| تعداد نشریات | 282 |
| تعداد نشریات سازمان | 80 |
| تعداد شماره‌ها | 3,262 |
| تعداد مقالات | 36,058 |
| تعداد مشاهده مقاله | 55,187,118 |
| تعداد دریافت فایل اصل مقاله | 94,185,814 |
طراحی، ساخت و ارزیابی سامانه سمپاش خودکار به منظور تشخیص برخط علفهرز-گیاه در مزارع چغندرقند | ||
| چغندرقند | ||
| مقاله 8، دوره 37، شماره 2، مهر 1400، صفحه 223-238 اصل مقاله (1.01 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22092/jsb.2022.355302.1298 | ||
| نویسندگان | ||
| هادی اورک1؛ سامان آبدانان مهدی زاده* 2؛ محمدامین آسودار3؛ الهام الهی فرد4 | ||
| 1کارشناسی ارشد پردازش تصویر، دانشکده مهندسی زراعی و عمران روستایی، گروه مکانیک بیوسیستم، دانشگاه علوم کشاورزی و منابع طبیعی خوزستان. اهواز، ایران. | ||
| 2دانشیار دانشکده مهندسی زراعی و عمران روستایی، گروه مکانیک بیوسیستم، دانشگاه علوم کشاورزی و منابع طبیعی خوزستان. اهواز، ایران. | ||
| 3استاد دانشکده مهندسی زراعی و عمران روستایی، گروه مکانیک بیوسیستم، دانشگاه علوم کشاورزی و منابع طبیعی خوزستان، اهواز، ایران | ||
| 4استادیار دانشکده کشاورزی، گروه زراعت، دانشگاه علوم کشاورزی و منابع طبیعی خوزستان، اهواز، ایران | ||
| چکیده | ||
| کنترل علفهای هرز در دوره رشد گیاهان بسیار مورد توجه بوده و روشهای مختلفی بدین منظور توسعه یافته است. در مبارزه با این گیاهان ناخواسته با روش مرسوم تمام مزرعه و گیاه اصلی نیز مورد حمله علفکش قرار میگیرد که سبب مصرف بی‌رویه سموم نیز میشود. در این پژوهش یک سامانه سمپاش هوشمند به‌منظور تشخیص علفهرز و بررسی میزان کاهش مصرف سم، در مزرعه چغندرقند بر اساس فناوری بینایی ماشین ((Machine Vision ارائه شد. به این منظور 49 ویژگیهای ظاهری و رنگی چغندرقند و علفهرز از تصاویر استخراج و مورد بررسی قرار گرفتند. با پیادهسازی الگوریتم ژنتیک (GA) 11 ویژگی که بیشترین دقت در تشخیص را داشتند انتخاب و به منظور افزایش سرعت و بهترین عملکرد پنج ویژگی (ضریب شعاع ناحیه محدب هال، ضریب کرویت، ممان ششم، I1I2I3_I3 و Lch_c) که بیشترین تکرار را در انتخاب ویژگی داشتند، برگزیده شدند. الگوریتم توسعه یافته برای تشخیص علف هرز از چغندرقند، دقت بیش از 98 درصد داشت که نشان از قدرت تشخیص بالای این سامانه هوشمند میباشد. جهت بررسی میزان کاهش مصرف محلول سم، سامانه سمپاش هوشمند با سمپاش بافرآگری ((Buferagri مورد مقایسه قرار گرفت. سرعت حرکت هشت کیلومتر بر ساعت با تراکتور نوع جاندایر و مسافت پیموده شده 27 متر برای هر دو سمپاش ثابت در نظر گرفته شد. در یک مسافت مشخص میزان علفکش مصرفی اندازهگیری و در نهایت میزان مصرف محلول توسط سمپاش بافرآگری نسبت به سامانه سمپاش هوشمند بیش از 77 درصد بود. این مساله نشان از کارایی این سامانه نسبت به سمپاشهای معمولی در کاهش مصرف علفکش است. نتایج نشان دادند که استفاده از سامانه ارائه شده به صورت سیستم سمپاش هوشمند در مزارع چغندرقند امکان‌پذیر است. | ||
| کلیدواژه‌ها | ||
| الگوریتم ژنتیک؛ بینایی ماشین؛ پردازش تصویر؛ چغندرقند؛ سمپاش هوشمند؛ کاهش مصرف سم | ||
| عنوان مقاله [English] | ||
| Design, construction and evaluation of an automatic sprayer system online weed-plant detection in sugar beet fields | ||
| نویسندگان [English] | ||
| H. Orak1؛ S. Abdanan Mehdizadeh2؛ M.A. Asoodar3؛ E. ٍElahifard4 | ||
| 1Master of Science in Biosystems engineering of Department of Mechanics of Biosystems Engineering, Faculty of Agricultural Engineering and Rural Development, Agricultural Sciences and Resources University of Khuzestan, Ahvaz, Iran. | ||
| 2Associate Professor, Department of Mechanics of Biosystems Engineering, Faculty of Agricultural Engineering and Rural Development, Agricultural Sciences and Resources University of Khuzestan, Ahvaz, Iran. | ||
| 3Professor of Department of Mechanics of Biosystems Engineering, Faculty of Agricultural Engineering and Rural Development, Agricultural Sciences and Resources University of Khuzestan, Ahvaz, Iran. | ||
| 4Assistant Professor, Department of Agronomy, Faculty of Agricultural, Agricultural Sciences and Resources University of Khuzestan, Ahvaz, Iran. | ||
| چکیده [English] | ||
| Weed control during the growth period of plantsis of great importance and various methods have been developed for this purpose. In the fight against these unwanted plants with the conventional method, the entire field as well as the main plant are covered by herbicides, which also causes excessive application of herbicide. In this study, a smart sprayer system was used to detect weed and reduce the amount of herbicide application in sugar beet field based on machine vision technology. For this purpose, 49 phenotype and color characteristics of beet and weed images were extracted and analyzed. By implementing Genetic Algorithm (GA), 11 characteristics that were most accurate in diagnosis were selected, and in order to increase the speed and improve performance, five characteristics (area ratio of convex hull, sphericity coefficient, moment 6, I1I2I3 and Lch_c) with had the most replication number in characteristic selection were selected. The developed algorithm to distinguish weed from sugar beet had an accuracy of more than 98%, which shows the high detection power of this smart system. To evaluate the reduction of herbicide usage, the smart sprayer system was compared with the Buferagri sprayer. The movement speed of 8 km hr-1 with John Deere tractor and 27 m travelled distance were considered to be fixed for both sprayers. In a certain distance, the amount of herbicide used was measured and it could be observed that the amount of herbicide used in the Buferagri sprayer was 77% higher than the smart sprayer system. This shows the efficiency of this system compared with conventional sprayers in reducing herbicides application. These results indicate the feasibility of using the presented system as a smart sprayer system in sugar beet fields. | ||
| کلیدواژه‌ها [English] | ||
| Genetic Algorithm, Herbicide reduction Weed, Image processing, Smart sprayer, Sugar beet | ||
| مراجع | ||
|
Abbas I, Liu J, Faheem M, Noor RS, Shaikh SA, Solangi KA, Raza SM. Different real-time sensor technologies for the application of variable-rate spraying in agriculture. Sensors and Actuators A: Physical, 2020. 112265. Abouzahir S, Sadik M, Sabir E. Bag-of-visual-words-augmented histogram of oriented gradients for efficient weed detection. Biosystems Engineering. 2021; 202: 179-194. Anonymous. Yield and cultivated area of Iranian sugar beet in 2021. Iranian Sugar Factories Syndicate. 2021. http://www.isfs.ir (in Persian) ASAE Standards S 217.12; Three-Point Free-Link Attachment for hitching implements to agricultural wheel tractors. American Society of Agricultural and Biological Engineers: St. Joseph, MI, USA, 2001. Babu LG. Smart agriculture system with E– Carbage using Iot. International Journal of Modern Agriculture. 2021; 10(1): 928-931. Bakhshipour Ziyaratgahi A, Jafari A, Emam Y, Nasiri SM, Kamgar S, Zare D. Use of modified huff in detection of sugar beet plant from grassland using machine vision. Journal of Agricultural Machinery. 2017; 7 (1): 73-85. (in Persian with English abstract) Burgos- Artizzu XP, Ribeiro A, Guijarro M, Pajares G. Real-time image processing for crop-weed discrimination in maize fields. Computer and Electronic in Agriculture. 2011; 75(2): 337–346. Cao X, Ning B, Yan P, Li X. Selecting key poses on manifold for pair-wise action recognition. Industrial Informatics, IEEE Transactions. 2012; 8(1): 168-177. Chapron M, Requena-Esteso M, Boissard P, Assemat L. A method for recognizing vegetal species from multispectral images. 2nd European Conference on Precision Agriculture Odense Congress Centre, Denmark. 1999. Christensen S, Heisel T, Walter M. Patch spraying in cereals. Proc. of Second Int. Weed Control Congress, Copenhagen, Denmark. 1996; pp. 963–938. Dammer KH. Real‐time variable‐rate herbicide application for weed control in carrots. Weed research; 2016. 56(3): 237-246. Du JX, Wang XF, zhang GJ. Leaf shape based plant species Recognition. Applied Mathematics and Computation. 2007; 185: 883-893. Food and Agriculture Organization (FAO) of the United Nations. FAOSTAT statistical database. 2019. Garcia-Mateos G, Hernandez-Hernandez JL, Escarabajal- Henarejos D, Jaen-Terrones S, Molina-Martinez J M. Study and comparison of color models for automatic image analysis in irrigation management applications. Agricultural Water Management. 2015; 151, 158-66. Guerrero JM, Guijarro M, Montalvo M, Romo J, Emmi L, Ribeiro A, Pajares G. Automatic expert system based on images for accuracy crop row detection in maize Fields. Expert Systems with Applications. 2013; 40: 656-664. Guerrero JM, Pajares G, Montalvo M, Romo J, Guijarro M. Support vector machines for crop/weeds identification in maize fields. Expert Systems with Applications. 2012; 39: 11149-11155. Hamuda E, Mc Ginley B, Glavin M, Jones E. Automatic crop detection under field conditions using the HSV colour space and morphological operations. Computers and Electronics in Agriculture. 2017; 133: 97–107. Hasan AM, Sohel F, Diepeveen D, Laga H, Jones MG. A survey of deep learning techniques for weed detection from images. Computers and Electronics in Agriculture. 2021; 184, 106067. HunterLab. Application note. Insight on Color. 2001; 13: 1-4. ISO 730. Agricultural Wheeled Tractors—Rear-Mounted Three-Point Linkage Categories 1N, 1, 2N, 2, 3N, 3, 4N and 4. American Society of Agricultural and Biological Engineers: St. Joseph, MI, USA, 2009; 1. Jafari A, Mohtasebi SS, Eghbali Jahromi H, Omid M. Presenting a suitable algorithm for separating weeds from sugar beet in real field conditions using image processing. International Journal of Agriculture and Biology. 2006; 8(5):602–605. Jahada Akbar MR, Tabatabaei Nimavard R, Ebrahimian HD. Investigation of the critical period of sugar beet weed control in Kabutarabad Isfahan. Journal of Sugar Beet. 2004; 20(1): 73-92. (in Persian with English abstract) Kanungo T, Mount DM, Netanyahu NS, Piatko CD, Silverman R, Wu AY. An efficient k-means clustering algorithm: Analysis and implementation. Pattern Analysis and Machine Intelligence, IEEE Transactions, 2002; 24(7): 881–892. Lin WM, Hu YT. Image segmentation method based on YUV color space for tomato harvesting robot. Trans. Chin. Society of Agricultural Engineering. 2012; 43(12): 176–180. Liu B, Bruch R. Weed detection for selective spraying: A review. Current Robotics Reports. 2020; 1(1): 19-26. Mohammad Zamani D, Minaei S, Alimardani R, Almasi M, Norouz poordeilami H, Rostami A. Design and fabrication of a map- based VRA system for a tractor- mounted boom-type field sprayer. Iranian Journal of Biosystems Engineering. 2013; 43(2): 111-123. (in Persian with English abstract) Montazeri EZ, Jodaii A, Zomorodi S, Hanaeh M, Habibi R. Investigating the effects of nitrogen and animal manure (poultry manure) and their mutual effects on the quantity and quality of tomatoes. Soil and Water Research Institute. Plan No. 102-15-19-82-059. 2013. (in Persian) Nadafzadeh M, Mehdizadeh SA. Design and fabrication of an intelligent control system for determination of watering time for turfgrass plant using computer vision system and artificial neural network. Precision Agriculture. 2019; 20(5): 857-879. Ohta Y, Kanade T, Sakai T. Color information for region segmentation. Computer. Graphics Image Process, 1980; 13(3): 222–241. Oluleye B, Leisa A, Leng L, Dean D. A Genetic Algorithm-Based Feature Selection. International Journal of Electronics Communication and Computer Engineering. 2014; 5(4) 2249–071. Perez AJ, Lopez F, Benlloch JV, Christensen S. Color and shape analysis techniques for weed detection in cereal fields. Computer and Electronic in Agriculture. 2000; 25(3): 197–212. Philipp I, Rath T. Improving plant discrimination in image processing by use of different colour space transformations. Computers and Electronics in Agriculture. 2002; 35: 1–15. Rani SV, Kumar PS, Priyadharsini R, Srividya SJ, Harshana S. Automated weed detection system in smart farming for developing sustainable agriculture. International Journal of Environmental Science and Technology. 2021; 1-12. Sabzi S, Abbaspour-Gilandeh Y, Arribas JI. an automatic visible-range video weed detection. Segmentation and classification prototype in potato field, Heliyon. 2020; 6(5): 03685. Sabzi S, Abbaspour-Gilandeh Y, García-Mateos G. A fast and accurate expert system for weed identification in potato crops using metaheuristic algorithms. Computers in Industry. 2018; 98: 80–89. Sester M, Delanoy M, Colbach N, Darmency H. Crop and density effect on weed beet growth and reproduction. Weed Research. 2004; 44: 50–59. Subr A, Parafiniuk S, Milanowski M, Krawczuk A, Kachel M. Study of deposited spray quality of spraying agents with different physical properties. Plant archives. 2020; 20(2): 6109-6114. Tang J, Wang D, Zhang Z, He L, Xin J, Xu Y. Weed identification based on K-means feature learning combined with convolutional neural network. Computers and Electronics in Agriculture. 2017; 135: 63–70. Tewari VK, Pareek CM, Lal G, Dhruw LK, Singh N. Image processing based real-time variable-rate chemical spraying system for disease control in paddy crop. Artificial Intelligence in Agriculture. 2020; 4: 21-30. Watchareeruetai U, Takeuchi Y, Matsumoto T, Kudo H, Ohnishi N. Computer vision based methods for detecting weeds in lawns. Machine Vision and Applications. 2006; 17(5): 287-296. Zoschke A, Quadranti M. Integrated weed management: Quo vadis. Weed Biology. 2002; 2: 1-10. | ||
|
آمار تعداد مشاهده مقاله: 1,099 تعداد دریافت فایل اصل مقاله: 682 |
||