International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 11 | Nov 2025
p-ISSN: 2395-0072
www.irjet.net
Intersection Alert System Anushree U1, Dr. Kavitha AS2, Anusha A3, Kritika Shridhar Naik4 1,2,3,4 Department of Artificial Intelligence and Machine Learning, East West Institute of Technology, Bangalore-560091, Karnataka, India -------------------------------------------------------------------------***-----------------------------------------------------------------------Abstract— Intersection Alert System is an innovative, real-time safety system that aims to minimize vehicle collisions.It
combines a sensor for detecting incoming vehicles with an TinyML-powered camera for object classification as a vehicle or a pedestrian. Depending on classification and movement patterns, the system gives timely, color-coded visual warning on a display board to slow down or stop, directing drivers. The alerts seek to enhance the response time of the driver, reduce honking or hard braking, and create safer crossing conditions. Scalable in design, this inexpensive which is best implementation in urban, semi-urban, and rural locations in India.Unlike typical traffic control devices, this system provides dynamic and situational alerts, rather than fixed-timer signals. Integration of TinyML provides the intelligence to the system, discriminating between harmless movements and possible collision threats at any given instance, reducing false alarms. The project presents an affordable mixture of hardware and AI as a new, different approach to very costly smart-city surveillance systems.
I. INTRODUCTION Road intersections are some of the most dangerous zones for both vehicles and pedestrians because of blind spots, limited visibility, and the absence of timely alerts. Traditional traffic systems often fall short in preventing sudden collisions, especially in areas without signal lights. In response to this practical problem, our project introduces an Intersection Alert System with Pedestrian Safety, which aims to reduce accident risks by detecting approaching vehicles and pedestrians and providing real-time alerts. The system utilizes a radar sensor to detect the presence of incoming vehicles, while a camera differentiates between humans and vehicles with high accuracy. This dual detection approach ensures reliable operation and minimizes false alarms. Once a threat is detected, the system triggers an immediate alert through a visual display board installed at the intersection. The board uses color-coded messages and directional arrows to inform drivers about the presence of fastapproaching vehicles from specific directions, allowing them to slow down or stop. The entire setup is controlled by a fastprocessing microcontroller like the Arduino, ensuring low latency and quick decision-making. To support sustainable deployment, the system can be powered by solar energy, making it suitable for both urban and rural areas. This project offers an affordable, scalable, and impactful solution to intersection safety, combining smart technology with real-time response to enhance road awareness, reduce collisions, and save lives. The proposed system is a real-time Intelligent Intersection Alert System developed to prevent collisions at multi-road junctions by detecting and classifying approaching objects like vehicles and pedestrians. This architecture combines low-cost IoT sensors with an embedded AI vision module, enabling real-time decision-making without relying on cloud infrastructure. II.LITERATURE SURVEY Recent research in intelligent transportation systems points to the increasing relevance of sensor-based and machinelearning solutions for enhancing safety at complex road intersections. In fact, studies demonstrate that traditionally implemented traffic control methods are rarely able to guarantee timely or dynamic warnings for drivers, particularly in unregulated environments. As Zhang et al. [1] underlined, the reliability of ADAS strongly relies on the accuracy and stability of sensing modules. Their findings show that the system's performance could degrade drastically in the event of a failure in the sensing module-a situation that calls for robustness in multi-modal detection, also implemented here by leveraging radar and TinyML-based vision sensing.
Fig 1: ADAS Architecture
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page | 982