Exercise rep counting: Datasets & Models
A keypoint-based computer vision workflow that tracks body joints during exercises to automatically count repetitions. It detects pose landmarks and analyzes their motion to identify completed reps for movements like squats, push-ups, and curls.
Exercise rep counting
This workflow uses keypoint detection to locate body joints such as shoulders, elbows, hips, and knees from video or live camera input, then tracks their motion across frames to count exercise repetitions. Trained on an exercise rep dataset, it measures joint angles and movement cycles to detect completed reps for movements like squats, push-ups, and curls.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate exercise rep counting
Manually counting reps or relying on wearables adds friction for users and produces inconsistent data across different exercises and body types. A keypoint model turns any ordinary camera into a rep-counting sensor, giving builders a scalable way to track form and volume directly from video. For fitness and AR app teams, this means richer workout analytics, automated feedback, and gamified experiences without asking users to buy extra hardware. Automating rep counting with pose estimation also frees developers from writing brittle, exercise-specific heuristics by hand.
Key benefits
Keypoint detection works with the cameras your users already have, so you can deploy on mobile, web, or AR devices without new infrastructure. Starting from an exercise rep dataset and a pretrained pose model shortens the path from prototype to production, and the approach scales across many movement types and workout environments. The result is consistent, real-time rep counting and form tracking that improves user engagement and generates measurable performance data.
How to use it
- Upload an image: Drop any photo into the widget above to try exercise rep counting for free, right on this page.
- Preview instant results: The model detects person, dumbbell, barbell, kettlebell, yoga mat within seconds and returns an annotated image with structured predictions, so you can immediately see how well it works. Adjust the detection classes and re-run until the results fit your scenario.
- Like what you see?: With a free Roboflow account, you can deploy this workflow with the Serverless Cloud API, customize it in your workspace, or train Keypoint detection on your own images for production accuracy.
- Get started for free: No code or training data required to begin: upload, review the results, and make it part of your stack in a single click.
Recommended model for exercise rep counting
When you're ready to build a production model for exercise rep counting, we recommend training Keypoint detection. Unlike the ready-to-use model in the demo above, you fine-tune it on your own labeled images for higher accuracy, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Exercise Rep Counting project to Roboflow Agent.