Hold Detector Computer Vision Project
Updated 8 months ago
Metrics
Climbing Holds and Volumes Dataset
This dataset is all about climbing holds and volumes. It's a collection of images from bouldering gyms showing all sorts of holds and volumes climbers use. The dataset is split into two parts:
- Holds: These are the smaller grips you find on climbing walls.
- Volumes: These are the big shapes on the walls that holds can be attached to.
Why This Matters
I'm putting this together to help anyone interested in making apps or tools that understand climbing routes better. With these images and some cool tech, we can build models to recognize different holds and volumes. This is just the beginning! I'm planning to use this to create tools that give climbers insights into their climbs, like how to tackle a route or what kind of holds they're good at.
Current Stage
Right now, it's just me working on this, and I'm constantly adding more images and improving how we tell holds and volumes apart. The goal is to make this the go-to dataset for anyone interested in climbing tech.
How You Can Help
If you've got images from your climbing gym or you're good with tech and want to help sort these images, get in touch! Every bit helps make this dataset better for everyone.
More Info
Current images in the dataset are from:
Use This Trained Model
Try it in your browser, or deploy via our Hosted Inference API and other deployment methods.
Build Computer Vision Applications Faster with Supervision
Visualize and process your model results with our reusable computer vision tools.
Cite This Project
If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{
hold-detector-rnvkl_dataset,
title = { Hold Detector Dataset },
type = { Open Source Dataset },
author = { Climb AI },
howpublished = { \url{ https://universe.roboflow.com/climb-ai/hold-detector-rnvkl } },
url = { https://universe.roboflow.com/climb-ai/hold-detector-rnvkl },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2024 },
month = { mar },
note = { visited on 2024-11-17 },
}