Show HN: Dataset for South Asian Road Scene Understanding in Autonomous Driving (github.com)

The dataset consists of 20K high-resolution images from the driving perspective on Bangladesh roads, and includes 130K bounding box annotations for 13 objects. Along with diverse road scenes, narrow streets and highways, objects from different viewpoints and scenes from crowded environments with densely cluttered objects and various weather conditions.

Demo of model trained on dataset: https://youtu.be/pdRXa10SrAc?si=bvr9gHtXFGjE7Bwh

Contact for commercial use.