复杂海天背景下红外舰船目标实时检测算法

Real-time Detection Algorithm Infrared Ship Target Under Complex Sea-sky Background

针对复杂海空背景条件下的低信噪比舰船目标检测问题,在分析海面背景舰船目标红外图像特点的基础上,提出首先进行红外图像预滤波以抑制噪声背景增强目标,然后通过检测图像水平与垂直边缘得到潜在目标区域,最后通过小范围的图像分割检测舰船目标。实际录取数据实验结果表明,算法针对各种海面场景与目标类型均能准确检测目标,实时性好。

For the detection of the Iow-SNR ships under complex sea-sky background, a new algorithm is proposed based on the characteristic analysis of IR ship images under the sea-sky background. First, the IR image is filtered to restrain noise and enhance targets, and then the possible target region is found by the detection of the horizontal and vertical edge, the target is detected by the small image segmentation region at last. The experiment result shows that the algorithm can efficiently detect the targets in different sea scenes and target styles, and has excellent real-time capability.