基于机器视觉的不同类型甘蔗茎节识别
|
摘要
针对不同种类甘蔗表面多样性和复杂性等因素导致甘蔗图像的茎节难以识别问题,提出一种基于机器视觉且适合各种类型甘蔗的茎节识别方法。首先,通过迭代拟合法从原始图像中提取甘蔗目标区域,并估计甘蔗目标与横轴的倾斜角度,根据倾斜角度参数旋转甘蔗目标成近似平行横轴姿态;然后,利用双密度双树复小波变换(DD-DTCWT)对图像进行分解,使用不同层次的垂直和近似垂直方向的小波系数重构图像;最后,运用图像直线检测算法对重构图像进行检测,得到甘蔗茎节部位的边缘线,对边缘线的密度、长度、相互距离信息进一步验证便可实现甘蔗茎节的识别和定位。实验结果显示甘蔗茎节完整识别率达到92%,约80%的茎节的定位精度小于16个像素,95%的茎节的定位精度小于32个像素,所提方法在不同的图像背景下,都能够成功地对不同类型的甘蔗进行茎节识别,并且定位精度高。
The sugarcane node is difficult to recognize due to the diversity and complexity of surface that different types of sugarcane have. To solve the problem, a sugarcane node recognition method suitable for different types of sugarcane was proposed based on machine vision. Firstly, by the iterative linear fitting algorithm, the target region was extracted from the original image and its slope angle to horizontal axis was estimated. According to the angle, the target was rotated to being nearly parallel to the horizontal axis. Secondly, Double-Density Dual Tree Complex Wavelet Transform(DD-DTCWT) was used to decompose the image, and the image was reconstructed by using the wavelet coefficients that were perpendicular or approximately perpendicular to the horizontal axis. Finally, the line detection algorithm was used to detect the image, and the lines near the sugarcane node were obtained. The recognition was realized by further verifying the density, length and mutual distances of the edge lines. Experimental results show that the complete recognition rate reaches 92%, the localization accuracy of about 80% of nodes is less than 16 pixels, and the localization accuracy of 95% nodes is less than 32 pixels. The proposed method realizes node recognition for different types of sugarcane under different background with high position accuracy.
The sugarcane node is difficult to recognize due to the diversity and complexity of surface that different types of sugarcane have. To solve the problem, a sugarcane node recognition method suitable for different types of sugarcane was proposed based on machine vision. Firstly, by the iterative linear fitting algorithm, the target region was extracted from the original image and its slope angle to horizontal axis was estimated. According to the angle, the target was rotated to being nearly parallel to the horizontal axis. Secondly, Double-Density Dual Tree Complex Wavelet Transform(DD-DTCWT) was used to decompose the image, and the image was reconstructed by using the wavelet coefficients that were perpendicular or approximately perpendicular to the horizontal axis. Finally, the line detection algorithm was used to detect the image, and the lines near the sugarcane node were obtained. The recognition was realized by further verifying the density, length and mutual distances of the edge lines. Experimental results show that the complete recognition rate reaches 92%, the localization accuracy of about 80% of nodes is less than 16 pixels, and the localization accuracy of 95% nodes is less than 32 pixels. The proposed method realizes node recognition for different types of sugarcane under different background with high position accuracy.
引文
[1]韦巧,杨宝玲,高振江.我国甘蔗产业化现状浅析[J].农机化研究,2015,37(4):247-253.(WEI Q,YANG B L,GAO Z J.Analysis of current situation of sugar cane industry[J].Journal of Agricultural Mechanization Research,2015,37(4):247-253.)
[2]MOSHASHAI K,ALMASI M,MINAEI S,et al.Identification of sugarcane nodes using image processing and machine vision technology[J].International Journal of Agricultural Research,2008,3(5):357-364.
[3]陆尚平,文友先,葛维,等.基于机器视觉的甘蔗茎节特征提取与识别[J].农业机械学报,2010,41(10):190-194.(LU S P,WEN Y X,GE W,et al.Recognition and features extraction of sugarcane nodes based on machine vision[J].Transactions of the Chinese Society of Agricultural Machinery,2010,41(10):190-194.)
[4]乔曦.基于计算机视觉的甘蔗种茎切割防伤芽系统的研究[D].南宁:广西大学,2013:24-36.(QIAO X.System of sugarcane cutting device to protect the bud based on computer vision[D].Nanning:Guangxi University,2013:24-36.)
[5]黄亦其,乔曦,唐书喜,等.基于Matlab的甘蔗茎节特征分布定位与试验[J].农业机械学报,2013,44(10):93-97.(HUANG Y Q,QIAO X,TANG S X,et al.Localization and test of characteristics distribution for sugarcane internode based on Matlab[J].Transactions of the Chinese Society for Agricultural Machinery,2013,44(10):93-97.)
[6]张卫正,董寿银,齐晓祥,等.基于图像处理的甘蔗茎节识别与定位[J].农机化研究,2016,38(4):217-221.(ZHANG WZ,DONG S Y,QI X X,et al.The identification and location of sugarcane internode based on image processing[J].Journal of Agricultural Mechanization Research,2016,38(4):217-221.)
[7]KINGSBURY N.Image processing with complex wavelets[J].Philosophical Transactions of the Royal Society A:Mathematical,Physical and Engineering Sciences,1999,357(1760):2543-2560.
[8]SELESNICK I W.The double-density dual-tree DWT[J].IEEETransactions on Signal Processing,2004,52(5):1304-1314.
[9]SELESNICK I W,BARANIUK R G,KINGSBURY N.The dualtree complex wavelet transform[J].IEEE Signal Processing Magazine,2005,22(6):231-239.
[10]黄学优,张长江.双树复小波域的MRI图像去噪[J].中国图象图形学报,2016,21(1):104-113.(HUANG X Y,ZHANGC J.MRI denoising based on dual-tree complex wavelet transform[J].Journal of Image and Graphics,2016,21(1):104-113.)
[11]CHEN S,QIU B,ZHAO F,et al.Fast compressed sensing MRIbased on complex double-density dual-tree discrete wavelet transform[J].International Journal of Biomedical Imaging,2017,2017:9604178.
[12]YASIN A S,PAVLOVA O N,PAVLOV A N.Speech signal filtration using double-density dual-tree complex wavelet transform[J].Technical Physics Letters,2016,42(8):865-867.
[13]HU H F.Illumination invariant face recognition based on dual-tree complex wavelet transform[J].IET Computer Vision,2015,9(2):163-173.
[14]KRISHNA M H,KUMAR G S.A noise based hybrid thresholding for enhanced noise reduction using double density dual tree complex wavelet transform[C]//Proceedings of the 2015 13th International Conference on Electromagnetic Interference and Compatibility.Piscataway,NJ:IEEE,2015:208-211.
[15]ZHANG Y,BI S.Quantum-inspired remote sensing image denoising with double density dual-tree complex wavelet transform[C]//Proceedings of SPIE 9299.Bellingham,WA:SPIE Press,2014:199-229.
[16]武士想,尚鹏,王立功.小波-Lagrange方法进行医学图像层间插值[J].中国图象图形学报,2016,21(1):78-85.(WU SX,SHANG P,WANG L G.Inter-slice interpolation for medical images by using the wavelet-Lagrange method[J].Journal of Image and Graphics,2016,21(1):78-85.)
[17]von GIOI R G,JAKUBOWICZ J,MOREL J M,et al.LSD:a fast line segment detector with a false detection control[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2010,32(4):722-732.
[18]BURNS J B,HANSON A R,RISEMAN E M.Extracting straight lines[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,8(4):425-455.
[19]AKINLAR C,TOPAL C.EDLines:a real-time line segment detector with a false detection control[J].Pattern Recognition Letters,2011,32(13):1633-1642.
[20]SALAN Y,MARLET R,MONASSE P.The multiscale line segment detector[C]//RRPR 2016:Proceedings of the 2016 Reproducible Research in Pattern Recognition,LNCS 10214.Berlin:Springer,2016:167-178.
[21]WEI H,YANG C,YU Q.Contour segment grouping for object detection[J].Journal of Visual Communication and Image Representation,2017,48:292-309.
[22]TANG G,XIAO Z,LIU Q,et al.A novel airport detection method via line segment classification and texture classification[J].IEEEGeoscience&Remote Sensing Letters,2015,12(12):2408-2412.
[23]IZADI M,SAEEDI P.Three-dimensional polygonal building model estimation from single satellite images[J].IEEE Transactions on Geoscience&Remote Sensing,2012,50(6):2254-2272.
[24]BAE G Y,HA J M,JEON J Y,et al.LED traffic sign detection using rectangular Hough transform[C]//Proceedings of the 2014International Conference on Information Science&Applications.Piscataway,NJ:IEEE,2014:1-4.
[2]MOSHASHAI K,ALMASI M,MINAEI S,et al.Identification of sugarcane nodes using image processing and machine vision technology[J].International Journal of Agricultural Research,2008,3(5):357-364.
[3]陆尚平,文友先,葛维,等.基于机器视觉的甘蔗茎节特征提取与识别[J].农业机械学报,2010,41(10):190-194.(LU S P,WEN Y X,GE W,et al.Recognition and features extraction of sugarcane nodes based on machine vision[J].Transactions of the Chinese Society of Agricultural Machinery,2010,41(10):190-194.)
[4]乔曦.基于计算机视觉的甘蔗种茎切割防伤芽系统的研究[D].南宁:广西大学,2013:24-36.(QIAO X.System of sugarcane cutting device to protect the bud based on computer vision[D].Nanning:Guangxi University,2013:24-36.)
[5]黄亦其,乔曦,唐书喜,等.基于Matlab的甘蔗茎节特征分布定位与试验[J].农业机械学报,2013,44(10):93-97.(HUANG Y Q,QIAO X,TANG S X,et al.Localization and test of characteristics distribution for sugarcane internode based on Matlab[J].Transactions of the Chinese Society for Agricultural Machinery,2013,44(10):93-97.)
[6]张卫正,董寿银,齐晓祥,等.基于图像处理的甘蔗茎节识别与定位[J].农机化研究,2016,38(4):217-221.(ZHANG WZ,DONG S Y,QI X X,et al.The identification and location of sugarcane internode based on image processing[J].Journal of Agricultural Mechanization Research,2016,38(4):217-221.)
[7]KINGSBURY N.Image processing with complex wavelets[J].Philosophical Transactions of the Royal Society A:Mathematical,Physical and Engineering Sciences,1999,357(1760):2543-2560.
[8]SELESNICK I W.The double-density dual-tree DWT[J].IEEETransactions on Signal Processing,2004,52(5):1304-1314.
[9]SELESNICK I W,BARANIUK R G,KINGSBURY N.The dualtree complex wavelet transform[J].IEEE Signal Processing Magazine,2005,22(6):231-239.
[10]黄学优,张长江.双树复小波域的MRI图像去噪[J].中国图象图形学报,2016,21(1):104-113.(HUANG X Y,ZHANGC J.MRI denoising based on dual-tree complex wavelet transform[J].Journal of Image and Graphics,2016,21(1):104-113.)
[11]CHEN S,QIU B,ZHAO F,et al.Fast compressed sensing MRIbased on complex double-density dual-tree discrete wavelet transform[J].International Journal of Biomedical Imaging,2017,2017:9604178.
[12]YASIN A S,PAVLOVA O N,PAVLOV A N.Speech signal filtration using double-density dual-tree complex wavelet transform[J].Technical Physics Letters,2016,42(8):865-867.
[13]HU H F.Illumination invariant face recognition based on dual-tree complex wavelet transform[J].IET Computer Vision,2015,9(2):163-173.
[14]KRISHNA M H,KUMAR G S.A noise based hybrid thresholding for enhanced noise reduction using double density dual tree complex wavelet transform[C]//Proceedings of the 2015 13th International Conference on Electromagnetic Interference and Compatibility.Piscataway,NJ:IEEE,2015:208-211.
[15]ZHANG Y,BI S.Quantum-inspired remote sensing image denoising with double density dual-tree complex wavelet transform[C]//Proceedings of SPIE 9299.Bellingham,WA:SPIE Press,2014:199-229.
[16]武士想,尚鹏,王立功.小波-Lagrange方法进行医学图像层间插值[J].中国图象图形学报,2016,21(1):78-85.(WU SX,SHANG P,WANG L G.Inter-slice interpolation for medical images by using the wavelet-Lagrange method[J].Journal of Image and Graphics,2016,21(1):78-85.)
[17]von GIOI R G,JAKUBOWICZ J,MOREL J M,et al.LSD:a fast line segment detector with a false detection control[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2010,32(4):722-732.
[18]BURNS J B,HANSON A R,RISEMAN E M.Extracting straight lines[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,8(4):425-455.
[19]AKINLAR C,TOPAL C.EDLines:a real-time line segment detector with a false detection control[J].Pattern Recognition Letters,2011,32(13):1633-1642.
[20]SALAN Y,MARLET R,MONASSE P.The multiscale line segment detector[C]//RRPR 2016:Proceedings of the 2016 Reproducible Research in Pattern Recognition,LNCS 10214.Berlin:Springer,2016:167-178.
[21]WEI H,YANG C,YU Q.Contour segment grouping for object detection[J].Journal of Visual Communication and Image Representation,2017,48:292-309.
[22]TANG G,XIAO Z,LIU Q,et al.A novel airport detection method via line segment classification and texture classification[J].IEEEGeoscience&Remote Sensing Letters,2015,12(12):2408-2412.
[23]IZADI M,SAEEDI P.Three-dimensional polygonal building model estimation from single satellite images[J].IEEE Transactions on Geoscience&Remote Sensing,2012,50(6):2254-2272.
[24]BAE G Y,HA J M,JEON J Y,et al.LED traffic sign detection using rectangular Hough transform[C]//Proceedings of the 2014International Conference on Information Science&Applications.Piscataway,NJ:IEEE,2014:1-4.