基于机器视觉的麦田杂草识别方法研究
|
摘要
杂草是影响我国农产品质量和产量的重要因素之一。目前除草主要靠喷洒除草剂，而且是大面积的均匀喷洒。这种喷洒方法不仅提高了农业的成本，也破坏了土地的质量，污染了环境，不利于农业的可持续发展。大量的实验表明田间杂草的分布是不均匀的，因此就要研究一种变量喷洒的方法，即在有杂草的地方喷洒，在没有杂草的地方或杂草密度很低的地方就停止喷洒。为了实现变量喷洒，首要问题就是要实现田间杂草的实时识别。本文就进行了基于图像处理技术的麦田行间杂草的实时识别方法的研究。
本文的研究是在实验的基础上进行的，实验系统的结构为在运动的机车上安装摄像头，通过采集卡和计算机连接。机车放置在一长6米宽1.5米高1米的平行轨道上，轨道下面是土壤箱，种植小麦和杂草，模拟田间环境。机车的运动方向和运动速度通过电气控制箱进行控制。采集的图像在计算机中进行处理，处理的结果是图像中杂草的分布密度，以此来控制除草剂的喷洒。
本文主要进行了以下的工作：
1、图像的动态采集：在实验室里，采集模拟田间环境的运动图像。
2、图像的滤波预处理：采集的图像中往往有一些噪声，在进行图像处理前要滤除掉这些噪声。本文采用了邻域均值法对图像进行了滤波预处理。
3、绿色植物和土壤背景的分割：可以利用植物和土壤不同的颜色特征进行分割。首先用超绿色方法对图像进行灰度化，然后对灰度图像选择合适的阈值进行二值化，就可以实现绿色植物和土壤背景物的分割。
4、杂草和作物的分割：本文尝试了用位置特征法对杂草和作物进行快速分割，并统计出杂草的密度。
Weed is one of the important factors, which damage the quality of the agricultural products. At present the method to weed is to spray the herbicide, and the means to spray is the well-distributed spraying. This method, not only improve the cost of agriculture but also damage the quality of field and pollute air. Study indicates that weed isn't well-distributed, so we should find a variable-controlling spraying method. It is to spray in the region where there are weed patches, and to stop in the region where there are not. In order to do so, the first thing is to realize the detection of weed patches. In this paper we study the method to detect the inter-row weeds in wheat field.
Our study is based on experiment, which is to fix the CCD camera in a vehicle which can move along a rail in the lab. The camera is linked with the computer. Under the rail is the soil box where weed and wheat are planted. The vehicle is controlled by the electric-control-box. The image is processed in the computer and the result is the density of weed in the image, which control the spraying of herbicide.
In this paper we do such works:
1.gather the dynamic-state-image in the lab ;
2.pre-process the image to remove the noise ;
3.partition the plant from the soil;
4.partition the weed with wheat, and count weed density.
本文的研究是在实验的基础上进行的，实验系统的结构为在运动的机车上安装摄像头，通过采集卡和计算机连接。机车放置在一长6米宽1.5米高1米的平行轨道上，轨道下面是土壤箱，种植小麦和杂草，模拟田间环境。机车的运动方向和运动速度通过电气控制箱进行控制。采集的图像在计算机中进行处理，处理的结果是图像中杂草的分布密度，以此来控制除草剂的喷洒。
本文主要进行了以下的工作：
1、图像的动态采集：在实验室里，采集模拟田间环境的运动图像。
2、图像的滤波预处理：采集的图像中往往有一些噪声，在进行图像处理前要滤除掉这些噪声。本文采用了邻域均值法对图像进行了滤波预处理。
3、绿色植物和土壤背景的分割：可以利用植物和土壤不同的颜色特征进行分割。首先用超绿色方法对图像进行灰度化，然后对灰度图像选择合适的阈值进行二值化，就可以实现绿色植物和土壤背景物的分割。
4、杂草和作物的分割：本文尝试了用位置特征法对杂草和作物进行快速分割，并统计出杂草的密度。
Weed is one of the important factors, which damage the quality of the agricultural products. At present the method to weed is to spray the herbicide, and the means to spray is the well-distributed spraying. This method, not only improve the cost of agriculture but also damage the quality of field and pollute air. Study indicates that weed isn't well-distributed, so we should find a variable-controlling spraying method. It is to spray in the region where there are weed patches, and to stop in the region where there are not. In order to do so, the first thing is to realize the detection of weed patches. In this paper we study the method to detect the inter-row weeds in wheat field.
Our study is based on experiment, which is to fix the CCD camera in a vehicle which can move along a rail in the lab. The camera is linked with the computer. Under the rail is the soil box where weed and wheat are planted. The vehicle is controlled by the electric-control-box. The image is processed in the computer and the result is the density of weed in the image, which control the spraying of herbicide.
In this paper we do such works:
1.gather the dynamic-state-image in the lab ;
2.pre-process the image to remove the noise ;
3.partition the plant from the soil;
4.partition the weed with wheat, and count weed density.
引文
[1] 魏守辉，万左玺，强胜，计算机在杂草科学中的应用及展望，杂草科学，2000第三期，7～10．
[2] 蒋正荣、王一鸣，计算机杂草识别的实现及应用，杂草科学，1999(4)：2～5
[3] 蒋正荣、王一鸣，计算机杂草识别技术的研究现状，上海环境科学，1999，18(10)：481～483
[4] 纪寿文、王荣本、陈佳娟、赵学笃，应用计算机图像处理技术识别玉米苗期田间杂草的研究，农业工程学报，2000，17(2)：154～155
[5] 贾云得编著，机器视觉，北京：科学出版社，2000
[6] 宋韬，应用计算机视觉进行作物籽粒形状识别的研究，中国农业大学(东区)论文，1995
[7] 苏光大著，微机图像处理系统，北京：清华大学出版社，2000
[8] 王新成编著，高级图像处理技术，北京：中国科学技术出版社，2001
[9] 相阿荣、王一鸣，利用色度法识别杂草和土壤背景物，中国农业大学学报，2000，5(4)：98～100
[10] 许俐、钱敏娟、方如明、罗玉坤，大米加工精度的图像识别方法，农业工程学报，1996，12(3)：172～175
[11] 袁祥辉等编著，固体图像处理技术及其应用，重庆：重庆大学出版社，1996
[12] 张朝贤、张跃进、倪汉文等编著，农田杂草防除手册，北京：中国农业出版社，2000
[13] 张朝贤、钱益新、，胡祥恩，农田化学除草与可持续发展农业，农药，1998(4)：8～12
[14] 张朝贤、钱益新，中国农田化学除草现状与努力方向，植保技术与推广，2001(10)：35～37
[15] 郑南宁，计算机视觉与模式识别，北京：国防工业出版社，1998：143～148
[16] 朱建楚、贺学礼、赵莉丽，麦田杂草对麦类作物生长的影响，国外农学，1996(3)：45～46
[17] 刘敏，基于分形的田间杂草图像分析与识别的研究，北京工业大学硕士论文，2002
[18] 夏良正，数字图像处理，东南大学出版社，1999．
[19] 王耀南等，计算机图像处理与识别技术，高等教育出版社，2001年6月．
[20] 夏德深，傅德胜，现代图像处理技术与应用，东南大学出版社，1997年12月，51～54
[21] zhang. N. and C. Chaisattapagon, "Effective criteria for weed identification in wheat fields , using machine vision", Transactions of the ASAE. 1995, Vol. 38(3)965-974.
[22] Woebbecke, D. M, G. E. Meyer, K. Vin Bargen et al, "Shape features for identifying young weeds using image analysis", ASAE, 1995, vol. 38(1):271-281.
[23] E. Blackshaw Robert , Merits of a weed-sensing sprayer to control weeds in conservation fall and cropping system, Weed Science 46, January-February 1998, 120-122.
[24] Suk Lee Won, Robotic Weed control system for tomatoes using machine vision system and precision chenical application , An ASAE Meeting Presentation , 97-3093, 1～14.
[25] Kondo Naoshi , weeds detection in lawn field by texture analysis using gray-level cooccurrence matrix, Proceedings of ARBIP95, Kobe, japan 1995, 195～197.
[26] Chaisattapagon, C. , and N. Zhang, 1992. Identifying effective criteria for
weed detection using machine vision. ASAE Paper No. 92-3605.
[27] Cooke, L. 1996. Smart sprayer selects weeds for elimination. Agricultural Research 44(4): 15.
[28] E. Blackshaw Robert, 1998. Merits of a weed-sensing sprayer to control weeds in conservation fallow and cropping systems. Weed Science 46:120～122
[29] Visser, R. and A. J. M. Timmermans. 1996. WEED-IT:a new selective weed control system. Proceedings of SPIE, Optics in Agriculture, Forestry, and Biological Processing Ⅱ 2907:120-129.
[30] Elfaki, M.S., N. Zhang, and D. E. Peterson, 1997. Weed detectio nusing color machine vision. ASAE Paper No. 97-3134
[31] Biller, R. H. , 1998. Reduced Input of Herbicides by Use of Optoelectronic Sensors. Journal of Agricultural Engineering Research. Vol. 71, 357 - 362.
[32] Felton, W. L. , and K. R. McCloy, 1992. Spot spraying. Agricultural Engineering, November 1992. , Vol. 73(6): 9-12
[33] H. J. Olsen, Determination of row position in small-grain crops by analysis of video images, Computers and Electronics in Agriculture 12 (1995) 147-162
[34] Franz, E. , M. R. Gebhardt, and K. B. Unklesbay. 1991. The use of local spectral properties of leaves as an aid for identifying weed seedlings in digital images. Transactions of the ASAE 34(2): 682-687.
[35] Ge Fan, Naiqian Zhang Dallas E. Peterson Thomas M. Loughin, 1998. Real-Time Weed Detection Using Machine Vision ASAE Paper No. 98-3032
[36] Gerhards-R, Kuhbauch-W, 1993. Dynamic decision model for weed control methods in cereals by means of digital image analysis. Journal of Agronomy and Crop Science. 171(5):329-335; 9 ref.
[37] Guyer, D. E. , G. E. Miles, M. M. Schreiber, O. R. Mitchell, and V. C. Vanderbuilt. 1986. Machine vision and image processing for plant identification. Transactions of ASAE 29(6): 1500-1507.
[38] Guyer, D. E. , G. E. Miles, L. D. Gaultney, and M. M. Schreiber. 1993. Application of machine vision to shape analysis in leaf and plant identification. Transactions of ASAE 36(1): 163-171.
[39] Haggar, R. J. , C. J. Stent, and S. Isaac. 1983. A prototype hand-held patch sprayer for killing weeds, activated by spectral differences in crop/weed canopies. Journal of Agricultural Engineering Research 281349-258.
[40] Johnson, G. A., D. A. Mortensen, and A. R. Martine, 1995. A simulation of herbicide use based on weed spatial distribution map. Weed Res. (Ⅰ Press. )
[41] Lee-WS, Slaughter-DC, Giles-DK, 1997. Robotic weed control system for tomatoes using machine vision system and precision chemical application. ASAE Paper No. 973093, 15 pp.
[42] Matas, J., R. Marik, and J. Kitter, 1995. Color-based Object recognition under spectrally non-uniform illumination. Image and Vision Computing. Vol. 13(9):663-669.
[43] Meyer-GE, Mehta-T, Kocher-MF, Mortensen-DA, Samal-A , 1998. Textural imaging and discriminant analysis for distinguishing weeds for spot spraying. Transactions of the ASAE 41(4): 1189-1197
[44] Paice MER. Miller PCH & Bodle JD, 1995. An experimental sprayer for the spatially selective application of herbicides. Journal of Agricultural Engineering Research. 60. 107-116.
[45] Petry-W, Kuhbauch-W,1989. Automated distinction of weed species using form parameters by means of digital image processing. Journal of Agronomy and Crop Science. 163(5):345-351; 17 ref.
[46] Shearer, S. A. and R. G. Holmes. 1990. Plant identification using color co-occurrence matrices. Transactions of ASAE 33(6): 2037-2044.
[47] Slaughter, D. C. and R. C. Harrell. 1989. Discriminating fruit for robotic harvest using color in natural outdoor scene. Transactions of the ASAE 32(2):757-763.
[48] B. L. Steward, L. F. Tian, 1999. Machine-vision weed density estimation for real-time , outdoor lighting conditions. Transaction of ASAE 42(6):1897-1909.
[49] Ning Wang, Naiqian Zhang, Yurui Sun, Development of a spectral-based weed sensor, 1999 ASAE Annual International Meeting.
[50] Ahmad-U, Kondo-N, Arima-S, Monta-M, Mohri-K , 1999. Weed detection in lawn field using machine vision: Utilization of textural features in segmented area. Journal of the Japanese Society of Agricultural Machinery 61 (2) :61-69
[51] Burks-TF, Shearer-SA, Gates-RS, Donohue-KD, 2000. Backpropagation neural network design and evaluation for classifying weed species using color image texture. Transactions of the ASAE 43(4): 1029-1037
[52] Brivot, R. and J. A. Marchant, 1996. Segmentation of plants and weeds for a precision crop protection robot using infrared images. IEE Proceedings on Vision, Image, and Signal Processing 143(2): 118-124.
[53] Borregaard-T, Nielsen-H, Norgaard-L, Have-H, 2000. Crop-weed discrimination by line imaging spectroscopy. Journal of Agricultural Engineering Research. 75: 4, 389-400; 28 ref.
[54] Mao wenhua, Machine vision system used for real-time detection inter-row weeds, Teansactions of CSAE, Vol. 19 No. 5, 114～117.
[2] 蒋正荣、王一鸣，计算机杂草识别的实现及应用，杂草科学，1999(4)：2～5
[3] 蒋正荣、王一鸣，计算机杂草识别技术的研究现状，上海环境科学，1999，18(10)：481～483
[4] 纪寿文、王荣本、陈佳娟、赵学笃，应用计算机图像处理技术识别玉米苗期田间杂草的研究，农业工程学报，2000，17(2)：154～155
[5] 贾云得编著，机器视觉，北京：科学出版社，2000
[6] 宋韬，应用计算机视觉进行作物籽粒形状识别的研究，中国农业大学(东区)论文，1995
[7] 苏光大著，微机图像处理系统，北京：清华大学出版社，2000
[8] 王新成编著，高级图像处理技术，北京：中国科学技术出版社，2001
[9] 相阿荣、王一鸣，利用色度法识别杂草和土壤背景物，中国农业大学学报，2000，5(4)：98～100
[10] 许俐、钱敏娟、方如明、罗玉坤，大米加工精度的图像识别方法，农业工程学报，1996，12(3)：172～175
[11] 袁祥辉等编著，固体图像处理技术及其应用，重庆：重庆大学出版社，1996
[12] 张朝贤、张跃进、倪汉文等编著，农田杂草防除手册，北京：中国农业出版社，2000
[13] 张朝贤、钱益新、，胡祥恩，农田化学除草与可持续发展农业，农药，1998(4)：8～12
[14] 张朝贤、钱益新，中国农田化学除草现状与努力方向，植保技术与推广，2001(10)：35～37
[15] 郑南宁，计算机视觉与模式识别，北京：国防工业出版社，1998：143～148
[16] 朱建楚、贺学礼、赵莉丽，麦田杂草对麦类作物生长的影响，国外农学，1996(3)：45～46
[17] 刘敏，基于分形的田间杂草图像分析与识别的研究，北京工业大学硕士论文，2002
[18] 夏良正，数字图像处理，东南大学出版社，1999．
[19] 王耀南等，计算机图像处理与识别技术，高等教育出版社，2001年6月．
[20] 夏德深，傅德胜，现代图像处理技术与应用，东南大学出版社，1997年12月，51～54
[21] zhang. N. and C. Chaisattapagon, "Effective criteria for weed identification in wheat fields , using machine vision", Transactions of the ASAE. 1995, Vol. 38(3)965-974.
[22] Woebbecke, D. M, G. E. Meyer, K. Vin Bargen et al, "Shape features for identifying young weeds using image analysis", ASAE, 1995, vol. 38(1):271-281.
[23] E. Blackshaw Robert , Merits of a weed-sensing sprayer to control weeds in conservation fall and cropping system, Weed Science 46, January-February 1998, 120-122.
[24] Suk Lee Won, Robotic Weed control system for tomatoes using machine vision system and precision chenical application , An ASAE Meeting Presentation , 97-3093, 1～14.
[25] Kondo Naoshi , weeds detection in lawn field by texture analysis using gray-level cooccurrence matrix, Proceedings of ARBIP95, Kobe, japan 1995, 195～197.
[26] Chaisattapagon, C. , and N. Zhang, 1992. Identifying effective criteria for
weed detection using machine vision. ASAE Paper No. 92-3605.
[27] Cooke, L. 1996. Smart sprayer selects weeds for elimination. Agricultural Research 44(4): 15.
[28] E. Blackshaw Robert, 1998. Merits of a weed-sensing sprayer to control weeds in conservation fallow and cropping systems. Weed Science 46:120～122
[29] Visser, R. and A. J. M. Timmermans. 1996. WEED-IT:a new selective weed control system. Proceedings of SPIE, Optics in Agriculture, Forestry, and Biological Processing Ⅱ 2907:120-129.
[30] Elfaki, M.S., N. Zhang, and D. E. Peterson, 1997. Weed detectio nusing color machine vision. ASAE Paper No. 97-3134
[31] Biller, R. H. , 1998. Reduced Input of Herbicides by Use of Optoelectronic Sensors. Journal of Agricultural Engineering Research. Vol. 71, 357 - 362.
[32] Felton, W. L. , and K. R. McCloy, 1992. Spot spraying. Agricultural Engineering, November 1992. , Vol. 73(6): 9-12
[33] H. J. Olsen, Determination of row position in small-grain crops by analysis of video images, Computers and Electronics in Agriculture 12 (1995) 147-162
[34] Franz, E. , M. R. Gebhardt, and K. B. Unklesbay. 1991. The use of local spectral properties of leaves as an aid for identifying weed seedlings in digital images. Transactions of the ASAE 34(2): 682-687.
[35] Ge Fan, Naiqian Zhang Dallas E. Peterson Thomas M. Loughin, 1998. Real-Time Weed Detection Using Machine Vision ASAE Paper No. 98-3032
[36] Gerhards-R, Kuhbauch-W, 1993. Dynamic decision model for weed control methods in cereals by means of digital image analysis. Journal of Agronomy and Crop Science. 171(5):329-335; 9 ref.
[37] Guyer, D. E. , G. E. Miles, M. M. Schreiber, O. R. Mitchell, and V. C. Vanderbuilt. 1986. Machine vision and image processing for plant identification. Transactions of ASAE 29(6): 1500-1507.
[38] Guyer, D. E. , G. E. Miles, L. D. Gaultney, and M. M. Schreiber. 1993. Application of machine vision to shape analysis in leaf and plant identification. Transactions of ASAE 36(1): 163-171.
[39] Haggar, R. J. , C. J. Stent, and S. Isaac. 1983. A prototype hand-held patch sprayer for killing weeds, activated by spectral differences in crop/weed canopies. Journal of Agricultural Engineering Research 281349-258.
[40] Johnson, G. A., D. A. Mortensen, and A. R. Martine, 1995. A simulation of herbicide use based on weed spatial distribution map. Weed Res. (Ⅰ Press. )
[41] Lee-WS, Slaughter-DC, Giles-DK, 1997. Robotic weed control system for tomatoes using machine vision system and precision chemical application. ASAE Paper No. 973093, 15 pp.
[42] Matas, J., R. Marik, and J. Kitter, 1995. Color-based Object recognition under spectrally non-uniform illumination. Image and Vision Computing. Vol. 13(9):663-669.
[43] Meyer-GE, Mehta-T, Kocher-MF, Mortensen-DA, Samal-A , 1998. Textural imaging and discriminant analysis for distinguishing weeds for spot spraying. Transactions of the ASAE 41(4): 1189-1197
[44] Paice MER. Miller PCH & Bodle JD, 1995. An experimental sprayer for the spatially selective application of herbicides. Journal of Agricultural Engineering Research. 60. 107-116.
[45] Petry-W, Kuhbauch-W,1989. Automated distinction of weed species using form parameters by means of digital image processing. Journal of Agronomy and Crop Science. 163(5):345-351; 17 ref.
[46] Shearer, S. A. and R. G. Holmes. 1990. Plant identification using color co-occurrence matrices. Transactions of ASAE 33(6): 2037-2044.
[47] Slaughter, D. C. and R. C. Harrell. 1989. Discriminating fruit for robotic harvest using color in natural outdoor scene. Transactions of the ASAE 32(2):757-763.
[48] B. L. Steward, L. F. Tian, 1999. Machine-vision weed density estimation for real-time , outdoor lighting conditions. Transaction of ASAE 42(6):1897-1909.
[49] Ning Wang, Naiqian Zhang, Yurui Sun, Development of a spectral-based weed sensor, 1999 ASAE Annual International Meeting.
[50] Ahmad-U, Kondo-N, Arima-S, Monta-M, Mohri-K , 1999. Weed detection in lawn field using machine vision: Utilization of textural features in segmented area. Journal of the Japanese Society of Agricultural Machinery 61 (2) :61-69
[51] Burks-TF, Shearer-SA, Gates-RS, Donohue-KD, 2000. Backpropagation neural network design and evaluation for classifying weed species using color image texture. Transactions of the ASAE 43(4): 1029-1037
[52] Brivot, R. and J. A. Marchant, 1996. Segmentation of plants and weeds for a precision crop protection robot using infrared images. IEE Proceedings on Vision, Image, and Signal Processing 143(2): 118-124.
[53] Borregaard-T, Nielsen-H, Norgaard-L, Have-H, 2000. Crop-weed discrimination by line imaging spectroscopy. Journal of Agricultural Engineering Research. 75: 4, 389-400; 28 ref.
[54] Mao wenhua, Machine vision system used for real-time detection inter-row weeds, Teansactions of CSAE, Vol. 19 No. 5, 114～117.