Augmented Bangladesh Traffic Dataset for Deep Learning-based Vehicle Detection under Diverse Weather Conditions

The "Augmented Bangladesh Traffic Dataset for Deep Learning-based Vehicle Detection under Diverse Weather Conditions" was developed to support research on vehicle detection in heterogeneous Bangladeshi traffic environments under varying weather and lighting conditions.

The dataset contains 9,287 annotated traffic images representing heterogeneous road traffic conditions in Bangladesh. The original dataset consisted of 4,953 images collected from multiple urban road intersections in Dhaka between March 2025 and February 2026.

Images were captured from several locations including Maghbazar, Mirpur-10, Kakrail, Gulshan, Dhanmondi, Shantinagar, Uttara, and Mugda. Additional images were collected from newspapers and social media sources to include rare traffic scenarios.

To increase robustness against environmental variability and class imbalance, offline data augmentation techniques were applied to the training subset of the dataset. These techniques include horizontal flipping, rotation, and brightness adjustments. After augmentation, the dataset size increased to 9,287 images.

All images were spatially normalized to a fixed resolution of 640×640 pixels using resizing and zero-padding while preserving the original aspect ratio.

The dataset includes bounding box annotations for 10 vehicle categories: Car, Bus, Truck, Bike, Rickshaw, Van, Bicycle, Leguna, CNG, and Emergency Vehicle (including Ambulance and Police). Annotation was performed using the Computer Vision Annotation Tool (CVAT) and exported in YOLO Detection format.

Additionally, each image includes global environmental metadata tags describing weather and illumination conditions such as Sunny, Rain, Fog, Night, Day, High Light, and Low Light.

The dataset is partitioned into training (7,801 images), validation (990 images), and testing (496 images) subsets. The augmented images are included only within the training subset to improve model generalization under diverse weather conditions.

This dataset is intended for research on deep learning-based vehicle detection, intelligent traffic monitoring, and environment-aware computer vision systems for complex traffic environments.

Citation:
If you use this dataset, please cite:

Mondal, Madhure Rani; Halder, Purbasha; Rahman, Anika (2026), “Augmented Bangladesh Traffic Dataset for Deep Learning-based Vehicle Detection under Diverse Weather Conditions”, Mendeley Data, V1, doi: 10.17632/2f9jp8bj45.1