复杂地面背景下的红外目标检测算法
|
摘要
提出一种静态场景下的基于帧差光流的随机采样均值漂移聚类检测算法.该方法首先通过隔帧差分法提取运动目标区域,并对运动区域进行光流计算,采用自适应光流阈值分割法准确提取出运动目标;然后运用连通区域标记算法对运动区域进行初步划分,得到若干个连通域子集特征向量样本点,通过提出的随机采样策略来确定对子集空间中样本点的抽样次数;最后利用均值漂移算法对每个子集中的样本点进行若干次抽样计算并分析聚类收敛结果是否相同,从而完成对连通域标记结果的检验.该策略通过减少对标记结果所有样本点的采样次数,提高了目标的检测速度和精度,在不同红外测试场景中的实验结果表明:与传统红外多目标检测算法相比,该方法具有良好的局部抗遮挡性、准确性和实时性,并且检测率能达到95.27%,每帧处理时间达到39.12ms,满足实时处理需求.
A random sampling mean-shift clustering algorithm based on frame difference light flow was proposed.Firstly,the moving target region was extracted by frame difference method,and the moving region was calculated by optical flow,and the moving target was accurately extracted by adaptive optical flow threshold segmentation method.Then,the connected region labeling algorithm was used to preliminarily divide the moving region,and several connected domain subset eigenvector sample points were obtained.The sampling times of sample points in the subset space were determined by the random sampling strategy proposed.At last,mean shift algorithm was used to carry out several sampling calculations of sample points in each subset,and analyzed whether the clustering convergence results were the same.This strategy improves the detection speed and accuracy of the target by reducing the sampling times of all sample points of the marked results.Experimental results in different infrared test scenarios show that,compared with the traditional infrared multi-target detection algorithm,the method in this paper has good local anti-blocking,accuracy and real-time performance,and the detection rate can reach 95.27%,and the processing time per frame reaches 39.12 ms,which meets the real-time processing needs.
A random sampling mean-shift clustering algorithm based on frame difference light flow was proposed.Firstly,the moving target region was extracted by frame difference method,and the moving region was calculated by optical flow,and the moving target was accurately extracted by adaptive optical flow threshold segmentation method.Then,the connected region labeling algorithm was used to preliminarily divide the moving region,and several connected domain subset eigenvector sample points were obtained.The sampling times of sample points in the subset space were determined by the random sampling strategy proposed.At last,mean shift algorithm was used to carry out several sampling calculations of sample points in each subset,and analyzed whether the clustering convergence results were the same.This strategy improves the detection speed and accuracy of the target by reducing the sampling times of all sample points of the marked results.Experimental results in different infrared test scenarios show that,compared with the traditional infrared multi-target detection algorithm,the method in this paper has good local anti-blocking,accuracy and real-time performance,and the detection rate can reach 95.27%,and the processing time per frame reaches 39.12 ms,which meets the real-time processing needs.
引文
[1]ZOU Rui-bin,SHI Cai-cheng,MAO Er-ke.Based on shear wave transform of complex sea surface infrared detection algorithm[J].Chinese Journal of Scientific Instrument,2011,32(5):1103-1108.邹瑞滨,史彩成,毛二可.基于剪切波变换的复杂海面红外目标检测算法[J].仪器仪表学报,2011,32(5):1103-1108.
[2]WANG Jun,JIANG Zhi,LIU Hong-yan,et al.Infrared small dim target detection based on multi-direction gradient[J].Journal of Optoelectronics·Laser,2016,27(9):957-962.王军,姜志,柳红岩,等.基于多向梯度法的红外弱小目标快速检测方法[J].光电子激光,2016,27(9):957-962.
[3]WU Yi-quan,YIN Dan-yan,WU Shi-hua.Small target detection in infrared image based on NSCT,KFCM and multi model LS-SVM[J].Chinese Journal of Scientific Instrument,2011,32(8):1704-1709.吴一全,尹丹艳,吴诗婳.基于NSCT、KFCM和多模型LS-SVM的红外小目标检测[J].仪器仪表学报,2011,32(8):1704-1709.
[4]GONG Wei-guo,WANG Xu,LI Zheng-hao.Anti-occlusion detection and tracking algorithm for multiple far-infrared targets[J].Chinese Journal of Scientific Instrument,2014,35(3):535-542.龚卫国,王旭,李正浩.一种抗遮挡的红外多目标实时检测跟踪算法[J].仪器仪表学报,2014,35(3):535-542.
[5]LUO Huan,WANG Fang,CHEN Zhong-qi,et al.Infrared target detecting based on symmetrical displaced frame difference and optical flow estimation[J].Acta Optica Sinica,2010,30(6):1715-1720.罗寰,王芳,陈中起,等.基于对称差分和光流估计的红外弱小目标检测[J].光学学报,2010,30(6):1715-1720.
[6]WU Yi-quan,SONG Yu.Background suppression of small infrared target image based on nonsubsampled complex contourlet transform and gaussian wavelet support vector regression[J].Acta Armamentarii,2015,36(4):687-695.吴一全,宋昱.基于复无下采样轮廓波和Gaussian小波支持向量回归的红外目标图像背景抑制[J].兵工学报,2015,36(4):687-695.
[7]LI Xiang,TAN Nan-lin,WANG Tian-lei,et al.Object detection based on local motion compensation in complex scenes[J].Chinese Journal of Scientific Instrument,2014,35(7):1555-1563.李响,谭南林,王天雷,等.复杂场景下基于局部运动补偿的目标检测[J].仪器仪表学报,2014,35(7):1555-1563.
[8]CUI Zhi-gao,WANG Hua,LI Ai-hua,et al.Moving object detection algorithm based on optical flow field analysis in dynamic background[J].Journal of Physics,2017,66(8):116-123.崔智高,王华,李艾华,等.动态背景下基于光流场分析的运动目标检测算法[J].物理学报,2017,66(8):116-123.
[9]LIU Hong-bin,CHANG Fa-liang.Moving object detection by optical flow method based on adaptive weight coefficient[J].Optics and Precision Engineering,2016,24(2):460-468.刘洪彬,常发亮.权重系数自适应光流法运动目标检测[J].光学精密工程,2016,24(2):460-468.
[10]WANG Jing-jing,QIN Shi-yin.High accuracy detection and segmentation of space moving target by complementary enhancement[J].Journal of Harbin Institute of Technology,2016,48(3):26-32.王静静,秦世引.互补增强式空间运动目标高精度检测与分割[J].哈尔滨工业大学学报,2016,48(3):26-32.
[11]ZHAO Peng-peng,CUI Shao-hui,GAO Min,et,al.Infrared target tracking with tightly coupling particle filter and mean shift[J].Journal of Optoelectronics·Laser,2016,27(10):1077-1085.赵鹏鹏,崔少辉,高敏,等.紧耦合粒子滤波与均值漂移的红外目标跟踪[J].光电子·激光,2016,27(10):1077-1085.
[12]LU Hao-bo,LI Jian-qiang,WANG Xiao-ming.Multi-objective tracking method based on mean shift-connected component labeling[J].Application Research of Computers,2011,28(10):3963-3966.鲁好波,李坚强,王小民.基于均值漂移-连通域标记的多目标跟踪算法[J].计算机应用研究,2011,28(10):3963-3966.
[13]XIE Ting,CHEN Zhong,MA Rong-yi,et al.A novel method for infrared small target detection based on PGF,BEMDand LIE[J].Journal of Infrared&Millimeter Waves,2017,36(1):92-101.解婷,陈忠,马荣毅.一种基于PGF、BEMD和局部逆熵的新型红外小目标检测方法[J].红外与毫米波学报,2017,36(1):92-101.
[14]QIN H,HAN J,YAN X,et al.Infrared small moving target detection using sparse representation-based image decomposition[J].Infrared Physics&Technology,2016,76:148-156.
[15]WAN M,GU G,CAO E,et al.In-frame and inter-frame information based infrared moving small target detection under complex cloud backgrounds[J].Infrared Physics&Technology,2016,76:455-467.
[16]QIAO Li-yong,XU Li-xin,GAO Min.Influences of infrared image complexity on the target detection performance[J].Infrared and Laser Engineering,2013,(S1):253-261.乔立永,徐立新,高敏.红外图像复杂度对目标检测性能的影响[J].红外与激光工程,2013,(S1):253-261.
[17]YI Xiang,WANG Bing-Jian.Fast infrared and dim target detection algorithm based on multi-feature[J].Acta Photonica Sinica,2017,46(6):0610002.易翔,王炳健.基于多特征的快速红外弱小目标检测算法[J].光子学报,2017,46(6):0610002.
[18]BI Y,BAI X,JIN T,et al.Multiple feature analysis for infrared small target detection[J].IEEE Geoscience&Remote Sensing Letters,2017,14(8):1333-1337.
[19]WAN M,GU G,CAO E,et al.In-frame and inter-frame information based infrared moving small target detection under complex cloud backgrounds[J].Infrared Physics&Technology,2016,76:455-467.
[20]LI Cheng-mei,BAI Hong-yang,GUO Hong-wei,et al.Moving object detection and tracking based on improved optical flow method[J].Chinese Journal of Scientific Instrument,2018,39(5):249-256.李成美,白宏阳,郭宏伟,等.一种改进光流法的运动目标检测及跟踪算法[J].仪器仪表学报,2018,39(5):249-256.
[21]CUI Z,YANG J,JIANG S,et al.An infrared small target detection algorithm based on high-speed local contrast method[J].Infrared Physics&Technology,2016,76:474-481.
[22]LV P Y,SUN S L,LIN C Q,et al.Space moving target detection and tracking method in complex background[J].Infrared Physics&Technology,2018,91:107-118.
[23]MORADI S,MOALLEM P,SABAHI M F.Scale-space point spread function based framework to boost infrared target detection algorithms[J].Infrared Physics&Technology,2016,77:27-34.
[24]QIN Jian,CHEN Qian,QIAN Wei-xian.Dim and small target detection based on optical flow estimation and adaptive background suppression[J].Acta Photonica Sinica,2011,40(3):476-482.秦剑,陈钱,钱惟贤.基于光流估计和自适应背景抑制的弱小目标检测[J].光子学报,2011,40(3):476-482.
[2]WANG Jun,JIANG Zhi,LIU Hong-yan,et al.Infrared small dim target detection based on multi-direction gradient[J].Journal of Optoelectronics·Laser,2016,27(9):957-962.王军,姜志,柳红岩,等.基于多向梯度法的红外弱小目标快速检测方法[J].光电子激光,2016,27(9):957-962.
[3]WU Yi-quan,YIN Dan-yan,WU Shi-hua.Small target detection in infrared image based on NSCT,KFCM and multi model LS-SVM[J].Chinese Journal of Scientific Instrument,2011,32(8):1704-1709.吴一全,尹丹艳,吴诗婳.基于NSCT、KFCM和多模型LS-SVM的红外小目标检测[J].仪器仪表学报,2011,32(8):1704-1709.
[4]GONG Wei-guo,WANG Xu,LI Zheng-hao.Anti-occlusion detection and tracking algorithm for multiple far-infrared targets[J].Chinese Journal of Scientific Instrument,2014,35(3):535-542.龚卫国,王旭,李正浩.一种抗遮挡的红外多目标实时检测跟踪算法[J].仪器仪表学报,2014,35(3):535-542.
[5]LUO Huan,WANG Fang,CHEN Zhong-qi,et al.Infrared target detecting based on symmetrical displaced frame difference and optical flow estimation[J].Acta Optica Sinica,2010,30(6):1715-1720.罗寰,王芳,陈中起,等.基于对称差分和光流估计的红外弱小目标检测[J].光学学报,2010,30(6):1715-1720.
[6]WU Yi-quan,SONG Yu.Background suppression of small infrared target image based on nonsubsampled complex contourlet transform and gaussian wavelet support vector regression[J].Acta Armamentarii,2015,36(4):687-695.吴一全,宋昱.基于复无下采样轮廓波和Gaussian小波支持向量回归的红外目标图像背景抑制[J].兵工学报,2015,36(4):687-695.
[7]LI Xiang,TAN Nan-lin,WANG Tian-lei,et al.Object detection based on local motion compensation in complex scenes[J].Chinese Journal of Scientific Instrument,2014,35(7):1555-1563.李响,谭南林,王天雷,等.复杂场景下基于局部运动补偿的目标检测[J].仪器仪表学报,2014,35(7):1555-1563.
[8]CUI Zhi-gao,WANG Hua,LI Ai-hua,et al.Moving object detection algorithm based on optical flow field analysis in dynamic background[J].Journal of Physics,2017,66(8):116-123.崔智高,王华,李艾华,等.动态背景下基于光流场分析的运动目标检测算法[J].物理学报,2017,66(8):116-123.
[9]LIU Hong-bin,CHANG Fa-liang.Moving object detection by optical flow method based on adaptive weight coefficient[J].Optics and Precision Engineering,2016,24(2):460-468.刘洪彬,常发亮.权重系数自适应光流法运动目标检测[J].光学精密工程,2016,24(2):460-468.
[10]WANG Jing-jing,QIN Shi-yin.High accuracy detection and segmentation of space moving target by complementary enhancement[J].Journal of Harbin Institute of Technology,2016,48(3):26-32.王静静,秦世引.互补增强式空间运动目标高精度检测与分割[J].哈尔滨工业大学学报,2016,48(3):26-32.
[11]ZHAO Peng-peng,CUI Shao-hui,GAO Min,et,al.Infrared target tracking with tightly coupling particle filter and mean shift[J].Journal of Optoelectronics·Laser,2016,27(10):1077-1085.赵鹏鹏,崔少辉,高敏,等.紧耦合粒子滤波与均值漂移的红外目标跟踪[J].光电子·激光,2016,27(10):1077-1085.
[12]LU Hao-bo,LI Jian-qiang,WANG Xiao-ming.Multi-objective tracking method based on mean shift-connected component labeling[J].Application Research of Computers,2011,28(10):3963-3966.鲁好波,李坚强,王小民.基于均值漂移-连通域标记的多目标跟踪算法[J].计算机应用研究,2011,28(10):3963-3966.
[13]XIE Ting,CHEN Zhong,MA Rong-yi,et al.A novel method for infrared small target detection based on PGF,BEMDand LIE[J].Journal of Infrared&Millimeter Waves,2017,36(1):92-101.解婷,陈忠,马荣毅.一种基于PGF、BEMD和局部逆熵的新型红外小目标检测方法[J].红外与毫米波学报,2017,36(1):92-101.
[14]QIN H,HAN J,YAN X,et al.Infrared small moving target detection using sparse representation-based image decomposition[J].Infrared Physics&Technology,2016,76:148-156.
[15]WAN M,GU G,CAO E,et al.In-frame and inter-frame information based infrared moving small target detection under complex cloud backgrounds[J].Infrared Physics&Technology,2016,76:455-467.
[16]QIAO Li-yong,XU Li-xin,GAO Min.Influences of infrared image complexity on the target detection performance[J].Infrared and Laser Engineering,2013,(S1):253-261.乔立永,徐立新,高敏.红外图像复杂度对目标检测性能的影响[J].红外与激光工程,2013,(S1):253-261.
[17]YI Xiang,WANG Bing-Jian.Fast infrared and dim target detection algorithm based on multi-feature[J].Acta Photonica Sinica,2017,46(6):0610002.易翔,王炳健.基于多特征的快速红外弱小目标检测算法[J].光子学报,2017,46(6):0610002.
[18]BI Y,BAI X,JIN T,et al.Multiple feature analysis for infrared small target detection[J].IEEE Geoscience&Remote Sensing Letters,2017,14(8):1333-1337.
[19]WAN M,GU G,CAO E,et al.In-frame and inter-frame information based infrared moving small target detection under complex cloud backgrounds[J].Infrared Physics&Technology,2016,76:455-467.
[20]LI Cheng-mei,BAI Hong-yang,GUO Hong-wei,et al.Moving object detection and tracking based on improved optical flow method[J].Chinese Journal of Scientific Instrument,2018,39(5):249-256.李成美,白宏阳,郭宏伟,等.一种改进光流法的运动目标检测及跟踪算法[J].仪器仪表学报,2018,39(5):249-256.
[21]CUI Z,YANG J,JIANG S,et al.An infrared small target detection algorithm based on high-speed local contrast method[J].Infrared Physics&Technology,2016,76:474-481.
[22]LV P Y,SUN S L,LIN C Q,et al.Space moving target detection and tracking method in complex background[J].Infrared Physics&Technology,2018,91:107-118.
[23]MORADI S,MOALLEM P,SABAHI M F.Scale-space point spread function based framework to boost infrared target detection algorithms[J].Infrared Physics&Technology,2016,77:27-34.
[24]QIN Jian,CHEN Qian,QIAN Wei-xian.Dim and small target detection based on optical flow estimation and adaptive background suppression[J].Acta Photonica Sinica,2011,40(3):476-482.秦剑,陈钱,钱惟贤.基于光流估计和自适应背景抑制的弱小目标检测[J].光子学报,2011,40(3):476-482.