DriveIndia: An Object Detection Dataset for Diverse Indian Traffic Scenes

We introduce DriveIndia, a large-scale object detection dataset purpose-built to capture the complexity and unpredictability of Indian traffic environments. The dataset contains 66,986 high-resolution images annotated in YOLO format across 24 traffic-relevant object categories, encompassing diverse conditions such as varied weather (fog, rain), illumination changes, heterogeneous road infrastructure, and dense, mixed traffic patterns and collected over $\mathbf{1 2 0} \boldsymbol{+}$ hours and covering $\mathbf{3, 4 0 0} \boldsymbol{+}$ kilometers across urban, rural, and highway routes. DriveIndia offers a comprehensive benchmark for realworld autonomous driving challenges. We provide baseline results using state-of-the-art YOLO family models, with the top-performing variant achieving a $m A P_{50}$ of 78.7 %. Designed to support research in robust, generalizable object detection under uncertain road conditions, DriveIndia will be publicly available via the TiHAN-IIT Hyderabad dataset repository (https://tihan.iith.ac.in/tiand-datasets/).