Target identification method based on visible light and hyperspectral image information fusion

• Main Authors: ZHANG YUNLONG, ZHANG LAIGANG, ZHAO LING
• Format: Patent
• Language: Chinese; English
• Published: 07.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses a target identification method based on visible light and hyperspectral image information fusion, and relates to the field of image information processing and target identification, and the method comprises the following steps: S1, collecting a visible light image and a hyperspectral image through a multi-source camera, carrying out the registration of the visible light image and the hyperspectral image, and creating a complete image training test database; s2, constructing and training a heterogeneous deep learning network model for hyperspectral image feature extraction and a deep learning network model for visible light image feature extraction; and S3, constructing a membership weighting algorithm, fusing deep feature information of the hyperspectral image and the visible light image, and creating a multi-source feature fusion classification model based on membership weighting. The technical problem to be solved by the invention is to provide a target identification method based on