低照度下的海上目标识别与跟踪  

Target Recognition And Tracking Under Low Illumination On Sea

作　　者：房广江 赵敏[1] 郭航宇[1] 林亮[1] 

机构地区：[1]南京航空航天大学自动化学院,江苏南京210016

出　　处：《机械制造与自动化》2016年第2期217-219,227,共4页Machine Building & Automation

摘　　要：针对海上目标识别过程中,热像仪图像存在干扰、目标不明显等问题,利用直方图均衡化的方法增强了目标与背景之间的对比度,便于识别;对均衡化后的图像二值处理,再利用数学形态学的方法进行开运算,消除图像中的细小噪声、平滑物体边界,在单帧图像中提取出候选目标。为了从多个候选目标中筛选出目标,通过具有平移、缩放及旋转不变性的圆形度来筛选出目标。针对现场环境在实验室做了模拟实验。实验表明,该方法能够快速准确的检测出存在强干扰、不明显的目标,将能够在海上防暴系统中发挥重要作用。In the process of target recognition,the thermal imaging device may be interfered with or the target is not obvious. The histogram equalization is used to enhance the contrast between the target and background to idenfify the target,and then the method of binarization is used with the open method of mathematical morphology operation to eliminate the image noise and smooth object boundary to extract the candidate targets in a single frame. The invariant circularity with pan,zoom and rotation is used to select the right target from multiple candidates. The simulation experiments are done in the laboratory under the site environment. Results show that the method can be used to quickly and accurately detect the less obvious target which is interfered with strongly. It means the method can play the important role in riot system on the sea.

关 键 词：直方图均衡化 目标识别 圆形度 目标跟踪 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]