MUMBAI, India, June 27 -- Intellectual Property India has published a patent application (202341079326 A) filed by NMICPS - Technology Innovation Hub On Autonomous Navigation Foundation; and Indian Institute Of Technology Hyderabad, Kandi, Telangana, on Dec. 22, 2023, for 'improved radar-camera calibration without rotation and translation matrices.'
Inventor(s) include Mr. Nitish Kumar; and Prof. Rajalakshmi Pachamuthu.
The application for the patent was published on June 27, under issue no. 26/2025.
According to the abstract released by the Intellectual Property India: "Improved Radar-Camera Calibration Without Rotation and Translation Matrices [0039] The present invention discloses a method for radar-camera calibration that eliminates the need for intrinsic and extrinsic calibration parameters such as focal length, principal axis points, rotation, and translation matrices. The method involves positioning a calibration setup comprising a trihedral aluminum corner reflector and a whiteboard, capturing radar data points and corresponding camera pixel coordinates, normalizing the collected data to minimize numerical precision issues, and applying a Direct Linear Transformation (DLT) algorithm to derive a single transformation matrix. The transformation matrix converts radar coordinates into camera pixel coordinates, enabling real-time synchronization and accurate sensor fusion. The method streamlines intrinsic camera calibration and ensures precise sensor orientation, contributing to enhanced object detection and localization in autonomous vehicles."
Disclaimer: Curated by HT Syndication.
