红外图像特征的三维提取技术
|
摘要
为了提高红外图像的识别能力,需要对红外图像的三维特征进行有效提取,提出一种基于图形自适应渲染和纹理特征分割的红外图像特征三维提取技术。采用三维红外点扫描方法进行红外图像的纹理渲染和点跟踪识别,在红外透射空间中对采集的红外图像进行纹理分割,在不同红外透射纹理区域中进行图像的动态特征融合处理,采用空间邻域边缘融合方法提取红外图像三维特征的亮度和色差信息,实现红外图像的三维重建和特征提取。仿真结果表明,采用该方法进行红外图像特征三维提取的准确度较高,三维特征重构能力较强,动态特征点的匹配性较好,在红外图像识别中具有很好的应用价值。
In order to improve the recognition ability of infrared image,it is necessary to extract the 3 D feature of infrared image effectively. A 3 D feature extraction technique based on image adaptive rendering and texture feature segmentation is proposed. The texture rendering and point tracking recognition of infrared image are carried out by 3 D infrared point scanning method,and the texture of the collected infrared image is segmented in infrared transmission space. Dynamic feature fusion is carried out in different infrared transmission texture regions. The spatial neighborhood edge fusion method is used to extract the brightness and color difference information of the 3 D features of the infrared image,and the 3 D reconstruction and feature extraction of the infrared image are realized. The simulation results show that the proposed method has higher accuracy,better ability of 3 D feature reconstruction and better matching of dynamic feature points,and it has a good application value in infrared image recognition.
In order to improve the recognition ability of infrared image,it is necessary to extract the 3 D feature of infrared image effectively. A 3 D feature extraction technique based on image adaptive rendering and texture feature segmentation is proposed. The texture rendering and point tracking recognition of infrared image are carried out by 3 D infrared point scanning method,and the texture of the collected infrared image is segmented in infrared transmission space. Dynamic feature fusion is carried out in different infrared transmission texture regions. The spatial neighborhood edge fusion method is used to extract the brightness and color difference information of the 3 D features of the infrared image,and the 3 D reconstruction and feature extraction of the infrared image are realized. The simulation results show that the proposed method has higher accuracy,better ability of 3 D feature reconstruction and better matching of dynamic feature points,and it has a good application value in infrared image recognition.
引文
[1]罗琦,朱敏,韦香.多频信号的自适应随机共振检测方法[J].武汉大学学报(理学版),2013,59(3):260-266.
[2]李明爱,崔燕,杨金福,等.基于HHT和CSSD的多域融合自适应脑电特征提取方法[J].电子学报,2013,41(12):2479-2486.
[3]潘宗序,禹晶,胡少兴,等.基于多尺度结构自相似性的单幅图像超分辨率算法[J].自动化学报,2014,40(4):594-603.
[4]MUKAINO M,ONO T,SHINDO K,et al.Efficacy of brain-computer interface-driven neuromuscular electrical stimulation for chronic paresis after stroke[J].Journal of Rehabilitation Medicine,2014,46(4):378-82.
[5]L SIWEI,P XUNYU,Z XING.Exposing region splicing forgeries with blind local noise estimation[J].International Journal of Computer Vision,2014,110(2):202-221.
[6]MEHER S K.Recursive and noise-exclusive fuzzy switching median filter for impulse noise reduction[J].Engineering Applications of Artificial Intelligence,2014,30:145-154.
[7]HSIEH M H,CHENG F C,SHIE M C,et al.Fast and efficient median filter for removing 1-99%levels of salt-and-pepper noise in images[J].Engineering Applications of Artificial Intelligence,2013,26(4):1333-1338.
[8]王波,孔维祥,尤新刚.利用颜色滤波矩阵估计原图的拼接定位盲取证[J].电子与信息学报,2012,34(1):200-206.
[9]乔良.三维图像视觉下运动关键特征的提取方法改进[J].计算机仿真,2017,34(1):216-219.
[10]GRIMM F,NAROS G,GHARABAGHI A.Closed-loop task difficulty adaptation during virtual reality reach-tograsp training assisted with an exoskeleton for stroke rehabilitation[J].Frontiers in Neuroscience,2016,10:518.
[11]张新明,尹欣欣,涂强.动态迁移和椒盐变异融合生物地理学优化算法的高维多阈值分割[J].光学精密工程,2015,23(10):2943-2951.
[12]邹业兵,朱彦陈,王欣,等.基于红外图像序列的排球运动关键技术特征提取方法[J].湘潭大学自然科学学报,2018,32(2):43-45.
[13]马兰,陈筱勇,邓国臣.热红外港口图像特征的评估器提取与选择[J].测绘科学,2017(5):87-93.
[14]张龙,乔铁柱.一种红外图像的二值化分割算法研究[J].红外技术,2014,36(8):649-651.
[15]蔡自兴,彭梦,余伶俐.基于时序特性的自适应增量主成分分析的视觉跟踪[J].电子与信息学报,2015,37(11):2571-2577.
[16]谭海鹏,曾炫杰,牛四杰,等.基于正则化约束的遥感图像多尺度去模糊[J].中国图象图形学报,2015,20(3):386-394.
[17]李肖,葛宝臻,罗其俊,李云鹏,田庆国.自由双目立体视觉摄像机动态外参数的获取[J].计算机应用,2017,37(10):2888-2894.
[2]李明爱,崔燕,杨金福,等.基于HHT和CSSD的多域融合自适应脑电特征提取方法[J].电子学报,2013,41(12):2479-2486.
[3]潘宗序,禹晶,胡少兴,等.基于多尺度结构自相似性的单幅图像超分辨率算法[J].自动化学报,2014,40(4):594-603.
[4]MUKAINO M,ONO T,SHINDO K,et al.Efficacy of brain-computer interface-driven neuromuscular electrical stimulation for chronic paresis after stroke[J].Journal of Rehabilitation Medicine,2014,46(4):378-82.
[5]L SIWEI,P XUNYU,Z XING.Exposing region splicing forgeries with blind local noise estimation[J].International Journal of Computer Vision,2014,110(2):202-221.
[6]MEHER S K.Recursive and noise-exclusive fuzzy switching median filter for impulse noise reduction[J].Engineering Applications of Artificial Intelligence,2014,30:145-154.
[7]HSIEH M H,CHENG F C,SHIE M C,et al.Fast and efficient median filter for removing 1-99%levels of salt-and-pepper noise in images[J].Engineering Applications of Artificial Intelligence,2013,26(4):1333-1338.
[8]王波,孔维祥,尤新刚.利用颜色滤波矩阵估计原图的拼接定位盲取证[J].电子与信息学报,2012,34(1):200-206.
[9]乔良.三维图像视觉下运动关键特征的提取方法改进[J].计算机仿真,2017,34(1):216-219.
[10]GRIMM F,NAROS G,GHARABAGHI A.Closed-loop task difficulty adaptation during virtual reality reach-tograsp training assisted with an exoskeleton for stroke rehabilitation[J].Frontiers in Neuroscience,2016,10:518.
[11]张新明,尹欣欣,涂强.动态迁移和椒盐变异融合生物地理学优化算法的高维多阈值分割[J].光学精密工程,2015,23(10):2943-2951.
[12]邹业兵,朱彦陈,王欣,等.基于红外图像序列的排球运动关键技术特征提取方法[J].湘潭大学自然科学学报,2018,32(2):43-45.
[13]马兰,陈筱勇,邓国臣.热红外港口图像特征的评估器提取与选择[J].测绘科学,2017(5):87-93.
[14]张龙,乔铁柱.一种红外图像的二值化分割算法研究[J].红外技术,2014,36(8):649-651.
[15]蔡自兴,彭梦,余伶俐.基于时序特性的自适应增量主成分分析的视觉跟踪[J].电子与信息学报,2015,37(11):2571-2577.
[16]谭海鹏,曾炫杰,牛四杰,等.基于正则化约束的遥感图像多尺度去模糊[J].中国图象图形学报,2015,20(3):386-394.
[17]李肖,葛宝臻,罗其俊,李云鹏,田庆国.自由双目立体视觉摄像机动态外参数的获取[J].计算机应用,2017,37(10):2888-2894.