Car Colors Computer Vision Project
Updated 2 years ago
3.4k
views168
downloadsMetrics
This project was built for detecting color and car model using two-stage detection and distance between two cars using mathmatical abstraction: https://github.com/Tyler-Odenthal/Car_Distance_Project
Companion Project: https://universe.roboflow.com/tyler-yonjx/car-models-nured/dataset/3
Objectives for the Project
-
Use Object Detection to Determine Car Model
-
Use Classification to Determine Car Color
-
Bonus: Calculate Distance Between Two Cars
By using two stage detection we can combine 10 car model types and 10 car colors to get 100 different detection combinations. 
Potential Use Cases
-
200 Amber Alerts each Year -> Enhancing DOT Cameras to Help Track Bad Actors
-
2B+ Parking Spaces in the USA -> Optimize Parking Garages and Enhance User Experience with Consumer Trends
-
3.2T+ US Miles Driven Each Year -> Monitoring Flow of Traffic and Estimating Accident Risks Profiles Based on Flow and Car Types
Estimate Distance
GitHub code can be modified to calculate distance between any numbers of cars or model type. Current iteration only accounts for Hyundia Elantra and Kia Rio. Will update code to be more robust if there is significant interest.
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{
car-colors-1smyc_dataset,
title = { Car Colors Dataset },
type = { Open Source Dataset },
author = { Tyler },
howpublished = { \url{ https://universe.roboflow.com/tyler-yonjx/car-colors-1smyc } },
url = { https://universe.roboflow.com/tyler-yonjx/car-colors-1smyc },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { dec },
note = { visited on 2024-12-31 },
}