现有的全色遥感图像机场目标检测方法, 对机场目标的直线特征利用得非常有限.提出一种同时利用自顶向下和自底向上显著性机制的新方法.利用线段检测算法检测直线, 通过跑道线段间邻近、平行且长度范围一定的特点, 提出了邻近平行性的概念, 可以深度挖掘机场跑道几何关系的先验知识.同时使用简化的基于图的视觉显著性模型, 提取自底向上的显著性.两者协同得到机场的候选位置.最后, 通过尺度不变特征变换提取特征, 利用支撑向量机进行判决, 可以精确定位机场目标.在具有各种类型的机场图像数据库上的实验结果表明, 相对于其他方法, 所提议算法具有速度快、识别率高、虚警率低的优势, 同时对于复杂背景具有更强的鲁棒性.

State-of-the-art methods for airport detection in panchromatic remote sensing images utilize very limit geometrical features of airport line segments. This paper proposed a new method which uses both bottom-up and top-down saliency. Because the airport runways have features of vicinity and parallelity, and their lengths are among certain range, the concept of near parallelity is introduced after using an improved line segments detector (LSD). It is used as a priori knowledge which can fully exploit geometrical relationship of airport runways to get top-down saliency. Meanwhile, a simplified graph-based visual saliency (GBVS) model is used to extract bottom-up saliency. Candidate regions can be gotten by combining those two clues. After that, scale-invariant features transform (SIFT) and support vector machine (SVM) are used to finally determine whether the regions contain an airport or not. The proposed method is tested on an image dataset composed of different kinds of airports. The experimental results show that the method has advantages in terms of speed, recognition rate and false alarm rate. Also, the method is more robust to complex background.