MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202511026253 A) filed by Cgc University, Mohali on March 21, 2025, for Ai-Driven Method Of Automated Detection Of Cracks In Pavement Using Drone Imagery.
Inventors include Sarabjit Singh; and Manish Sharma.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: An AI-driven method and system for automated pavement crack detection using drone imagery is disclosed. The system includes a drone equipped with an RGB camera and a thermal imaging sensor to capture multi-spectral pavement imagery along a predefined flight path. The captured imagery undergoes pre-processing to reduce noise and enhance crack visibility before being analyzed by an artificial intelligence processor. A convolutional neural network detects crack patterns through pixel-level segmentation and assigns severity scores based on width, depth, and length metrics. The detected cracks and severity assessments are overlaid onto a GIS- based pavement map using geospatial data collected by the drone. The processed data is stored in a cloud-based system for longitudinal analysis, enabling predictive maintenance. The system integrates real-time positional accuracy, transfer learning for enhanced detection, and a web-based dashboard for interactive monitoring. [
Disclaimer: Curated by HT Syndication.
