Three-dimensional reconstruction method based on infrared visible light fusion image

• Main Authors: LIANG ZHIQING, ZHAO JIAXUE, ZHENG XING, LIU ZIJI, WEN ZHIMING, GUAN HONGYUN, TANG YAOYI, LIU SHUO
• Format: Patent
• Language: Chinese; English
• Published: 25.11.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention provides a three-dimensional reconstruction method based on an infrared and visible light fusion image, and the method comprises the steps: carrying out the image fusion of an infrared image and a visible light image which are shot at the same visual angle, and outputting the infrared and visible light fusion image; then feature point extraction and matching are carried out on the infrared visible light fusion picture, a camera pose corresponding to the feature point extraction and matching is calculated, and the camera pose is optimized by minimizing a re-projection error; taking the infrared visible light fusion image and the corresponding camera pose as input, and calculating a depth map and a pixel point plane normal vector map corresponding to each image through a block matching algorithm; and finally, combining the infrared and visible light fusion image, the depth image and the pixel point plane normal graph in a depth image fusion module, and outputting a three-dimensional model with inf