Infrared small target detection method based on multi-layer nested non-full mapping U-shaped network

The invention discloses an infrared small target detection method based on a multi-layer nested non-full mapping U-shaped network, and relates to the technical field of target detection and image processing, and the method comprises the following steps: 1, constructing a dense nested feature extract...

Full description

Saved in:
Bibliographic Details
Main Authors HE WEI, SHEN WENZENG, LI WUJIN, KWAK YONG WON, TU BING
Format Patent
LanguageChinese
English
Published 28.07.2023
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:The invention discloses an infrared small target detection method based on a multi-layer nested non-full mapping U-shaped network, and relates to the technical field of target detection and image processing, and the method comprises the following steps: 1, constructing a dense nested feature extraction model; 2, constructing a cascade model, and calculating feature mapping of a channel space attention module; 3, channel dimension connection is carried out on the feature map, and the quality and details of the image are reconstructed; 4, calculating a global robust feature map, and obtaining deep feature information; step 5, calculating the centroid of each target belonging to the same type of pixels; step 6, obtaining a target detection image according to the infrared image and the reconstructed image; therefore, the correlation between the neighborhood information and the spatial information of the infrared image is fully mined by introducing the cascade model and calculating the global robust feature map so
Bibliography:Application Number: CN202310780145