NIT Rourkela Proposes Real-time Alert System for Blind Corners
Share
A research team from the Department of Electronics and Communication Engineering at National Institute of Technology Rourkela (NIT Rourkela) has proposed a smart roadside system that can “see” around blind corners and warn drivers about upcoming traffic before they can visually see it. By using Internet of Things (IoT) and edge computing technology integrated with roadside units and small on-site processors, the framework can be installed near sharp turns to detect approaching vehicles in real time and send audio and visual alerts to drivers approaching the intersection.
It uses surveillance cameras, with a computer vision algorithm, installed at strategic locations to detect moving vehicles from live video streams and estimate their speed and distance as they approach a predefined blind corner.
The research has been published in the prestigious International Journal of Computational Vision and Robotics. The paper is co-authored by Mr. K.L. Sanjeev Tudu (BTech graduate), Prof. Santos Kumar Das, Prof. Umesh Chandra Pati, and Prof. Poonam Singh, along with research graduates Dr. Goutam Kumar Sahoo and Dr. Rashmiranjan Nayak from the Department of Electronics and Communication Engineering at NIT Rourkela.
What makes this framework unique from conventional systems is that, instead of sending all the recorded data to a distant cloud server, the processing is carried out on edge devices located close to the cameras. This reduces communication delays and ensures that warnings are generated in real time. Another key feature of the studied algorithm is the graphical user interface for traffic management centres to monitor sharp corners.
Speaking about the growing research momentum at the Institute, Prof. K. Umamaheshwar Rao, Director, NIT Rourkela, said, “It is heartening to see that our B. Tech students are now actively publishing in reputed international journals and contributing to meaningful technological innovations. I congratulate the faculty members and students for raising the benchmark of research through their dedication and impactful work.”
Speaking about the real-world application of the studied technology, Prof. Santos Kumar Das, Associate Professor, Department of Electronics and Communication Engineering, NIT Rourkela, said, “In a real-world test, the proposed “IoT-edge paradigm-enabled vision-based driving assistance” system successfully detected vehicles in blind zones and accurately estimated their speed and distance. The algorithms performed well even on devices with limited computational power, making the technology cost-effective and scalable. The system responded immediately when vehicles entered the danger zone, providing timely warnings through audio-visual alarms and notifications.”
The system may offer an efficient way to enhance road safety, especially in rural and hilly regions where road geometry and limited infrastructure remain significant risk factors. In this setup, intelligence is built into the roadside infrastructure, so there is no need for complicated vehicle modifications. The work also supports the design of smart cities and connected mobility systems, where “a low-cost IMU/GPS sensor-based real-time system” will help alert first-response teams including police, fire rescue, nearby hospitals and ambulance services based on analysis of the situation when a road accident occurs.
Extending Vision-Based Road Safety Towards a Patented Real-Time Accident Detection and Emergency Response Ecosystem
To make the system more advanced, the research team has also secured a patent titled “A Low-Cost IMU/GPS Sensor-Based Real-Time System with ESP32 for Automatic Vehicle Accident Detection and Alerting” (Patent No. 580396, Application No. 202331060341).
Engineered at an estimated one-time cost of Rs. 6000, the patented innovation is an economical sensor-based intelligent Accident Detection and Emergency Alerting System designed for location tracking using Global Positioning System (GPS) technology and embedded sensors through Android applications.
This smart system combines an Inertial Measurement Unit (IMU) and GPS for detecting accidents using sensors and alerting first-response teams, including police, fire rescue, and ambulance services, based on the analysis of the situation. To complement this technology, the research team has also developed a smartphone application called “Track,” which can automatically help road crash victims connect with their emergency contacts, police, or medical responders.
As the next step, the research team is focusing on a low-cost hybrid AI framework for smart city and connected mobility integration. This framework will combine roadside vision systems with embedded IMU-GPS accident detection units to create an intelligent, distributed safety network. This system will help in accurate prediction of accidents and sending emergency alerts to the authorities concerned.
