Infrared ship target detection method for complex sea-sky background
The invention relates to an infrared ship target detection method for a complex sea-sky background, and the method comprises the following steps: constructing an Adaboost ship detection classifier, training the Adaboost ship detection classifier based on HOG features, and achieving the rough detecti...
Saved in:
| Main Authors | , , , , |
|---|---|
| Format | Patent |
| Language | Chinese English |
| Published |
14.05.2024
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Summary: | The invention relates to an infrared ship target detection method for a complex sea-sky background, and the method comprises the following steps: constructing an Adaboost ship detection classifier, training the Adaboost ship detection classifier based on HOG features, and achieving the rough detection of a ship; expanding the detection area; performing block row and column mean value enhancement on the detection area; performing step-by-step image segmentation on the enhanced image; and obtaining a target detection result through the segmentation result. According to the invention, the image processing method is used to detect the infrared ship target, the calculation amount is low, and the method is convenient to transplant on an embedded platform. A high-precision detection result is obtained in various complex sea-sky backgrounds, and the method has excellent robustness.
本发明涉及一种面向复杂海天背景的红外船只目标检测方法，包括以下步骤：构建Adaboost船只检测分类器，基于HOG特征，训练Adaboost船只检测分类器，实现船只粗检测；对检测区域扩充；对检测区域进行分块行列均值增强；对增强图像使用逐级图像分割；通过分割结果得到目标检测结 |
|---|---|
| Bibliography: | Application Number: CN202211385005 |