Using artificial intelligence, researchers at National Institute of Technology Rourkela (NIT Rourkela) have developed a ‘multi-class vehicle detection’ (MCVD) model and a ‘light fusion bi-directional feature pyramid network’ (LFBFPN) tool aimed at improving traffic management in developing countries. Led by Prof Santos Kumar Das, Associate Professor, Department of Electronics and Communication Engineering, the team leveraged an intelligent vehicle detection (IVD) system, which uses computer vision to identify vehicles in images and videos. This system collects real-time traffic data to optimise traffic flow, reduce congestion, and aid in future road planning.

While IVD systems perform well in developed countries with organised traffic, they face challenges in developing nations with mixed traffic. In India, a wide variety of vehicles — from cars and trucks to cycles, rickshaws, and animal carts, alongside pedestrians — often operate in proximity, making accurate vehicle detection difficult. 

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, including rain and dust storms. Moreover, these systems are expensive. Video-based systems hold greater promise, especially for India, but traditional video processing techniques struggle with fast-moving traffic and demand significant computational power. 

Deep learning (DL) models, a type of AI that learn from existing data, provide an efficient way to detect vehicles in video feeds. These models use convolutional neural networks (CNNs) to identify and analyse traffic images. However, they often fail to accurately detect vehicles of varying sizes and angles, particularly in busy, mixed-traffic environments. 

Additionally, there is a lack of labelled data sets designed for such complex conditions. 

Also read
MOONSHOT. A second home?

Silicon carbide from moon’s soil

MICRO CROSSOVER: Healing molecules

Drug-free diabetes care

piyaset

Study warns against ‘oppressive heatwaves’ due to global warming

Pixxel Space’s hyperspectral satellite ‘Fireflies’

Pixxel’s hyperspectral satellite set for launch

To address these challenges, Prof Das and his team have developed the new MCVD model, which uses video deinterlacing network (VDnet) to efficiently extract key features from traffic images, even when the vehicles vary in size and shape. They also introduced the specialised LFBFPN tool to further refine the extracted details.

Related Topics