复杂背景下的红外图像弱小目标检测

Infrared small target detection under various complex backgrounds

针对红外图像中的弱小目标极易受到背景杂波干扰,导致检测结果不准确的问题,提出了一种基于视觉显著性和支持向量数据描述的红外图像弱小目标检测方法。首先,对红外图像进行显著性检测,以抑制杂波,凸显红外图像中的弱小目标;然后,在显著图中提取候选目标,并自适应地确定候选目标在原始红外图像中的目标区域。根据红外图像弱小目标特点,生成仿真红外图像弱小目标,训练支持向量数据描述模型。最后,采用支持向量数据描述模型,对候选目标区域进行判别,提取红外弱小目标。实验结果表明,该方法能够有效抑制背景杂波和噪声的干扰,显著提高红外弱小目标的检测性能。

To solve the problem that small targets in infrared images are easily subject to a large amount of background clutter,leading to unsatisfactory detection results,an infrared image detection method based on visual saliency and support vector data description is proposed.Firstly,the saliency detection is applied to the infrared image to suppress the clutter and highlight the small targets.Second,the candidate targets are extracted from the saliency image,and the target area of the candidate targets in the original infrared image is adaptively determined.According to the characteristics of small target in infrared image,the small targets are simulated,and a support vector data description model is trained.Finally,the support vector data description model is used to distinguish the candidate target areas and extract the infrared small targets.The experimental results show that this method can effectively suppress the interference of background clutter and noise,and improve the detection performance of the infrared small targets.