DOT_NN Computer Vision Project
readme with project details and resources.
Some helpful things you should add are:
A project overview The DOT and the Asset Management Department wants to collect assets, such as stops signs, curb cuts, street lights, etc and their exact coordinates to create a thorough database of these assets. The data scientists and engineers will create these databases and servers for a multitude of uses, whether that be adding more assets or knowing which assets need improvement.
Descriptions of each class type Classes : Streetlight, curbcut
Current status Current status: Task 1 Data collection & annotating (streetlights, curbcuts)
**Timeline**
Task 2 : Create Dataset
Task 3: Select a Model
Task 4: Train
Task 5: Visualize
Using LiDAR -> point cloud
Next Steps
Once your model is trained you can use your best checkpoint best.pt to:
- Run CLI or Python inference on new images and videos
- Validate accuracy on train, val and test splits
- Export to TensorFlow, Keras, ONNX, TFlite, TF.js, CoreML and TensorRT formats
- Evolve hyperparameters to improve performance
- Improve your model by sampling real-world images and adding them to your dataset
Cite This Project
If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{
dot_nn_dataset,
title = { DOT_NN Dataset },
type = { Open Source Dataset },
author = { Opal_v },
howpublished = { \url{ https://universe.roboflow.com/opal_v/dot_nn } },
url = { https://universe.roboflow.com/opal_v/dot_nn },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { mar },
note = { visited on 2024-06-29 },
}
Connect Your Model With Program Logic
Find utilities and guides to help you start using the DOT_NN project in your project.