Systems and methods for fusing color image and near-infrared image
AssigneeInnopeak Technology, Inc.
InventorsKim C. Ng, Jinglin Shen, Chiuman Ho
Life of this patent
Estimating the term…
Abstract
A method for image fusion includes the following. One or more geometric characteristics of the NIR image and the RGB image are normalized. The normalized NIR image and the normalized RGB image are converted to a first NIR image and a first RGB image in a radiance domain, respectively. The first NIR image is decomposed to an NIR base portion and an NIR detail portion, and the first RGB image is decomposed to an RGB base portion and an RGB detail portion. The NIR base portion, RGB base portion, NIR detail portion and RGB detail portion are combined using a set of weights. A resulting weighted combination of these base and detail portions is converted from the radiance domain to a fused image in an image domain.
Claims20
A method for image fusion, comprising:
- obtaining a near infrared (NIR) image and an RGB image captured simultaneously in a scene;
- normalizing one or more geometric characteristics of the NIR image and the RGB image;
- converting the normalized NIR image to a first NIR image in a radiance domain and converting the normalized RGB image to a first RGB image in the radiance domain;
- decomposing the first NIR image to an NIR base portion and an NIR detail portion in the radiance domain, and decomposing the first RGB image to an RGB base portion and an RGB detail portion in the radiance domain;
- generating a weighted combination of the NIR base portion, the RGB base portion, the NIR detail portion, and the RGB detail portion in the radiance domain using a set of weights;
- and
- converting the weighted combination in the radiance domain to a first fused image in an image domain.
A method for image fusion, comprising:
- obtaining a first image and a second image captured simultaneously in a scene by two distinct image sensors;
- normalizing one or more geometric characteristics of the first image and the second image;
- converting the normalized first image to a third image in a radiance domain and converting the normalized second image to a fourth image in the radiance domain;
- decomposing the third image to a first base portion and a first detail portion in the radiance domain, and decomposing the fourth image to a second base portion and a second detail portion in the radiance domain;
- generating a weighted combination of the first base portion, the first detail portion, the second base portion, and the second detail portion using a set of weights;
- and
- converting the weighted combination in the radiance domain to a first fused image in an image domain.
A computer system, comprising:
- one or more processors;
- and
- a memory having instructions stored thereon, which when executed by the one or more processors cause the one or more processors to:
- obtain a near infrared (NIR) image and an RGB image captured simultaneously in a scene;
- normalize one or more geometric characteristics of the NIR image and the RGB image;
- convert the normalized NIR image to a first NIR image in a radiance domain and convert the normalized RGB image to a first RGB image in the radiance domain;
- decompose the first NIR image to an NIR base portion and an NIR detail portion in the radiance domain, and decompose the first RGB image to an RGB base portion and an RGB detail portion in the radiance domain;
- generate a weighted combination of the NIR base portion, the RGB base portion, the NIR detail portion, and the RGB detail portion in the radiance domain using a set of weights;
- and
- convert the weighted combination in the radiance domain to a first fused image in an image domain.
Dependencies are inferred from the claim text.