose video surveillance system to automatically analyze swimmer without detecting their body parts from a fixed camera view. Our approach allows the swimmer to be located and tracked smoothly in each frame. Our approach allows the swimmer to be estimated stroke rate.