The gigantic vehicle image data on the Internet can potentially promote more advanced object detection and classification models and algorithms. But organized, balanced, and valuable dataset remains a critical problem. We developed a new comprehensive Bangladesh road transport-based balanced image dataset called "Sorokh-Poth" is proposed, which harmonious with several CNN-based architectures such as YOLO, VGG-16, R-CNN, and DPM. Most of the dataset images were collected from a smartphone. The dataset comprises 9809 labeled and annotated images of 10 categories of vehicle images like Auto-rickshaw, bike, bus, bicycle, car, CNG, leguna, rickshaw, truck, and van.

THIS DATASET IS ARCHIVED AT DANS/EASY, BUT NOT ACCESSIBLE HERE. TO VIEW A LIST OF FILES AND ACCESS THE FILES IN THIS DATASET CLICK ON THE DOI-LINK ABOVE