MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641110926 A) filed by Srm Institute Of Science And Technology, Ramapuram Campus; and Easwari Engineering College on September 16, 2026, for Smart Road Infrastructure Damage Detection System.
Inventors include D. Kaviya; R. Thrisha; Dr. Shiny Duela; and Dr. Mageshkumar. N.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: Abstract: Road surface damage such as potholes and cracks can create serious safety risks for vehicles and passengers. These defects may also lead to higher vehicle maintenance costs and traffic problems. Early detection of such damage helps road maintenance authorities repair roads faster and reduce accidents. This work presents a real-time road damage detection system that uses edge artificial intelligence to identify potholes and cracks while a vehicle is moving. The proposed system collects two types of information. A camera captures continuous images of the road surface, while motion sensors mounted on the vehicle record vibration signals that occur when the vehicle travels over uneven road sections. The captured images are analyzed using the MobileNet deep learning model, which is designed to operate efficiently on low- power edge devices. At the same time, vibration data from an accelerometer and gyroscope are processed using a Bidirectional Long Short-Term Memory (Bi-LSTM) network together with an Adaptive Random Forest classifier. These models learn patterns from sequential sensor signals and help distinguish normal road conditions from pothole-related vibrations. The outputs from the visual model and vibration models are combined using a sensor fusion technique to increase the reliability of the detection process. When road damage is confirmed, the system records the geographic location through a GPS module and sends the information to a cloud database. The detected damage locations can then be displayed on a digital map to assist authorities in identifying and repairing problematic road segments. Since the data processing occurs directly on an edge computing device, the system is capable of operating in real time and reduces the need for continuous communication with remote servers.
Disclaimer: Curated by HT Syndication.
