MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541124215 A) filed by B V Raju Institute Of Technology, Narsapur, Telangana, on Dec. 9, 2025, for 'a deep learning-assisted method for crack detection and quantification in reinforced concrete structures.'
Inventor(s) include Ambati Supraja; Samanasa Krishna Rao; Thota Vamsi; Vasireddy Chaithanya Kumar; Kondapuram Bhavani; Nadulapuram Saikethan; Sriram Kishore Goud; Kunti Gopichand; Bachu Kushil; Duddala Akhil Kumar; and Korra Mothilal.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The invention relates to an automated method and system for detecting and quantifying cracks in reinforced concrete structures using deep learning techniques. The method includes capturing images of concrete surfaces, pre-processing the images to enhance clarity, and applying a trained deep-learning model to identify and segment crack regions. The system further computes key crack parameters such as width, length, density, and propagation direction using pixel-based measurement techniques. The invention provides improved accuracy in detecting fine and micro cracks through multi-scale feature extraction and reduces false detections using post-processing refinement. The results are displayed or transmitted to a structural monitoring platform for assessment of damage severity. The system may be implemented on drones, handheld devices, or automated inspection units, enabling faster, safer, and more reliable evaluation of reinforced concrete structures."
Disclaimer: Curated by HT Syndication.
