本文關(guān)鍵詞：復(fù)雜背景下基于機(jī)器視覺的葡萄葉片檢測與跟蹤方法研究　出處：《甘肅農(nóng)業(yè)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 檢測 跟蹤 可變形部件模型 HOG特征 判別模型

【摘要】：近年來釀酒葡萄的種植向集約化發(fā)展,大規(guī)模種植給生長狀態(tài)的監(jiān)測帶來了極大的挑戰(zhàn),而人工檢測效率低、工作強(qiáng)度大。葡萄葉片的健康狀態(tài)在很大程度上能反映葡萄的生長狀態(tài),其作為視頻監(jiān)控的首要目標(biāo)。葉片目標(biāo)的實(shí)時檢測和跟蹤也是后續(xù)研究的基礎(chǔ),如基于機(jī)器視覺的葉片的分割、病害的識別和缺素診斷技術(shù)需要在復(fù)雜自然背景圖像中準(zhǔn)確檢測出葉片目標(biāo),此外,葉片在生長且不斷改變其位置、狀態(tài),為了判斷葡萄生長狀態(tài)的變化,對于已檢測到的葉片需進(jìn)行不斷跟蹤。本文首先對退化的葉片圖像進(jìn)行了顏色復(fù)原,然后采用了多角度可變形部件模型的葉片檢測算法,結(jié)合顏色直方圖描述外觀特征,建立一種具有判別能力的目標(biāo)跟蹤模型,并能通過模型的學(xué)習(xí)克服跟蹤中對目標(biāo)相似區(qū)域的偏移,實(shí)現(xiàn)了對葡萄葉片運(yùn)動的準(zhǔn)確跟蹤。在葉片圖像顏色復(fù)原方面,針對自然條件下獲取的視頻圖像受到灰塵干擾發(fā)生顏色失真問題,在大氣散射模型的基礎(chǔ)上建立了一種圖像顏色復(fù)原模型,并通過暗元原理對模型參數(shù)進(jìn)行了估計,恢復(fù)后的顏色分量接近葉片的原始顏色。在葉片檢測方面,本文提出了改進(jìn)的混合多角度可變形部件模型的葉片檢測算法。首先,采用了G/R圖像中提取HOG特征,并對特征向量進(jìn)行了PCA降維處理,有效消除了光照和背景變化的影響。其次對G/R顏色特征圖像采用可變形部件模型訓(xùn)練出了正面、側(cè)面和背面3角度的葉片檢測器,在多模型匹配過程中采用降低閾值參數(shù)和非極大值抑制的方式對產(chǎn)生葉片檢測候選集合進(jìn)行后期處理,檢測結(jié)果的總體性能有所提高。試驗(yàn)結(jié)果表明,在自然條件下的葉片平均檢測率為88.31%,平均誤檢率為8.73%,葉片檢測準(zhǔn)確性相對較高。在葉片跟蹤方面,針對葡萄葉片的運(yùn)動特點(diǎn),本文采用基于判別模型和顏色特征的跟蹤方法。為克服在目標(biāo)相似區(qū)域被跟蹤的可能性,建立了目標(biāo)干擾區(qū)域判別模型,并將該模型與目標(biāo)判別模型相結(jié)合;在跟蹤定位過程將位置函數(shù)的最大值作為相鄰幀的目標(biāo)位置,并對該位置的目標(biāo)采用了自適應(yīng)閾值的方法進(jìn)行尺度估計,實(shí)現(xiàn)了葉片的準(zhǔn)確跟蹤。試驗(yàn)結(jié)果表明,葉片跟蹤的準(zhǔn)確性也相對較高,其重疊率高達(dá)0.83,平均中心誤差為17.33像素。最后,基于Matlab開發(fā)平臺創(chuàng)建出可視化的人機(jī)交互界面,實(shí)現(xiàn)了監(jiān)控視頻的自動目標(biāo)檢測與跟蹤,并能通過切換IP地址對不同的攝像頭實(shí)現(xiàn)了操作。
[Abstract]:In recent years, the development of wine grapes has been developing to intensive development. Large-scale planting has brought great challenges to the monitoring of growth status, and the efficiency of artificial detection is low and the intensity of work is great. The healthy state of grape leaves to a great extent can reflect the state of grape growth, which is the primary target of video surveillance. Based on the real-time detection and tracking of the target is also leaves for further research, such as the identification of disease leaf segmentation, machine vision and the deficiency diagnosis technology needed in complex natural background image to accurately detect the target based on the blade, in addition, leaves in the growth and changing its position, status, changes in order to determine the grape growth state the leaves, has been detected for continuous tracking. Firstly, the color restoration of leaf image degradation, leaf detection algorithm and then using the multi angle deformable part model, combined with the color histogram to describe its appearance characteristics, establish a discriminatory target tracking model, and through the model of learning to overcome the similar region offset on the target tracking, to achieve accurate to track the movement of grape leaves. In the image restoration of leaf color, for the video image acquisition under natural conditions by the dust interference problem of color distortion, based on atmospheric scattering model is established on a color image restoration model, and the model parameters were estimated by dark element principle, the original color components recovered close to the color of leaves. In the aspect of blade detection, an improved hybrid multi angle deformable component model is proposed in this paper. First, the HOG feature is extracted from the G/R image, and the feature vector is treated with PCA reduction, which effectively eliminates the influence of illumination and background changes. The features in G/R color images using deformable part model training out of the front, side and back blade detector 3 angle, by decreasing the threshold parameter and non maximum suppression of the blade was processed to detect candidate sets in multi model matching process can improve the overall performance test results. The test results show that the average detection rate of the blade under natural conditions is 88.31%, the average false detection rate is 8.73%, and the accuracy of the blade detection is relatively high. In the aspect of blade tracking, the tracking method based on discriminant model and color feature is used in view of the characteristics of the motion of grape leaves. In order to overcome the possibility of tracking in the target area is similar, setting up target interference region discrimination model, and the model and target discrimination model combination; during the positioning process will function as the maximum position of adjacent frames in the target location, and the location of the target by using the adaptive threshold method for size estimation, implementation the accurate tracking of leaves. The experimental results show that the accuracy of the blade tracking is relatively high, the overlap rate is as high as 0.83, and the average center error is 17.33 pixels. Finally, a visual human-machine interaction interface is created based on the Matlab development platform, which realizes the automatic target detection and tracking of surveillance video, and realizes the operation of different cameras by switching IP addresses.
【學(xué)位授予單位】：甘肅農(nóng)業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：S663.1;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 程雅瓊;蔡亮;張忠林;;惡劣天氣下車牌識別系統(tǒng)及MATLAB GUI實(shí)現(xiàn)[J];自動化與儀器儀表;2017年02期

2 曾接賢;程瀟;;結(jié)合單雙行人DPM模型的交通場景行人檢測[J];電子學(xué)報;2016年11期

3 孫煒;薛敏;孫天宇;胡夢云;呂云峰;;基于支持向量機(jī)優(yōu)化的行人跟蹤學(xué)習(xí)檢測方法[J];湖南大學(xué)學(xué)報(自然科學(xué)版);2016年10期

4 李鵬飛;夏克付;;面向服務(wù)機(jī)器人的多行人檢測與跟蹤[J];計算機(jī)系統(tǒng)應(yīng)用;2016年10期

5 張凱兵;章愛群;李春生;;基于HSV空間顏色直方圖的油菜葉片缺素診斷[J];農(nóng)業(yè)工程學(xué)報;2016年19期

6 賈松敏;盧迎彬;王麗佳;李秀智;徐濤;;分層特征移動機(jī)器人行人跟蹤[J];浙江大學(xué)學(xué)報(工學(xué)版);2016年09期

7 孫挺;齊迎春;耿國華;;基于幀間差分和背景差分的運(yùn)動目標(biāo)檢測算法[J];吉林大學(xué)學(xué)報(工學(xué)版);2016年04期

8 姜文濤;劉萬軍;袁Y，

本文編號：1345307