基于BP神經(jīng)網(wǎng)絡(luò)的田間雜草識別技術(shù)的研究
發(fā)布時間：2018-12-13 05:36
【摘要】：農(nóng)田伴生雜草的威脅是導(dǎo)致農(nóng)作物生長勢態(tài)萎靡、產(chǎn)量下降的主要原因,采用化學(xué)除草方式能高效及時地防治雜草幼苗,避免雜草成熟后影響農(nóng)作物產(chǎn)量。化學(xué)除草多為大面積粗放式噴灑,簡單省時卻存有水土污染、農(nóng)藥殘留、人員中毒等諸多弊端,與當(dāng)下提倡的綠色環(huán)保、可持續(xù)發(fā)展、精準(zhǔn)農(nóng)業(yè)等理念相悖,加之現(xiàn)代農(nóng)作物的播種多為定點條播式,雜草以簇生且隨機(jī)性生長在壟間,因此需要設(shè)計一種定點變量式噴藥系統(tǒng)。本研究以吉林農(nóng)業(yè)大學(xué)玉米試驗田間常見雜草的防治問題為例,設(shè)計了以機(jī)器視覺和圖像處理技術(shù)相結(jié)合的雜草識別系統(tǒng),為實時除草設(shè)備的研發(fā)提供了基礎(chǔ)條件。本文的主要研究內(nèi)容如下:1.分析比較雜草與作物的出苗速度以及后續(xù)處理對圖像質(zhì)量的要求,從而確定圖像采集的時間和采集過程鏡頭的高度與角度;提取圖像在RGB、2G-R-B、HIS、YCbCr等顏色空間內(nèi)的顏色特征,確定2G-R-B特征值最能滿足灰度化的要求;分別利用鄰域均值濾波和中值濾波兩種算法消除圖像采集、傳輸和變換的過程中引入的噪聲和干擾,比較處理結(jié)果發(fā)現(xiàn)中值濾波對帶有椒鹽噪聲的田間圖像的處理效果更好。2.列舉三種閾值分割方法進(jìn)行比較分割,其中OTUS閾值分割法的運行速度最快,前景植物圖像完整且沒有噪聲干擾,但背景區(qū)域噪聲較多;利用數(shù)學(xué)形態(tài)學(xué)開運算進(jìn)行后處理,比較不同尺寸的腐蝕單元和膨脹單元的作用效果,最終選定半徑為23的平面圓盤腐蝕算子和直徑為13的棱形膨脹算子。3.對形態(tài)學(xué)分割完成后的獨立葉片進(jìn)行連通區(qū)域標(biāo)記,計算基于區(qū)域特征的面積和矩特征等參數(shù);利用5種邊緣檢測方法對標(biāo)記后的連通區(qū)域進(jìn)行邊緣檢測,發(fā)現(xiàn)Canny算子檢測結(jié)果最為理想,然后基于輪廓特征計算各區(qū)域的周長、長和寬等有量綱參數(shù);對比玉米、稗草和莧菜三種植物的特征參數(shù)發(fā)現(xiàn)寬長比、圓形度和第一不變矩能有效區(qū)分植物的種類,宜作為雜草分類器的輸入特征參數(shù)。4.人工神經(jīng)網(wǎng)絡(luò)對于復(fù)雜的田間圖像具有獨特的存儲、聯(lián)想和識別判斷的功能,因此建立基于BP神經(jīng)網(wǎng)絡(luò)的雜草分類器;對隱層節(jié)點數(shù)、學(xué)習(xí)率和動量因子進(jìn)行試驗設(shè)計分析得到了最優(yōu)組合解,確定了網(wǎng)絡(luò)結(jié)構(gòu)為MLP:361,學(xué)習(xí)率為0.5,動量因子為0.5;利用MATLAB仿真建立BP神經(jīng)網(wǎng)絡(luò),并以田間作物和雜草共120幅圖像的特征參數(shù)作為輸入進(jìn)行識別分析,其中90組特征參數(shù)作為訓(xùn)練樣本,30組作為測試樣本,仿真得到的識別正確率分別為98.89%和93.33%。
[Abstract]:The threat of associated weeds in farmland is the main reason leading to the decline of crop growth and yield. The chemical weeding method can effectively and timely control weed seedlings and avoid the effect of weeds ripening on crop yield. Chemical weeding is mostly extensive spraying in a large area. Simple and time-saving, however, there are many drawbacks such as soil and water pollution, pesticide residues, personnel poisoning, etc., which are contrary to the current concepts of green environmental protection, sustainable development, precision agriculture, etc. In addition, the sowing of modern crops is mostly fixed spot seeding, weeds are clustered and growing randomly between ridges, so it is necessary to design a fixed point variable spraying system. Taking the common weed control problems in maize experimental field of Jilin Agricultural University as an example, a weed recognition system based on machine vision and image processing is designed, which provides a basic condition for the research and development of real time weeding equipment. The main contents of this paper are as follows: 1. The emergence speed of weeds and crops and the requirements of image quality for subsequent processing were analyzed and compared to determine the time of image acquisition and the height and angle of lens during acquisition. Extracting the color feature of the image in the color space such as RGB,2G-R-B,HIS,YCbCr and determining the 2G-R-B feature value can meet the requirement of grayscale most. The neighborhood mean filter and median filter are used to eliminate the noise and interference in the process of image acquisition, transmission and transformation, respectively. Compared with the processing results, the median filter has better effect on the field image with salt and pepper noise. 2. 2. Three threshold segmentation methods are listed. Among them, OTUS threshold segmentation method has the fastest running speed, the foreground plant image is complete and has no noise interference, but the background region noise is more. The effect of corrosion unit and expansion unit with different sizes were compared by using mathematical morphological open operation. Finally, the plane disk corrosion operator with radius 23 and the prism expansion operator with diameter 13 were selected. The independent leaves after morphological segmentation were labeled with connected region, and the parameters such as area and moment characteristics based on regional features were calculated. Five edge detection methods are used to detect the marked connected regions, and the results of Canny operator detection are found to be the most ideal. Then the dimensionality parameters such as perimeter, length and width of each region are calculated based on the contour features. Comparing the characteristic parameters of corn, barnyard grass and amaranth, it was found that the ratio of width to length, roundness and the first invariant moment could effectively distinguish the species of plants, and it should be used as the input characteristic parameter of weed classifier. 4. Artificial neural network (Ann) has unique functions of storing, associating and judging complex field images, so a weed classifier based on BP neural network is established. The optimal combination solution is obtained by analyzing the number of hidden nodes, learning rate and momentum factor. The network structure is determined as MLP:361, learning rate of 0.5 and momentum factor of 0.5. The BP neural network was established by MATLAB simulation, and the characteristic parameters of 120 images of field crops and weeds were used as input for identification and analysis. 90 groups of characteristic parameters were used as training samples, 30 groups as test samples. The recognition accuracy obtained by simulation is 98.89% and 93.33% respectively.
【學(xué)位授予單位】：吉林農(nóng)業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：S451;TP391.41
本文編號：2375981
[Abstract]:The threat of associated weeds in farmland is the main reason leading to the decline of crop growth and yield. The chemical weeding method can effectively and timely control weed seedlings and avoid the effect of weeds ripening on crop yield. Chemical weeding is mostly extensive spraying in a large area. Simple and time-saving, however, there are many drawbacks such as soil and water pollution, pesticide residues, personnel poisoning, etc., which are contrary to the current concepts of green environmental protection, sustainable development, precision agriculture, etc. In addition, the sowing of modern crops is mostly fixed spot seeding, weeds are clustered and growing randomly between ridges, so it is necessary to design a fixed point variable spraying system. Taking the common weed control problems in maize experimental field of Jilin Agricultural University as an example, a weed recognition system based on machine vision and image processing is designed, which provides a basic condition for the research and development of real time weeding equipment. The main contents of this paper are as follows: 1. The emergence speed of weeds and crops and the requirements of image quality for subsequent processing were analyzed and compared to determine the time of image acquisition and the height and angle of lens during acquisition. Extracting the color feature of the image in the color space such as RGB,2G-R-B,HIS,YCbCr and determining the 2G-R-B feature value can meet the requirement of grayscale most. The neighborhood mean filter and median filter are used to eliminate the noise and interference in the process of image acquisition, transmission and transformation, respectively. Compared with the processing results, the median filter has better effect on the field image with salt and pepper noise. 2. 2. Three threshold segmentation methods are listed. Among them, OTUS threshold segmentation method has the fastest running speed, the foreground plant image is complete and has no noise interference, but the background region noise is more. The effect of corrosion unit and expansion unit with different sizes were compared by using mathematical morphological open operation. Finally, the plane disk corrosion operator with radius 23 and the prism expansion operator with diameter 13 were selected. The independent leaves after morphological segmentation were labeled with connected region, and the parameters such as area and moment characteristics based on regional features were calculated. Five edge detection methods are used to detect the marked connected regions, and the results of Canny operator detection are found to be the most ideal. Then the dimensionality parameters such as perimeter, length and width of each region are calculated based on the contour features. Comparing the characteristic parameters of corn, barnyard grass and amaranth, it was found that the ratio of width to length, roundness and the first invariant moment could effectively distinguish the species of plants, and it should be used as the input characteristic parameter of weed classifier. 4. Artificial neural network (Ann) has unique functions of storing, associating and judging complex field images, so a weed classifier based on BP neural network is established. The optimal combination solution is obtained by analyzing the number of hidden nodes, learning rate and momentum factor. The network structure is determined as MLP:361, learning rate of 0.5 and momentum factor of 0.5. The BP neural network was established by MATLAB simulation, and the characteristic parameters of 120 images of field crops and weeds were used as input for identification and analysis. 90 groups of characteristic parameters were used as training samples, 30 groups as test samples. The recognition accuracy obtained by simulation is 98.89% and 93.33% respectively.
【學(xué)位授予單位】：吉林農(nóng)業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：S451;TP391.41
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 付宇超;袁文勝;張文毅;紀(jì)要;;我國施肥機(jī)械化技術(shù)現(xiàn)狀及問題分析[J];農(nóng)機(jī)化研究;2017年01期
2 楊建姣;齊跡;朱鳳武;;基于遺傳神經(jīng)網(wǎng)絡(luò)的田間雜草識別的研究[J];中國農(nóng)機(jī)化學(xué)報;2016年09期
3 林精波;;淺析玉米苗期的具體管理對策[J];農(nóng)民致富之友;2016年13期
4 王路軍;石峻全;黃津津;;基于植株整體形狀特征的雜草識別算法的研究[J];農(nóng)業(yè)工程技術(shù);2016年14期
5 訾百華;;玉米出苗期的管理技術(shù)[J];農(nóng)民致富之友;2016年01期
6 關(guān)強(qiáng);薛河儒;姜新華;;基于二維OTSU的田間植物圖像分割方法[J];江蘇農(nóng)業(yè)科學(xué);2015年12期
7 雷瓊;;基于Matlab圖像分割的研究[J];電子設(shè)計工程;2015年21期
8 孫會東;;無公害玉米苗期管理技術(shù)[J];北京農(nóng)業(yè);2015年19期
9 劉艷紅;;田間雜草識別軟件系統(tǒng)的研究[J];農(nóng)業(yè)網(wǎng)絡(luò)信息;2015年05期
10 劉紅;;玉米苗期管理方法[J];農(nóng)民致富之友;2015年09期
相關(guān)博士學(xué)位論文 前3條
1 潘新;基于計算機(jī)視覺技術(shù)的草地牧草數(shù)字化系統(tǒng)研究[D];中國農(nóng)業(yè)科學(xué)院;2014年
2 李先鋒;基于特征優(yōu)化和多特征融合的雜草識別方法研究[D];江蘇大學(xué);2010年
3 吳蘭蘭;基于數(shù)字圖像處理的玉米苗期田間雜草的識別研究[D];華中農(nóng)業(yè)大學(xué);2010年
相關(guān)碩士學(xué)位論文 前4條
1 康戀戀;基于圖像處理的玉米與雜草機(jī)器視覺分類模型的設(shè)計[D];山西農(nóng)業(yè)大學(xué);2015年
2 李義;基于相關(guān)學(xué)習(xí)神經(jīng)網(wǎng)絡(luò)的圖像識別方法研究[D];哈爾濱工業(yè)大學(xué);2015年
3 周果;基于圖像處理技術(shù)的大田玉米苗期雜草識別方法研究[D];吉林農(nóng)業(yè)大學(xué);2013年
4 沈旭;除草機(jī)器人農(nóng)田行內(nèi)作物/雜草識別研究[D];南京林業(yè)大學(xué);2011年
，本文編號：2375981
本文鏈接：http://sikaile.net/shoufeilunwen/zaizhiyanjiusheng/2375981.html
最近更新
教材專著
