结合形态学和Canny算法的红外弱小目标检测

为了解决红外弱小目标精确自适应检测的问题，本文提出了一种基于Canny算法、top-hat算法和中值滤波算法结合的红外弱小目标检测方法。该方法不同于传统的Canny弱小目标检测方法，本方法先选定合适的窗口对图像进行中值滤波处理，在去除噪声的同时有效保持图像的边缘信息；再用形态学处理中的top-hat算法抑制复杂背景，去除云层；最后使用自适应Canny算法提取红外小目标的边缘信息精确定位目标的位置。实验结果证明了该方法的有效性和优越性，本文设计的组合算法能够精确定位小目标的位置，信噪比增益达到10倍以上，排除噪声以及云层的干扰作用较强，具有一定的自适应性。

Infrared small target detection based on adaptive Canny algorithm and morphology

In order to solve the problem of accurate and adaptive detection of infrared dim small targets, this paper proposes a new method based on median filter which combines top-hat algorithm and Canny algorithm.This method is different from the infrared dim target detection using traditional Canny algorithm.First,this method selected suitable window for image processing, using median filter to remove noise effectively and keep the image edge information at the same time.Then this method eliminates the effect of complex dynamic background by using top-hat algorithm. Finally, this method adopts adaptive Canny algorithm to extract the edge of infrared small target.Experimental results demonstrate the effectiveness and superiority of the proposed method,this design method which is self-adaptive can accurately locate the position of the small target, the SNR gain reaches more than 10 times. Besides, this method can eliminate noise and the effect of clouds. Moreover,this method has a certain degree of adaptability.