摘要
为了提高红外激光图像的定位识别能力,提出基于机器学习的红外激光图像特征定位技术,采用红外遥感采集设备进行原始红外激光图像采集,采用多层Gabor小波降噪技术对采集的红外激光图像进行降噪处理,采用Radon尺度变换技术进行红外激光图像的特征分量RGB分解,提取红外激光图像的光谱特征,对提取的特征量采用机器学习算法进行分类识别,实现红外激光图像特征定位。仿真结果表明,采用该方法进行红外激光图像特征定位的准确度较高,输出红外激光图像的峰值信噪比较高,特征分类的误分率较低,从而提高了红外激光图像的定位识别能力。
In order to improve the recognition ability of infrared laser image,the image features of infrared laser positioning technology based on machine learning is proposed. use infrared remote sensing acquisition equipment for the original infrared laser image acquisition. use multi-layer wavelet denoising technology of infrared laser Gabor in the image denoising. Feature RGB of infrared laser image use Radon wavelet transform to decompose,Extract spectral features of infrared laser image,and then use machine learning algorithm for classification,realize infrared laser image feature location. The simulation results show that the method of infrared laser image feature location reaches high accuracy,improves infrared laser image's output PSNR,reduce the misclassification rate of feature classification,soas to improve the recognition ability of the infrared laser image.
引文
[1]宋涛,李鸥,刘广怡.基于空时多线索融合的超像素运动目标检测方法[J].电子与信息学报,2016,38(6):1503-1511.
[2]刘婷,程建.基于训练字典的遥感图像融合[J].计算机工程与应用,2013,49(19):135-140.
[3]莫建文,曾儿孟,张彤,等.基于多字典学习和图像块映射的超分辨率重建[J].计算机应用,2016,36(5):1394-1398.
[4]冯彦超,冯华君,徐之海,等.基于分色校正的大像差光学成像系统图像处理技术[J].光子学报,2015,44(6):33-38.
[5]El-MEZOUAR M C,KPALMA K,TALEB N,et al.A pan-sharpening based on the non-subsampled contourlet transform:application to worldview-2 imagery[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(5):1806-1815.
[6]DAVID M S,PASCOAL A M,JOAQUIN A.Optimal sensor placement for multiple target positioning with range-only measurements in two-dimensional scenarios[J].Sensors,2013,13(8):10674-10710.
[7]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.
[8]丁小康,闫磊,孔建磊,等.基于二维激光与图像的人工林采育目标检测方法[J].林业科学,2015,51(7):129-135.
[9]MEHER S K.Recursive and noise-exclusive fuzzy switching median filter for impulse noise reduction[J].Engineering Applications of Artificial Intelligence,2014,30(3):145-154.
[10]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.
[11]黄光亚,曾水玲,张书真,等.基于三维轴距的图像去噪算法[J].电子与信息学报,2015,37(3):552-559.
[12]李滔,何小海,滕奇志,吴小强.基于自适应双lp-l2范数的单幅模糊图像超分辨率盲重建[J].计算机应用,2017,37(8):2313-2318.
[13]李卓,刘洁瑜,李辉,等.基于ORB-LATCH的特征检测与描述算法[J].计算机应用,2017,37(6):1759-1762.
[14]周来恩,王晓丹.基于非监督特征学习的兴趣点检测算法[J].计算机科学,2016,43(9):289-294.
[15]张迪飞,张金锁,姚克明,等.基于SVM分类的红外舰船目标识别[J].红外与激光工程,2016,45(1):167-172.
[16]DI W,CRAWFORD M M.View generation for multiview maximum disagreement based active learning for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(5):1942-1954.
[17]蒋理,李维勇.红外激光成像中的弱小目标的准确定位技术研究[J].现代电子技术,2016,39(20):83-86.
