UFPR-VCR Dataset

Overview

UFPR‑VCR (UFPR Vehicle Color Recognition) is designed to address more complex vehicle color recognition scenarios than previous works. The construction of the dataset and preliminary deep‑learning experiments are detailed in our paper "Toward Enhancing Vehicle Color Recognition in Adverse Conditions: A Dataset and Benchmark".

Dataset Details

• Number of images: 10,039
• Number of vehicles: 9,502
• Vehicle categories: cars, trucks, buses, and trucks
• Image conditions: various real‑world conditions such as frontal and rear views, partial occlusion, diverse lighting, and nighttime
• Vehicle colors: 11 colors – beige, black, blue, brown, gray, green, orange, red, silver, white, yellow
• Data sources: six public datasets originally created for automatic license‑plate recognition (ALPR), including OpenALPR‑BR, RodoSol‑ALPR, SSIG‑SegPlate, UFOP, UFPR‑ALPR, and Vehicle‑Rear
• Privacy statement: The data originate from Brazilian datasets; license plates are linked only to vehicles and do not contain driver or owner personal information

Access

The dataset is provided free of charge for academic, non‑commercial research. Access requires signing a license agreement and sending a request from an institutional email address to gelima@inf.ufpr.br.

Citation

If you use the UFPR‑VCR dataset in your research, please cite our paper:

@inproceedings{lima2024toward, title = {Toward Enhancing Vehicle Color Recognition in Adverse Conditions: A Dataset and Benchmark}, author = {G. E. Lima and R. Laroca and E. Santos and E. Nascimento Jr. and D. Menotti}, year = {2024}, month = {Sept}, booktitle = {Conference on Graphics, Patterns and Images (SIBGRAPI)}, pages = {1-6}, }