Abstract
In Bangladesh, people sadly are not very much concerned about traffic rules. This study focuses on traffic flow patterns at four locations in Dhaka: Shapla Chattar, Arambag, Bashabo and Abul Hotel. Foot over bridges were used to collect video data, which captured single-lane and double-lane traffic conditions involving different types of vehicles and irregular pedestrian movement. The dataset comprises of 23,678 images extracted from the videos, taken at five different time periods on weekdays. These photos were later annotated using roboflow. This dataset provides a unique view on traffic situations in Dhaka, Bangladesh, by presenting unstructured traffic environments in different conditions at different road junctions. Monitoring vehicle fitness, examining pedestrian behaviour, and measuring vehicle flow in varying environmental contexts (e.g., day, dusk, night, rain) are all possible applications. Researchers can experiment with different machine learning techniques in such traffic environments.