基于多模态特征图融合的红外热图像目标区域提取算法
|
摘要
红外热图像目标区域(Region of Interest,ROI)提取对故障检测、目标跟踪等有着重要意义.为解决红外热图像干扰多、需人工标记及准确率低等问题,提出一种基于多模态特征图融合的红外热图像ROI提取算法.通过对比度、熵及梯度特征构建多模态特征图并进行区域填充,实现ROI提取.将新算法应用于实际采集的光伏太阳能板图像中.结果表明,新算法具有平均查准率高(93. 0553%)、平均查全率高(90. 2841%)、F1指数和J指数均优于图割法,人工标记少等优点,可有效用于红外热图像ROI提取.
Infrared thermal image region of interest( ROI) extraction has important significance for fault detection,target tracking and so on. In order to solve the problems of many infrared thermal image disturbances,artificial markers and lowaccuracy,a ROI of infrared thermal image extraction algorithm based on fusion of multi-modal feature map is proposed. Multi-modal feature maps are constructed by contrast,entropy,and gradient features,and region filling is performed to achieve ROI extraction.Newalgorithm is applied to actual collected photovoltaic solar panel image. Simulation results showthat the proposed algorithm has high average precision( 93. 0553%),high average recall( 90. 2841%),F_1 index and J index are better than Grab Cut,less artificial marks,etc.. It can be effectively used for ROI extraction of infrared thermal images.
Infrared thermal image region of interest( ROI) extraction has important significance for fault detection,target tracking and so on. In order to solve the problems of many infrared thermal image disturbances,artificial markers and lowaccuracy,a ROI of infrared thermal image extraction algorithm based on fusion of multi-modal feature map is proposed. Multi-modal feature maps are constructed by contrast,entropy,and gradient features,and region filling is performed to achieve ROI extraction.Newalgorithm is applied to actual collected photovoltaic solar panel image. Simulation results showthat the proposed algorithm has high average precision( 93. 0553%),high average recall( 90. 2841%),F_1 index and J index are better than Grab Cut,less artificial marks,etc.. It can be effectively used for ROI extraction of infrared thermal images.
引文
[1]WANG Rui-Feng,YANG Xian-Jiang,WU Wei-Dong. Development of infrared thermal imaging technology[J]. Infrared and Laser Engineering.(王瑞凤,杨宪江,吴伟东.发展中的红外热成像技术.红外与激光工程),2008,37(增刊):699-702.
[2]Yasaswi V,Keerthi S,Jainab B S,et al. Infrared thermal image segmentation for fault detection in electrical circuits using watershed algorithm[J]. International Journal of Engineering Trends and Technology,2015,21(9):423-429.
[3]Kim T H,Song T L. Adaptive automatic thresholding in infrared image target tracking[J]. Journal of Institute of Control,2011,17(6):579-586.
[4]Guo F F,Yan G S,Li X D,et al. An improved canny infrared edge detection method based on otsu algorithm[J].Infrared,2010,31(7):24-27.
[5]Alamri S S,Kalyankar N V,Khamitkar S D. Image segmentation by using thershold techniques[J]. Computer Science,2010,2(5):83-86.
[6]Xia R B,Zhao J B,Hui B,et al. A simple and efficient saliency extraction method based on multi-scale horizon-directional filter for infrared dim small target detection[J].Proceedings of SPIE-The International Society for Optical Engineering,2011,8004(3):510-514.
[7]LI Zhong-Bin,SHI Wen-Zhong. Partial differential equation-based object extraction from remote sensing imagery[J]. Journal of Infrared&Millimeter Waves.(李仲玢,史文中.基于偏微分方程的遥感图像目标提取.红外与毫米波学报),2016,35(3):257-262.
[8]Zhao Y,Pan H B,Du C P,et al. Bilateral two-dimensional least mean square filter for infrared small target detection[J]. Infrared Physics&Technology,2014,65(5):17-23.
[9]Bai X Z,Chen Z G,Zhang Y,et al. Spatial information based FCM for infrared ship target segmentation[C]. IEEE International Conference on Image Processing,2015,46(12):5127-5131.
[10]Qu S R,Yang H H. Automation S O. Infrared image segmentation based on PCNN with genetic algorithm parameter optimization[J]. High Power Laser&Particle Beams,2015,27(5):32-37.
[11]Rother C,Kolmogorov V,Blake A."Grab Cut":interactive foreground extraction using iterated graph cuts[C].ACM SIGGRAPH,2004,23(3):309-314.
[12]Shijin K P S,Dharun V S. Extraction of texture features using GLCM and shape features using connected regions[J]. International Journal of Engineering&Technology,2016,8(6):2926-2930.
[2]Yasaswi V,Keerthi S,Jainab B S,et al. Infrared thermal image segmentation for fault detection in electrical circuits using watershed algorithm[J]. International Journal of Engineering Trends and Technology,2015,21(9):423-429.
[3]Kim T H,Song T L. Adaptive automatic thresholding in infrared image target tracking[J]. Journal of Institute of Control,2011,17(6):579-586.
[4]Guo F F,Yan G S,Li X D,et al. An improved canny infrared edge detection method based on otsu algorithm[J].Infrared,2010,31(7):24-27.
[5]Alamri S S,Kalyankar N V,Khamitkar S D. Image segmentation by using thershold techniques[J]. Computer Science,2010,2(5):83-86.
[6]Xia R B,Zhao J B,Hui B,et al. A simple and efficient saliency extraction method based on multi-scale horizon-directional filter for infrared dim small target detection[J].Proceedings of SPIE-The International Society for Optical Engineering,2011,8004(3):510-514.
[7]LI Zhong-Bin,SHI Wen-Zhong. Partial differential equation-based object extraction from remote sensing imagery[J]. Journal of Infrared&Millimeter Waves.(李仲玢,史文中.基于偏微分方程的遥感图像目标提取.红外与毫米波学报),2016,35(3):257-262.
[8]Zhao Y,Pan H B,Du C P,et al. Bilateral two-dimensional least mean square filter for infrared small target detection[J]. Infrared Physics&Technology,2014,65(5):17-23.
[9]Bai X Z,Chen Z G,Zhang Y,et al. Spatial information based FCM for infrared ship target segmentation[C]. IEEE International Conference on Image Processing,2015,46(12):5127-5131.
[10]Qu S R,Yang H H. Automation S O. Infrared image segmentation based on PCNN with genetic algorithm parameter optimization[J]. High Power Laser&Particle Beams,2015,27(5):32-37.
[11]Rother C,Kolmogorov V,Blake A."Grab Cut":interactive foreground extraction using iterated graph cuts[C].ACM SIGGRAPH,2004,23(3):309-314.
[12]Shijin K P S,Dharun V S. Extraction of texture features using GLCM and shape features using connected regions[J]. International Journal of Engineering&Technology,2016,8(6):2926-2930.