基于多尺度局部对比度的前视红外舰船目标增强  被引量:1

Forward-Looking Infrared Ship Target Enhancement Based on Multi-scale Local Contrast

在线阅读下载全文

作  者:仇荣超 吕俊伟 娄树理 QIU Rongchao;LYU Junwei;LOU Shuli(Naval Aviation University,Yantai 264001,China;School of Opto-Electronic Information Science and Technology,Yantai University,Yantai 264001,China)

机构地区:[1]海军航空大学,山东烟台264001 [2]烟台大学光电信息科学技术学院,山东烟台264001

出  处:《电光与控制》2020年第9期71-77,共7页Electronics Optics & Control

基  金:国家自然科学基金(61701519)。

摘  要:前视红外海天场景图像中的舰船目标可能面临着信噪比低、尺寸差异大等问题,为了更好地突出目标、抑制背景,提出了一种基于多尺度局部对比度的前视红外舰船目标增强方法。首先分析了前视红外海天图像中的场景内容,然后定义了一种新的局部对比度度量——相对区域对比度度量(RRCM),通过改变网格窗口的尺寸构建了多尺度局部对比度度量(MRRCM),最终得到了尺度不变局部对比度图像。实验结果表明,所提方法可以适应前视红外图像中多类型多尺寸的舰船目标,显著提高目标信号的信噪比(SNR)和信背比(SBR),与其他方法相比,所提方法的舰船目标增强效果更好,尤其是对于暗弱目标区域;另外,所提方法运算速度快,并且可以借助并行处理和积分图像进一步加速运行。The ship targets in the forward-looking infrared image under sea-sky scene may face problems such as low signal-to-noise ratio and large size difference.In order to better highlight the targets and suppress the background,a forward-looking infrared ship target enhancement method based on multi-scale local contrast is proposed.Firstly,the scene content in the forward-looking infrared images under sea-sky scene is analyzed.Then a new local contrast measure,called Relative Regional Contrast Measure(RRCM)is defined.By changing the size of the grid window,a Multi-scale RRCM(MRRCM)is constructed.Finally,the scale-invariant local contrast image is obtained.The experimental results show that,the proposed method can well adapt to the multi-type and multi-size ship targets in the forward-looking infrared image,which improves the signal-to-noise ratio and signal-to-background ratio of the target signal significantly.Compared with other methods,the ship target enhancement effects of the proposed method is better,especially for small and dim ship target regions.In addition,the proposed method has high operation speed,and can be further accelerated by parallel processing and integral image.

关 键 词:前视红外图像 舰船目标增强 局部对比度 尺度不变 

分 类 号:TN215[电子电信—物理电子学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象