NIT Rourkela develops AI-based vehicle detection model, tool to improve traffic management

NEW DELHI: National Institute of Technology (NIT) Rourkela, has developed an artificial intelligence (AI)-based tool and model to improve traffic management in developing countries. The researchers at the institute have designed a Multi-Class Vehicle Detection (MCVD) model and Light Fusion Bi-Directional Feature Pyramid Network (LFBFPN) tool to deal with traffic congestion issues.

The research team led-by Santos Kumar Das, associate professor, department of electronics and communication engineering (ECE), at NIT Rourkela, have also designed an Intelligent Vehicle Detection (IVD) system, which uses computer vision to identify vehicles in images and videos, as per the official statement.

On January 17, NIT Rourkela also developed a new class of cathode materials for lithium-ion batteries in order to minimise the adverse effects of cobalt.

The IVD system analyses the real-time traffic data to “optimise traffic flow, reduce congestion, and aid in future road planning,” the institute said.

Explaining the mechanism of the newly developed tool and model, Das said: “What makes LFBFPN unique is that it uses a simpler method, reducing the complexity of the model without sacrificing its accuracy. The system then processes the details through another tool called Modified Vehicle Detection Head (MVDH), which helps it accurately detect and classify vehicles in all kinds of traffic situations.”

“By overcoming the limitations of older models and addressing the unique challenges of mixed traffic, the MCVD model offers a scalable option for real-time vehicle detection in developing countries. Its use could help improve traffic systems, reduce congestion, and enhance road safety,” Das added.

The institute also said that the IVD systems perform well in developed countries with organised traffic, however, it faces challenges in developing nations with mixed traffic. “In countries like India, a wide variety of vehicles, from cars and trucks to cycles, rickshaws, animal carts, and pedestrians, often operate in proximity, thus making accurate vehicle detection difficult,” the institute added.

Also read IIT Kanpur develops LiDAR-based intelligent sprayer to enhance orchard farming

NIT Rourkela upcoming project: Traffic control system

As per the institute, the research team is also working on developing a “traffic control system” based on this idea and is also planning to commercialise it through a start-up.

Referring to India’s traffic conditions, the institute said that the traditional IVD methods, including sensor systems such as radar and Light Detection and Ranging (LiDAR), are effective in controlled environments but struggle in adverse weather conditions such as dust or rain. Moreover, these systems are expensive to install. “Video-based systems hold greater promise, especially for India, but traditional video processing techniques struggle with fast-moving traffic and demand significant computational power,” it added.

To address these challenges, the new MCVD model uses “Video Deinterlacing network (VDnet) to efficiently extract key features from traffic images, even when vehicles vary in size and shape. We also introduced a specialised tool called Light Fusion Bi-Directional Feature Pyramid Network (LFBFPN) to further refine the extracted details,” it said.

The journal IEEE Transactions on Intelligent Transportation Systems, has published findings of the research conducted by NIT Rourkela.