AA posted that he built a model tracking ball speed, forehand versus backhand strokes, shot placement, and body position at contact. The input is iPhone video fed through a pipeline that labels data with Astra 6 and detects objects with a fine-tuned model. Several replies offered feedback on additional metrics such as distance to the ball at impact, early positioning, balance, and footwork. One reply stated the author downloaded the video, generated another app with ChatGPT, and submitted it for App Store review.
i trained a computer vision model to train me at tennis it tracks ball speed, forehand vs backhand strokes, shot placement, body position when i strike the ball how this works: - input video from an iphone - CV pipeline orchestrated with roboflow agent: data labelling using…
156.5K
8 posts, first seen 7h ago
The engineer posted about a computer vision model that analyzes iPhone video of his tennis sessions.
AA posted that he built a model tracking ball speed, forehand versus backhand strokes, shot placement, and body position at contact. The input is iPhone video fed through a pipeline that labels data with Astra 6 and detects objects with a fine-tuned model. Several replies offered feedback on additional metrics such as distance to the ball at impact, early positioning, balance, and footwork. One reply stated the author downloaded the video, generated another app with ChatGPT, and submitted it for App Store review.
i trained a computer vision model to train me at tennis it tracks ball speed, forehand vs backhand strokes, shot placement, body position when i strike the ball how this works: - input video from an iphone - CV pipeline orchestrated with roboflow agent: data labelling using…
#10
#10