2026-10-15T06:41:45Z https://data.mendeley.com/oai

oai:data.mendeley.com/ycv2mbph4b.1 2026-09-22T17:59:47Z

Bar, Ashesh Traffic Rule Violation Detection Dataset in Dhaka Urban Traffic Environment Mendeley Data This dataset is designed for automated vision-based monitoring of motorcycle traffic violations in complex urban environments, focusing on real-world traffic conditions in Dhaka, Bangladesh. It provides bounding-box annotations for two major motorcycle violations: helmet non-compliance (no helmet) and triple riding (three or more occupants on one motorcycle). The raw dataset contains approximately 1,100 manually annotated street traffic images. Through offline geometric and environmental augmentation, including flips, brightness and exposure variation, Gaussian blur, and sensor noise, the dataset was expanded to 4,839 frames containing 30,506 bounding-box instances. Dataset Structure The repository contains two dataset variants and a metadata file: Raw_Dataset/ – Original, un-augmented images and annotations divided into standard splits: train/ – Training images with MS-COCO JSON annotations (_annotations.coco.json). valid/ – Validation images for model development and hyperparameter tuning. test/ – Held-out evaluation set containing 78 frames and 497 annotated instances. augmented_dataset/ – Offline-augmented images: Training split: 4,644 frames containing 29,250 bounding boxes. Validation split: 117 frames containing 759 bounding boxes. dataset_metadata.csv – Summary of class distributions, image counts, and bounding-box statistics. Classes and Annotations The dataset follows a five-class object detection schema, with annotations provided in Microsoft COCO JSON format: Rider – Individual occupants seated on a motorcycle or scooter (10,986 training instances). No_helmet – Uncovered heads of riders or passengers (5,610 instances). Bike – Motorcycles or scooters (5,514 instances). Helmet_On – Riders or passengers correctly wearing helmets (5,244 instances). Trippling – A bounding box enclosing the motorcycle and all occupants when three or more people travel on one motorcycle (1,896 instances). Machine Learning Image Classification Deep Learning Biswas, Manobendra Hasan, Abir Rahman Mithu, Marufur Ahmad, Faisal Das, Tonmoy Dataset doi:10.17632/ycv2mbph4b.1 oai:data.mendeley.com/ycv2mbph4b.1 Attribution Noncommercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/ https://data.mendeley.com/datasets/ycv2mbph4b 2026-09-22T17:59:47Z