Bodhyaan

IDD (Indian Driving Dataset) is the world’s first dataset of Indian driving conditions. The dataset consists of images obtained from a front facing camera attached to a car driven in Hyderabad and Bengaluru.

The driving conditions in India are quite diverse and the traffic behaviour is highly unstructured compared with rest of the world. These driving conditions pose unique challenges that are yet unsolved, for research in artificial intelligence (AI) and machine learning (ML) systems, and hence offer an immense opportunity for possible technical innovations in AI/ML systems for better road safety.

Since the publication of the first dataset 4 years ago, IDD enabled researchers to develop algorithms for the unique Indian conditions, and also provided an opportunity for the global research community to investigate emerging AI concepts and benchmark their solutions.

  • 5 datasets released: more in progress for release
  • Over 7800 users from 30+ countries
  • 3 international and 2 national data challenges conducted
  • Over 140 research papers across the world have used IDD

Bodhyaan has been conceptualized as an advanced multi-modal data capture & research platform to expand the scope of IDD further and also provide a flexible platform to partners to generate their own datasets relevant to their specific use cases. The platform will have multiple sensors – cameras, LIDARs, night-vision cameras, RADARs, including the required computational power to capture and process real-time data on the car.

Bodhyaan 1.0 is presently equipped with 6 cameras for a full surround view, a LIDAR sensor and high compute for data capture and processing.

It is intended to become a platform of choice for all researchers, academics, and start-ups in India, to test algorithms or methods in vehicle navigation, data collection, or other areas related to Indian roads and research. Example Use-cases:

  • Quick, cost-effective road-audit system, mapping problem locations
  • Automatic road-side tree count with the camera on car
  • Traffic-violation capture from mobile police vehicles (helmetless drivers, 3-person driving)
  • Road/street cleanliness monitoring • Road Infra (Poles, Railings, Greenery etc.) Monitoring
  • Short & long-term changes in municipal areas (new buildings, changes to buildings, floor count)