Rourkela/New Delhi: Researchers from the National Institute of Technology, Rourkela, have secured a patent for BHU-MANACHITRA, an autonomous real-time land mapping drone system, officials said. The developed system uses Artificial Intelligence (AI) and Unmanned Aerial Vehicle (UAV) technology to automatically generate land maps without requiring internet connectivity, external computers or manual interventions, they added.
Used to identify farmlands, forests, vegetation, and urban areas, land mapping is essential for the geographic governance of any country. It serves as the basis for planning, infrastructure development, natural resource management, and environmental monitoring. In India, land mapping relies heavily on manual surveys, which often take weeks or months to produce unstable maps. In recent times, drones have been adopted to image distant terrains.
However, the captured images still need lab processing, a time-consuming process, to get a readable map. According to Sambit Bakshi, Associate Professor, Department of Computer Science and Engineering, while deep learning models are being developed worldwide to help interpret aerial images, they often struggle to identify roads, buildings, and vegetation due to the overcrowding of multiple objects. “These models often produce inaccurate or unstable maps when used in real-time. To address these limitations, we have developed a deep-learning model which allows the drone to recognise land features in real time,” he said.
Unlike conventional drones that only collect images for later analysis, BHU-MANACHITRA is suitable for on-board processing, which makes it self-sufficient and especially valuable in remote locations, disaster-hit regions, or areas with no communication networks, he said.
While the government agencies can apply the innovation in land record modernisation, urban planning and smart-city development, agriculture departments can instantly assess crop conditions, soil health and irrigation needs, improving both productivity and sustainability.
Moreover, this system may also help in the Digital India Land Records Modernisation Programme (DILRMP), launched by the Government of India in 2016, which aims to digitise cadastral maps to create a modernised and integrated land record system. The researchers explained that during natural disasters such as floods, landslides, and earthquakes, the system can provide immediate terrain information, helping authorities plan quicker and more effective responses. Environmental and forest departments can use it to monitor deforestation, encroachments, and changes in biodiversity.
A lightweight AI model with as few as 2.48 million parameters, used in BHU-MANACHITRA, makes it suitable for onboard processing, Bakshi said. Drones, by their design, cannot carry heavy dedicated hardware for real-time image processing, but can carry a tiny processor for executing this lightweight AI model that performs land mapping, he said. The innovation opens new possibilities for faster decision-making, efficient resource management, and stronger disaster resilience. With its potential use in a diverse range of sectors, BHU-MANACHITRA can play a pivotal role in enhancing national infrastructure, supporting field-level operations, and enabling more responsive, informed decision-making across the country, he added.
Orissa POST- Odisha’s No.1 Trusted English Daily
