Method and system for detecting small ship targets in thermal infrared images based on hierarchical feature attention network

A method for detecting small ship targets in thermal infrared images based on hierarchical feature attention network, comprising the following steps:

• S1:
• collecting and preprocessing image data of detection areas in three thermal infrared bands of Sustainable Development Goals Science Satellite 1 (SDGSAT-1) to establish a pixel level annotated three-channel infrared ship target detection dataset;
• and
• S2:
• constructing a network model based on hierarchical feature attention mechanism for thermal infrared image ship target identification, wherein the thermal infrared image ship target identification is divided into four stages:
• input stage, feature extraction stage, prediction stage, and localization stage;
• wherein the step S2 comprises:
• S21:
• in the input stage, performing a multi-level detail enhancement process on the three-channel infrared ship target detection dataset to generate feature maps of different scales;
• S22:
• in the feature extraction stage, extracting multi-level long-distance information from multi-scale feature maps, and fusing the multi-level long-distance information into the feature maps of different scales to generate feature maps of different scales containing the multi-level long-distance information;
• S23:
• in the prediction stage, fusing the feature maps of different scales containing the multi-level long-distance information to generate predicted target probability maps;
• and
• S24:
• in the localization stage, performing a ship target localization through an eight connected aggregation algorithm with the predicted target probability maps.