结合局部纹理特征滤波的海天线检测方法  

Sea-sky line detection method combined with local texture feature filtering

作　　者：张忠民[1] 王冠华 卫俊岭 郭培涛 ZHANG Zhongmin;WANG Guanhua;WEI Junling;GUO Peitao(College of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China;Sany Construction Industry,Ltd.,Beijing 102206,China)

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001 [2]三一筑工科技股份有限公司,北京102206

出　　处：《应用科技》2024年第3期82-87,共6页Applied Science and Technology

摘　　要：针对视频监测下海天线检测图像易出现的海天对比度低、海上物体、海雾、海浪及云层等干扰条件引起的图像模糊和海天线遮挡问题,提出一种基于偏心邻域的灰度共生矩阵对比度滤波的梯度域下海天线检测方法。方法设计使用上下两方向偏心盒状滤波器获取图像的对比度梯度值图,利用滑动窗对分块图像搜索梯度极大值候选位置,根据设计策略通过构建海天线参数的概率统计模型提取拟合直线作为检测结果。仿真实验表明,本文方法能提升视觉图像下含多景物等干扰的复杂场景海天线检测的准确率,与同类方法相比提升7.69%。In view of the problems of low contrast between sea and sky,image blur caused by interference conditions such as sea objects,sea fog,waves,and clouds,and the obscuring of sea-sky-line in the image detected under video surveillance,a method for detecting sea-sky-line in the gradient domain based on the gray level co-occurrence matrix contrast filtering of the eccentric neighborhood is proposed.The method design uses two directional eccentric box filters to obtain the contrast gradient value map of the image,and uses a sliding window to search for the gradient maximum candidate position in the block image.According to the design strategy,a probability statistical model is constructed to extract the fitted straight line as the detection result.Simulation experiments show that the proposed method can improve the accuracy of detection in complex scenes with multiple objects and other interference under visual images,with a 7.69%improvement compared to similar methods.

关 键 词：海天线检测 灰度共生矩阵 对比度 滑动窗 梯度域 投票策略 图像处理 局部滤波 

分 类 号：TP391.7[自动化与计算机技术—计算机应用技术]