Boundary + Cricket Computer Vision Project
Updated 3 months ago
13
views4
downloadsMetrics
This project started as a PoC that was to show that YOLO model could be used on videos realtime to perform visual analyses. Detecting various objects shown on the screen consistently.
This project gave us several valuable insights regarding the workings of the YOLO model and the Pros/Cons of various underlying options for YOLO, The project was primarily done on bounding box information while there could be some data which could be useful for segmentation.
The PoC was a success and the last model is one that can detect the cricket ball in all shots, close-up, pitch-view and long-shots. Getting the detections on the long shots were the most challenging task. Roboflow was very helpful in getting the last part right.
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{
boundary-cricket_dataset,
title = { Boundary + Cricket Dataset },
type = { Open Source Dataset },
author = { pirai },
howpublished = { \url{ https://universe.roboflow.com/pirai-hgb3d/boundary-cricket } },
url = { https://universe.roboflow.com/pirai-hgb3d/boundary-cricket },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2024 },
month = { sep },
note = { visited on 2024-12-18 },
}