MULTI-SPECTRAL CAMERA EXTRINSIC PARAMETER SELF-CALIBRATION ALGORITHM BASED ON EDGE FEATURES

• Main Authors: LIU, Risheng, WANG, Zhihui, LIU, Boqian, LUO, Zhongxuan, LI, Haojie, FAN, Xin, ZHONG, Wei
• Format: Patent
• Language: Chinese; English; French
• Published: 27.05.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The present invention relates to the field of image processing and computer vision, and disclosed is a multi-spectral camera extrinsic parameter self-calibration algorithm based on edge features. Since a visible light camera and an infrared camera belong to different modes, few of matching point pairs obtained by directly extracting feature points meet requirements. In order to solve the problem, the method finds an optimal corresponding position of an infrared image on a visible light image by means of edge extraction and matching on the basis of the edge features, thereby narrowing a search range and increasing the number of matching point pairs meeting the requirements. Joint self-calibration on the infrared camera and the visible light camera can be performed more efficiently, the operation is simple, and the result is accurate. La présente invention concerne le domaine du traitement d'image et de la vision informatique, et l'invention concerne un algorithme d'auto-étalonnage de paramètre extrinsèque de c