基于对比度和梯度分布的红外弱小目标检测

红外弱小目标检测技术是目标自动检测系统中的核心技术之一。在复杂背景以及强杂波存在的情形下,红外弱小目标检测往往会有高虚警率的问题。对于这一问题,提出了一种基于多尺度局部对比度与局部梯度分布的红外弱小目标检测算法,具有重要意义。相比于以前的算法,该方法利用多尺度局部对比度机制增强红外图像中的疑似红外弱小目标的区域,再利用红外图像的局部梯度分布信息对这些疑似红外弱小目标的区域进行判别,剔除其中的虚警区域,得到有低虚警率红外弱小目标检测结果。实验结果表明:该算法结果可靠,检测准确率高。可见,新算法可以有效地提高在复杂背景以及存在强杂波情形下红外图像中弱小目标的检测准确率。

Infrared Dim Small Target Detection Based on Contrast and Gradient Distribution

Infrared dim-small target detection technology is one of the core technologies in the target automatic detection system. In the case of complex backgrounds and heavy clutter, infrared dim small target detection often has a high false alarm rate. For this problem, this paper proposes an infrared dim small target detection algorithm based on multi-scale local contrast and local gradient distribution, which is of great significance. The method uses a multi-scale local contrast mechanism to enhance the region of the suspected infrared dim small target in the infrared image, and then uses the local gradient distribution information of the infrared image to discriminate these suspected infrared dim small targets for eliminating the false alarm region to get a low false alarm rate in the infrared dim small target detection results. Finally, the experimental results show that the algorithm is reliable and the detection accuracy is high. It can be seen that the new algorithm effectively improves the accuracy of infrared dim small target detection in the case of complex background and heavy clutter.