国产日韩欧美一区二区三区三州_亚洲少妇熟女av_久久久久亚洲av国产精品_波多野结衣网站一区二区_亚洲欧美色片在线91_国产亚洲精品精品国产优播av_日本一区二区三区波多野结衣 _久久国产av不卡

?

基于無(wú)人機(jī)遙感影像的水稻種植信息提取

2018-03-09 05:26:26黃愉淇李緒孟彭冬星謝景鑫
關(guān)鍵詞:正確率試驗(yàn)區(qū)灰度

李 明,黃愉淇,李緒孟,彭冬星,謝景鑫

?

基于無(wú)人機(jī)遙感影像的水稻種植信息提取

李 明1,3,黃愉淇1,李緒孟2,彭冬星1,謝景鑫1

(1. 湖南農(nóng)業(yè)大學(xué)工學(xué)院,長(zhǎng)沙 410128; 2. 湖南農(nóng)業(yè)大學(xué)理學(xué)院,長(zhǎng)沙 410128; 3. 湖南星索爾航空科技有限公司,長(zhǎng)沙 410100)

水稻是中國(guó)南方最主要的糧食作物,種植面積波動(dòng)對(duì)國(guó)家糧食穩(wěn)定有很大影響。通過(guò)無(wú)人機(jī)遙感試驗(yàn)獲取多幅有重疊區(qū)域的圖像,使用Agisoft photoscan軟件拼接重構(gòu)試驗(yàn)區(qū)的完整圖像,利用多尺度分割方法將試驗(yàn)區(qū)域分割成若干對(duì)象,并基于統(tǒng)計(jì)方法提取對(duì)象的光譜特征、幾何特征和紋理特征;然后,建立識(shí)別水稻地塊的二分類Logistic回歸模型,特征指標(biāo)為形狀指數(shù)、紅色均值、紅色標(biāo)準(zhǔn)偏差、最大化差異度量、灰度共生矩陣同質(zhì)性和灰度共生矩陣非相似性。結(jié)果表明:模型辨識(shí)訓(xùn)練樣本集的正確率為100%,辨識(shí)檢驗(yàn)樣本的正確率為97%,模型應(yīng)用于辨識(shí)驗(yàn)證區(qū)域水稻田塊,總體正確率為98%。最后基于累計(jì)像素方法測(cè)算水稻田塊的面積,并與目視解譯測(cè)算的結(jié)果對(duì)比,面積誤差小于3.5%,研究方法識(shí)別水稻田塊效果好,面積測(cè)算準(zhǔn)確率高。因此,該研究對(duì)利用無(wú)人機(jī)遙感影像普查水稻種植信息具有一定的適用性。

無(wú)人機(jī);遙感;農(nóng)作物;可見(jiàn)光;水稻;二分類

0 引 言

中國(guó)是擁有13億人口的大國(guó),糧食問(wèn)題是關(guān)系國(guó)計(jì)民生的大事,在國(guó)民經(jīng)濟(jì)和社會(huì)發(fā)展中占有極其重要的地位[1]。隨著中國(guó)城鎮(zhèn)化、工業(yè)化的推進(jìn),耕地面積下降,并且種植作物呈多元化發(fā)展趨勢(shì)[2]。水稻是中國(guó)南方最主要的糧食作物[3],及時(shí)掌握其種植信息,對(duì)維護(hù)國(guó)家的糧食穩(wěn)定及制定相關(guān)政策有著巨大意義。

遙感技術(shù)[4],具備獲取信息豐富、多分辨率和多平臺(tái)、快速和覆蓋范圍廣的優(yōu)勢(shì),被廣泛用于農(nóng)情信息獲取[5-9]。隨著飛行技術(shù)的發(fā)展,具有機(jī)動(dòng)靈活、作業(yè)選擇性強(qiáng)、作業(yè)周期短、時(shí)效性好、維護(hù)使用費(fèi)低、安全性好的無(wú)人機(jī)平臺(tái)近年來(lái)逐漸趨于成熟[10-11]。隨著微型計(jì)算機(jī)、通訊設(shè)備等技術(shù)迅速發(fā)展,搭載遙感設(shè)備的無(wú)人機(jī)平臺(tái)成為近年獲取作物種植信息研究的熱點(diǎn)[12-13]。

前人利用無(wú)人機(jī)平臺(tái)獲取可見(jiàn)光圖像提取物種植信息的研究取得了一定的進(jìn)展,就其方法而言,大致分為兩類:基于像元的提取方法和基于面向?qū)ο蠓诸惣夹g(shù)的提取方法。在基于像元提取方法的研究方面,汪小欽等[14]基于可見(jiàn)光無(wú)人機(jī)遙感的RGB圖像,利用植被在綠光波段的反射及在紅光和藍(lán)光波段的吸收特性,構(gòu)建了植被指數(shù)VDVI(可見(jiàn)光波段差異植被指數(shù));李宗南等[15]基于小型電動(dòng)無(wú)人機(jī)搭載彩色數(shù)碼相機(jī)獲取的彩色圖像,分別通過(guò)色彩特征和紋理特征區(qū)分正常、倒伏玉米,發(fā)現(xiàn)基于紅、綠、藍(lán)色均值紋理特征提取倒伏玉米面積的誤差??;韓文霆等[16]基于固定翼無(wú)人機(jī)獲取RGB圖像,研究拔節(jié)期玉米種植信息提取方法,綠色均值、藍(lán)色協(xié)同性和紋理低通植被指數(shù)TLVI作為玉米種植信息提取特征,面積提取誤差總體可以控制在20%以內(nèi);Kyle等[17]基于DJI多旋翼無(wú)人機(jī)獲取的多幅RGB圖像,使用自適應(yīng)余弦估計(jì)器和譜角映射器算法完成藻類識(shí)別;Carlos Poblete-Echeverría等[18]基于無(wú)人機(jī)遙感捕捉具有超高空間分辨率的圖像,比較-均值、人工神經(jīng)網(wǎng)絡(luò)、隨機(jī)森林和光譜指數(shù)在VSP訓(xùn)練的葡萄園中的冠層檢測(cè)性能。在基于面向?qū)ο蠓诸惣夹g(shù)的提取方法的研究方面,王利民等[19]基于無(wú)人機(jī)獲取RGB影像,利用光譜特征、幾何形狀特征、紋理特征,采用面向?qū)ο蠓诸惙椒▽?duì)苜蓿、春玉米、夏玉米和裸土進(jìn)行分類;董梅等[20]基于無(wú)人機(jī)遙感影像技術(shù),以面向?qū)ο蟮倪b感影像分析方法提取煙草種植面積及其分布信息;魯恒等[21]基于無(wú)人機(jī)影像技術(shù),提出利用遷移學(xué)習(xí)機(jī)制的耕地提取方法。

水稻是中國(guó)南方最主要的糧食作物,然而,目前國(guó)內(nèi)還沒(méi)有利用無(wú)人機(jī)平臺(tái)獲取水稻種植信息的研究,為此,本文研究將一種基于無(wú)人機(jī)搭載可見(jiàn)光遙感設(shè)備獲取的數(shù)字影像研究提取水稻種植信息的方法,為水稻種植信息普查提供方法補(bǔ)充。

1 數(shù)據(jù)來(lái)源

1.1 研究區(qū)概況

研究區(qū)域分為試驗(yàn)區(qū)和驗(yàn)證區(qū),分別位于湖南省中部新化縣土坪村和湖南省長(zhǎng)沙市省農(nóng)業(yè)科學(xué)院水稻研究所水稻試驗(yàn)展示基地,地處中緯度地帶(110°45′-111°41′E,27°31′-28°14′N)和(111°53′-114°15′E,27°51′-28°41′N),屬亞熱帶季風(fēng)性濕潤(rùn)氣候,氣候溫和,降水充沛,雨熱同期,四季分明[22],土地平坦且肥沃,熱量資源豐富,光照充足,適合水稻的種植生產(chǎn),早稻的生長(zhǎng)期為3月到7月[23]。測(cè)區(qū)條件交通條件便利、田塊多且地勢(shì)相對(duì)平整,為遙感影像分類提取提供便利,同時(shí)對(duì)作物的地面生長(zhǎng)情況監(jiān)控充足,各種作物資料獲取方便,為無(wú)人機(jī)遙感影像的農(nóng)情監(jiān)測(cè)應(yīng)用研究提供了可靠的保障。試驗(yàn)區(qū)測(cè)區(qū)面積大約為6 km×2 km;驗(yàn)證區(qū)測(cè)區(qū)面積大約為0.8 km×0.6 km。

1.2 數(shù)據(jù)獲取

研究的數(shù)據(jù)來(lái)源于2017年6月在試驗(yàn)區(qū)和2017年7月在驗(yàn)證區(qū)進(jìn)行的無(wú)人機(jī)遙感試驗(yàn)。無(wú)人機(jī)平臺(tái)采用星索爾航空科技有限公司的六旋翼無(wú)人機(jī),最大飛行速度為6 m/s,軸距1 300 mm,起重限額10 kg,最大續(xù)航時(shí)間50 min。其搭載的相機(jī)影像傳感器為CMOS,鏡頭搭載的為FOV94,對(duì)焦點(diǎn)無(wú)窮遠(yuǎn),單幅照片最大像素4 000× 3 000 pixel。試驗(yàn)區(qū)設(shè)計(jì)飛行航高120 m,航線20條,航線總長(zhǎng)30 km,航拍獲取了試驗(yàn)田地及附近地區(qū)374張航片。驗(yàn)證區(qū)設(shè)計(jì)飛行航高60 m,航線10條,航線總長(zhǎng)8 km,航拍獲取了試驗(yàn)田地及附近地區(qū)140張航片。

1.3 數(shù)據(jù)處理

航空影像通過(guò)Agisoft PhotoScan軟件進(jìn)行影像拼接,整個(gè)工作流程由軟件自動(dòng)完成。試驗(yàn)區(qū)和驗(yàn)證區(qū)正射影像圖如圖1所示。

圖1 試驗(yàn)區(qū)和驗(yàn)證區(qū)正射影像圖

首先Agisoft PhotoScan利用 POS數(shù)據(jù)通過(guò)尋找同名點(diǎn)的方法完成數(shù)據(jù)定向及點(diǎn)云提取,然后通過(guò)地面控制點(diǎn)數(shù)據(jù)進(jìn)行點(diǎn)云數(shù)據(jù)的幾何校正及地理信息配準(zhǔn),最終經(jīng)過(guò)立體建模、生成紋理,獲取符合《數(shù)字航空攝影測(cè)量空中三角測(cè)量規(guī)范》中對(duì)1:1000 0平地平面精度要求的圖像[24]。由軟件導(dǎo)出正射影像圖,以JPEG圖像格式儲(chǔ)存。圖像的空間分辨率為0.04和0.02 m,圖像位深度為24,色彩空間為sRGB;該圖像存儲(chǔ)了地物紅、綠、藍(lán)3種色彩的灰度值,每種色彩含8位字節(jié)的信息,數(shù)值范圍為0~255。

2 基于面向?qū)ο蠓诸惙ǖ乃痉N植面積提取方法

研究使用的JPEG圖像只具有紅、綠、藍(lán)3色的灰度信息,僅僅使用基于單個(gè)像元的光譜信息對(duì)地物進(jìn)行分離,造成分類精度不高,而且分類結(jié)果易呈現(xiàn)“椒鹽”現(xiàn)象,對(duì)遙感影像的應(yīng)用帶來(lái)不利影響[25]。通過(guò)面向?qū)ο蠓诸惙椒?,不再僅僅依靠單一像素的光譜信息,而是針對(duì)影像對(duì)象單元集合,充分利用光譜信息、幾何特征、紋理特征和上下文等屬性信息,遙感影像信息的提取得到明顯的改善,對(duì)分類及面積提取的精度得到提高[26-27]。因此研究首先對(duì)JPEG圖像進(jìn)行對(duì)象分割,然后針對(duì)影像的對(duì)象分割單元提取多空間特征值進(jìn)行處理分析與統(tǒng)計(jì),建立多特征對(duì)象的分類體系。數(shù)據(jù)處理軟件使用eCognition Developer 9,分割算法采用圖像多尺度分割,分類算法采用指定類分類。

2.1 圖像的分割參數(shù)的選擇

多尺度分割是較為常用的分割算法,分割尺度、光滑度和緊密度等參數(shù)的選擇直接決定影像對(duì)象的大小以及信息提取的精度。利用eCognition軟件,結(jié)合影像數(shù)據(jù)實(shí)際地物特征,通過(guò)多次試驗(yàn),最終選取具體的影像分割參數(shù)。試驗(yàn)區(qū)的尺度參數(shù)Scale=480,形狀因子Shape=0.1,緊湊度因子Compact=0.1。分割后共880個(gè)對(duì)象,其中水稻地塊173塊,其他地塊707塊。驗(yàn)證區(qū)的尺度參數(shù)Scale=1 500,形狀因子Shape=0.1,緊湊度因子Compact=0.3,分割后得到共240個(gè)分割對(duì)象,水稻地塊17塊,其他地塊223塊。目視檢驗(yàn)表明分割效果較好,圖2為試驗(yàn)區(qū)與驗(yàn)證區(qū)多尺度分割結(jié)果。

圖2 試驗(yàn)區(qū)和驗(yàn)證區(qū)多尺度分割

2.2 試驗(yàn)區(qū)特征統(tǒng)計(jì)分析

使用eCognition Developer 9統(tǒng)計(jì)對(duì)象特征值。試驗(yàn)區(qū)域影像中173個(gè)水稻田塊、707個(gè)其他地塊的亮度、紅色均值、綠色均值、藍(lán)色均值、最大化差異度量、紅色標(biāo)準(zhǔn)偏差等32項(xiàng)特征參數(shù)的最大值和最小值見(jiàn)表1。分析表1發(fā)現(xiàn),兩類對(duì)象的所有特征值都有交集,使用單一特征辨別水稻地塊是不可行的,因此將利用多個(gè)特征組合對(duì)水稻地塊進(jìn)行區(qū)分。

表1 水稻地塊與其他地塊的特征值

2.3 辨識(shí)模型構(gòu)建與檢驗(yàn)

2.3.1 二分類Logistic回歸模型

在統(tǒng)計(jì)分析上,Logistic回歸應(yīng)用非常廣泛。其中Binary logistic回歸分析因變量為0和1。為試驗(yàn)方便,把水稻地塊標(biāo)記為1,水稻地塊以外的其他地塊標(biāo)記為0。采用Logistic模型,將因變量的范圍鎖定在[0,1]范圍內(nèi),記發(fā)生的條件概率為,把的某個(gè)函數(shù)()假設(shè)為變量的函數(shù)形式,進(jìn)行l(wèi)ogit變換。

Logistic線性回歸模型[28-29]為

將式(2)對(duì)求解得到

式中0,1,2,…,α為回歸系數(shù);1,2,3,…,X為線性回歸自變量。

2.3.2 二分類Logistic辨識(shí)模型的構(gòu)建

將試驗(yàn)區(qū)的對(duì)象分成兩份,隨機(jī)選取水稻地塊87塊和其他地塊354塊作為訓(xùn)練樣本,用于二分類Logistic回歸模型的構(gòu)建。使用SPSS的條件向前逐步法構(gòu)建二分類Logistic回歸模型,在處理過(guò)程中,所有變量依據(jù)比分檢驗(yàn)的概率大小依次進(jìn)入方程,并依據(jù)條件參數(shù)似然比進(jìn)行檢驗(yàn)剔除變量?;貧w系數(shù)α見(jiàn)表2,訓(xùn)練樣本的分類結(jié)果見(jiàn)表3。

表2 模型參數(shù)估計(jì)結(jié)果

表3表明:正確分類水稻地塊數(shù)為87,正確分類其他地塊數(shù)為354,正確率均為100%。具體的二分類Logistic回歸模型為

式中1,2,3,4,5,6分別代表對(duì)象的形狀指數(shù)、紅色均值、紅色標(biāo)準(zhǔn)偏差和最大化差異度量、灰度共生矩陣對(duì)比度和灰度共生矩陣非相似性的值。

2.3.3 對(duì)象分類的Holdout檢驗(yàn)

Holdout檢驗(yàn)是將隨機(jī)剔除掉的樣本進(jìn)行檢驗(yàn)[30]。利用全部對(duì)象檢驗(yàn)構(gòu)建的二分類Logistic回歸模型和對(duì)象分類特征。檢驗(yàn)結(jié)果表明:構(gòu)建的二分類Logistic回歸模型辨識(shí)檢驗(yàn)樣本的正確率為100%,見(jiàn)表3,基于二分類Logistic分類算法水稻的提取結(jié)果見(jiàn)圖3。

表3 基于二分類Logistic分類算法的試驗(yàn)區(qū)分類結(jié)果

注: 1表示水稻地塊,0表示非水稻地塊。余同

Note: 1 is defined as rice area, 0 is defined as other area. The same as below.

注:綠色圖塊為提取的水稻地塊。余同

2.4 基于二分類Logistic分類算法提取水稻地塊的驗(yàn)證

為進(jìn)一步檢驗(yàn)方法的可行性,從驗(yàn)證區(qū)的240個(gè)對(duì)象中隨機(jī)選取總對(duì)象的約1/2,即水稻地塊8塊,其他地塊101塊,作為訓(xùn)練樣本,其余為檢驗(yàn)樣本,訓(xùn)練樣本用于構(gòu)建二分類Logistic回歸模型,重新確定式(4)中形狀指數(shù)、紅色均值、紅色標(biāo)準(zhǔn)偏差和最大化差異度量、灰度共生矩陣對(duì)比度和灰度共生矩陣非相似性特征6個(gè)變量的系數(shù),然后利用重新構(gòu)建的二分類Logistic回歸模型辨識(shí)檢驗(yàn)樣本。

結(jié)果表明,訓(xùn)練樣本正確分類水稻地塊數(shù)為8,正確率為100%,正確分類其他地塊數(shù)為101,正確率為100%,總體正確率為100%;驗(yàn)證樣本正確分類水稻地塊數(shù)為8,正確率為89%,正確分類其他地塊數(shù)為122,正確率為100%,總體正確率為99%(表4)。基于二分類分類算法驗(yàn)證區(qū)域提取結(jié)果見(jiàn)圖4。通過(guò)觀察該區(qū)域觀察值為1而預(yù)測(cè)值為0的地塊,發(fā)現(xiàn)產(chǎn)生誤判的原因是該田塊在該時(shí)期生長(zhǎng)還未封行,光譜信息上與其他的水稻地塊差異大。

表4 基于二分類Logistic分類算法的驗(yàn)證區(qū)分類結(jié)果

圖4 基于二分類Logistic分類算法驗(yàn)證區(qū)域提取結(jié)果

3 水稻種植面積提取精度驗(yàn)證

使用目視解譯獲得水稻種植面積的實(shí)測(cè)值,根據(jù)地面調(diào)查數(shù)據(jù)和觀察試驗(yàn)區(qū)域圖像中水稻的特征,以田埂為邊界,用鋼筆工具勾畫出試驗(yàn)區(qū)域和驗(yàn)證區(qū)域圖像所有水稻地塊,水稻種植面積的目視解譯提取結(jié)果見(jiàn)圖5,綠色為水稻地塊。

圖5 目視解譯提取結(jié)果

對(duì)比圖3和圖5a、圖4和圖5b發(fā)現(xiàn)提取出的水稻地塊在試驗(yàn)區(qū)域圖像中分布位置基本相同,說(shuō)明基于二分類Logistic回歸模型的分類算法能夠較準(zhǔn)確定位水稻種植地塊的分布?;诶塾?jì)像素點(diǎn)方法分別統(tǒng)計(jì)目視解譯和基于二分類類分類算法方法提取結(jié)果的水稻地塊的面積,并以目視解譯結(jié)果為基于二分類Logistic算法進(jìn)行精度評(píng)價(jià),精度表見(jiàn)表5,試驗(yàn)區(qū)與驗(yàn)證區(qū)的誤差分別為0.20%和3.5%。

表5 水稻地塊提取面積精度

4 討 論

本文試驗(yàn)區(qū)和驗(yàn)證區(qū)地物主要包括水稻、樹體、草地、裸地、水體和建筑。紅色均值是區(qū)分植被覆蓋對(duì)象(水稻、草地、樹體)與非植被覆蓋對(duì)象(裸地、水體、建筑)顏色信息;紅色標(biāo)準(zhǔn)偏差和最大化差異度量刻畫水稻和草地的顏色變化差異,水稻地塊的顏色相對(duì)均勻,雜草地缺乏管理,長(zhǎng)勢(shì)不均,顏色變化相對(duì)較大;水稻地塊和樹體顏色變化都較小,但是樹體的邊界較破碎,其形狀指數(shù)較大,形狀指數(shù)能有效區(qū)分顏色均值接近且變化較小的水稻地塊和樹體;紋理特征體現(xiàn)地物表面緩慢變化或者周期性變化的結(jié)構(gòu)組織排列屬性[31],水稻、樹體、草地、裸地、水體和建筑均存在一定差異,是從地物中區(qū)分水稻地塊的補(bǔ)充屬性。機(jī)理分析上看6個(gè)特征指標(biāo)區(qū)分試驗(yàn)區(qū)和驗(yàn)證區(qū)地物是合理的。

6個(gè)特征指標(biāo)基于試驗(yàn)區(qū)確定,同時(shí)適合于不同地域,不同生長(zhǎng)期的驗(yàn)證區(qū)水稻地塊的辨識(shí),驗(yàn)證區(qū)的辨識(shí)正確率99%。試驗(yàn)結(jié)果表明,紅色均值、紅色標(biāo)準(zhǔn)偏差和最大化差異度量,形狀指數(shù),灰度共生矩陣對(duì)比度和灰度共生矩陣非相似性六個(gè)特征指標(biāo)能有效辨識(shí)水稻地塊。

5 結(jié) 論

1)基于對(duì)象的32項(xiàng)特征統(tǒng)計(jì),運(yùn)用二分類Logistic回歸模型確定了水稻地塊提取的6個(gè)特征指標(biāo),其中,光譜特征3個(gè)指標(biāo),紅色均值、紅色標(biāo)準(zhǔn)偏差和最大化差異度量,即對(duì)象所有像素紅色圖層的均值、標(biāo)準(zhǔn)差和三種光譜均值的最大的差異,其作用是區(qū)分水稻地塊對(duì)象與其他對(duì)象的顏色信息。形狀特征1個(gè)指標(biāo),形狀指數(shù),表示對(duì)象邊界的光滑度,對(duì)象邊界越破碎,其形狀指數(shù)越大。紋理特征2個(gè)指標(biāo),灰度共生矩陣對(duì)比度和灰度共生矩陣非相似性,均表示對(duì)象局部灰度變化總量,灰度差別越大則對(duì)比度的值越大,對(duì)比度越高,非相似性度也越大。

2)基于二分類Logistic模型進(jìn)行地塊分類,有效提取了辨識(shí)水稻地塊的光譜特征、形狀特征和紋理特征,能夠較準(zhǔn)確的辨識(shí)水稻地塊,辨識(shí)正確率高,采用累計(jì)像素點(diǎn)方法測(cè)量試驗(yàn)區(qū)與檢驗(yàn)區(qū)的面積,以目視解譯的面積作為精度評(píng)價(jià),誤差率分別為0.20%和3.5%。表明利用本文方法對(duì)水稻種植情況普查具有一定參考價(jià)值。

3)利用本方法辨識(shí)水稻田塊受水稻生育期的影響,進(jìn)一步分析發(fā)現(xiàn)驗(yàn)證區(qū),與其他水稻田塊比較,錯(cuò)誤分類的水稻田塊水稻生育期差異明顯,該田塊水稻明顯未封行。因此,不同時(shí)期調(diào)進(jìn)行多次調(diào)查是進(jìn)一步提高本方法辨識(shí)水稻地塊正確率的有效途徑。

[1] 章秀福,王丹,方福平,等. 中國(guó)糧食安全和水稻生產(chǎn)[J]. 農(nóng)業(yè)現(xiàn)代化研究,2005,26(2):85-88. Zhang Xiufu, Wang Dan, Fang Fuping, et al. Food safety and rice production in China[J]. Research of Agricultural Modernization, 2005, 26(2): 85-88. (in Chinese with English abstract)

[2] 李景奇. 中國(guó)農(nóng)業(yè)的現(xiàn)狀和前景展望[J]. 中國(guó)農(nóng)業(yè)信息,2013,17(1):56-58.

[3] 唐華俊. 新形式下中國(guó)糧食自給戰(zhàn)略[J]. 農(nóng)業(yè)經(jīng)濟(jì)問(wèn)題,2014(2):4-10.

[4] 史舟,梁宗正,楊媛媛,等. 農(nóng)業(yè)遙感研究現(xiàn)狀與展望[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào),2015,46(2):247-258. Shi Zhou, Liang Zongzheng, Yang Yuanyuan, et al. Status and prospect of agricultural remote sensing[J]. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(2): 247-258. (in Chinese with English abstract)

[5] 李明,趙俊霞,胡芬. 國(guó)家航空航天遙感影像獲取現(xiàn)狀及發(fā)展[J]. 測(cè)繪通報(bào),2015(10):12-15. Li Ming, Zhao Junxia, Hu Fen. Status and development for acquisition of national aerospace remote sensing imageries[J]. Bulletin of Surveying and Mapping, 2015(10): 12-15. (in Chinese with English abstract)

[6] 宋曉宇,王仁紅,楊貴軍,等. 高分辨率遙感影像中冬小麥長(zhǎng)勢(shì)空間異質(zhì)性特征分析[J]. 農(nóng)業(yè)工程學(xué)報(bào),2014,30(37):192-199. Song Xiaoyu, Wang Renhong, Yang Guijun, et al. Winter wheat growth spatial variability character analysis based on remote sensing image with high resolution[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2014, 30(17): 192-199. (in Chinese with English abstract)

[7] Lamb D W. The use of qualitative airborne multispectral imaging for managing agricultural crops: A case study in south-eastern Australia[J]. Australian Journal of Experimental Agriculture, 2000(40): 725-738.

[8] Xiang Haitao, Tian Lei. Development of a low-cost agricultural remote sensing system based on an autonomous unmanned aerial vehicle (UAV)[J]. Biosystems Engineering, 2011(108): 174-190.

[9] 汪沛,羅錫文,周志艷,等. 基于微小型無(wú)人機(jī)的遙感信息獲取關(guān)鍵技術(shù)綜述[J]. 農(nóng)業(yè)工程學(xué)報(bào),2014,30(18):1-12. Wang Pei, Luo Xiwen, Zhou Zhiyan, et al. Key technology for remote sensing information acquisition based on micro UAV[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2014, 30(18): 1-12. (in Chinese with English abstract)

[10] 白由路,金繼運(yùn),楊俐蘋,等. 低空遙感技術(shù)及其在精準(zhǔn)農(nóng)業(yè)中的應(yīng)用[J].土壤肥料,2004(1):3-6. Bai Youlu, Jin Jiyun, Yang Liping, Technology of low altitude remote sensing and its applications in precision agriculture[J]. Soil and Fertilizer Sciences in China, 2004(1): 3-6. (in Chinese with English abstract)

[11] 高奮生. 低空無(wú)人機(jī)遙感的應(yīng)用及發(fā)[J].農(nóng)業(yè)網(wǎng)絡(luò)信息,2014(12):75-78. Gao Fensheng, Application and progress on low-altitude unmanned aerial vehicle remote sensing[J]. Agriculture Network Information, 2014(12): 75-78. (in Chinese with English abstract)

[12] 楊邦杰,裴志遠(yuǎn),周清波. 我國(guó)農(nóng)情遙感監(jiān)測(cè)關(guān)鍵技術(shù)研究進(jìn)展[J]. 農(nóng)業(yè)工程學(xué)報(bào),2002,18(3):191-194. Yang Bangjie, Pei Zhiyuan, Zhou Qingbo, et al. Key technologies of crop monitoring using remote sensing at a national scale progress and problems[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2002, 18(3): 191-194. (in Chinese with English abstract)

[13] Rango A, Laliberte A, Herrick J E, et al. Unmanned aerial vehicle-based remote sensing for rangeland assessment,, monitoring, and management[J]. Journal of Applied Remote Sensing, 2009, 3(1): 335-342.

[14] 汪小欽,王苗苗,王紹強(qiáng),等. 基于可見(jiàn)光波段無(wú)人機(jī)遙感的植被信息提取[J]. 農(nóng)業(yè)工程學(xué)報(bào),2015,31(5):152-159. Wang Xiaoqin, Wang Miaomiao, Wang Shaoqiang, et al. Extraction of vegetation information from visible unmanned aerial vehicle images[J]. Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2015, 31(5): 152-159. (in Chinese with English abstract)

[15] 李宗南,陳仲新,王利民,等. 基于小型無(wú)人機(jī)遙感的玉米倒伏面積提取[J]. 農(nóng)業(yè)工程學(xué)報(bào),2014,30(19):207-213. Li Zongnan, Chen Zhongxin, Wang Limin, et al. Area extraction of maize lodging based on remote sensing by small unmanned aerial vehicle[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2014, 30(19): 207-213. (in Chinese with English abstract)

[16] 韓文霆,李廣,苑夢(mèng)嬋,等. 基于無(wú)人機(jī)遙感技術(shù)的玉米種植信息提取方法研究[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào),2017,48(1):140-147. Han Wenting, Li Guang, Yuan Mengchan, et al. Extraction method of maize planting information based on UAV remote sensing techonology[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(1): 140-147. (in Chinese with English abstract)

[17] Kyle F F, Steven C C. Remote sensing of submerged aquatic vegetation in a shallow non-turbid river using an unmanned aerial vehicle[J]. Remote Sensing, 2014, 6(12): 12815-12836.

[18] Carlos Poblete-Echeverría, Guillermo Federico Olmedo, Ben Ingram, et al. Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV):A case study in a commercial vineyard[J]. Remote Sensing, 2017, 9(268): 14.

[19] 王利民,劉佳,楊玲波,等. 基于無(wú)人機(jī)影像的農(nóng)情遙感監(jiān)測(cè)應(yīng)用[J]. 農(nóng)業(yè)工程學(xué)報(bào),2013,29(18):136-145. Wang Limin, Liu Jia, Yang Lingbo, et al. Applications of unmanned aerial vehicle images on agricultural remote sensing monitoring[J]. Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2013, 29(18): 136-145. (in Chinese with English abstract)

[20] 董梅,蘇建東,劉廣玉,等. 面向?qū)ο蟮臒o(wú)人機(jī)遙感影像煙草種植面提取和監(jiān)測(cè)[J]. 測(cè)繪科學(xué),2014,39(9):87-90. Dong Mei, Su Jiandong, Liu Guangyu, et al. Extraction of tobacco planting areas from UAV remote sensing imagery by object-oriented classification method[J]. Science of Surveying and Mapping, 2014, 39(9): 87-90. (in Chinese with English abstract)

[21] 魯恒,付蕭,賀一楠,等. 基于遷移學(xué)習(xí)的無(wú)人機(jī)影像耕地信息提取方法[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào),2015,46(12):274-279,284. Lu Heng, Fu Xiao, He Yinan, et a. Cultivated land information extraction from high resolution UAV images based on transfer learning[J]. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(12): 274-279, 284. (in Chinese with English abstract)

[22] 劉朝陽(yáng),劉黎明,彭 倩. 南方雙季稻區(qū)農(nóng)戶水稻種植模式的決策行為分析:基于湖南省長(zhǎng)沙縣農(nóng)戶調(diào)查的實(shí)證研究[J]. 資源科學(xué),2012,34(12):2234-2241. Liu Zhaoyang, Liu Liming, Peng Qian. Analysis of rice cropping decision-making in a double-cropping rice area of southern china[J]. Resources Science, 2012, 34(12): 2234-2241. (in Chinese with English abstract)

[23] 廖中華,周玉梅,劉振之. 新化縣水稻“壓?jiǎn)螖U(kuò)雙”瓶頸及發(fā)展對(duì)策[J]. 湖南農(nóng)業(yè)科學(xué),2016(7):100-102. Liao Zhonghua, Zhou Yumei, Liu Zhenzhi. Bottleneck and development countermeasures of rice “reduce single and expand double” in xinhua county[J]. Hunan Agricultural Science, 2016(7): 100-102. (in Chinese with English abstract)

[24] 張小宏,趙生良,陳豐田. Agisoft photoscan在無(wú)人機(jī)航空攝影影像數(shù)據(jù)處理中的應(yīng)用[J]. 價(jià)值工程,2013(20):230-231. Zhang Xiaohong, Zhao Shengliang, Chen Fengtian. The application of agisoft photoscan in UAV aerial photographic image data processing[J].Value Engineering, 2013(20): 230-231. (in Chinese with English abstract)

[25] 張俊,于慶國(guó),侯家槐. 面向?qū)ο蟮母叻直媛视跋穹诸惻c信息提取[J]. 遙感技術(shù)與應(yīng)用,2010,25(1):112-117. Zhang Jun, Yu Qingguo, Hou Jiahuai. Object-oriented classification and information extraction based on high spatial resolution remote sensing image[J].Remote Sensing Technology and Application, 2010, 25(1): 112-117. (in Chinese with English abstract)

[26] 羅開(kāi)盛,李仁東,常變?nèi)? 利用面向?qū)ο蠓诸惣夹g(shù)的大尺度土地覆被調(diào)查方法[J]. 中國(guó)科學(xué)院大學(xué)學(xué)報(bào),2013,30(6):770-777. Luo Kaisheng, Li Rendong, Chang Bianrong. Land-cover survey method using object-oriented technology and HJ-CCD image on large scale[J]. Journal of University of Chinese Academy of Sciences, 2013, 30(6): 770-777. (in Chinese with English abstract)

[27] 郭琳,裴志遠(yuǎn),吳全,等. 面向?qū)ο蟮耐恋乩?覆蓋遙感分類方法與流程應(yīng)用[J]. 農(nóng)業(yè)工程學(xué)報(bào),2010,26(7):194-198. Guo Lin, Pei Zhiyuan, Wu Quan, et al. Application of method and process of object-oriented land use-cover classification using remote sensing images[J]. Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2010, 26(7): 194-198. (in Chinese with English abstract)

[28] 杜謙,范文,李凱,等.二元Logistic回歸和信息量模型在地質(zhì)災(zāi)害分區(qū)中的應(yīng)用[J]. 災(zāi)害學(xué),2017,32(2):220-226. Du Qian, Fan Wen, Li Kai, et al. Geohazard susceptibility assessment by using binary logical regression and Information value model[J]. Journal of Catastrophology, 2017, 32(2): 220-226. (in Chinese with English abstract)

[29] 萬(wàn)婷,蒲春玲,劉志有.農(nóng)戶耕地利用影響因素二元Logistic回歸模型分析:以新疆阿瓦提縣為例[J]. 新疆農(nóng)業(yè)科學(xué),2012,49(7):1366-1370. Wan Ting, Pu Chunling, Liu Zhiyou. Analysis of influence factors of farmers’ cultivated land use by binary logistic regression mode: A case study of a wat county in Xingjiang[J]. Xinjiang Agricultural Sciences, 2012, 49(7): 1366-1370. (in Chinese with English abstract)

[30] 蔣斌,賈克斌. 一種用于表情識(shí)別的局部判別分量分析算法[J]. 電子學(xué)報(bào),2014,42(1):155-159. Jiang Bin, Jia Kebin. A local discriminative component analysis algorithm for facial expression recognition[J]. Acta Electronica Sinica, 2014, 42(1): 155-159. (in Chinese with English abstract)

[31] 謝嘉麗,李永樹,李何超,等. 利用灰度共生矩陣紋理特征識(shí)別空心村損毀建筑物的方法[J]. 測(cè)繪通報(bào),2017(12):90-93. Xie Jiali, Li Yongshu, Li Hechao, et al. Recognition of damage buildings in hollow village based on texture feature of gray level co-ocurrence matrix[J]. Bulletin of Surveying and Mapping, 2017(12): 90-93. (in Chinese with English abstract)

Extraction of rice planting information based on remote sensing image from UAV

Li Ming1,3, Huang Yuqi1, Li Xumeng2, Peng Dongxing1, Xie Jingxin1

(1,,410128,; 2.,410128,; 3.,410100,)

The rice is the main crop in China. Based on the advantages of flexibility, high accuracy and short working cycle of the unmanned aerial vehicle (UAV), in this paper, we aim to establish a method for the investigation of rice planting area by UAV remote sensing image. The six-rotor UAV's camera image sensor is CMOS with FOV94. The focus is on infinity. The maximum single pixel is 4 000×3 000 pixels. The experimental region and verification region mainly included rice, tree, grassland, bare land, water body and buildings and so on. At first, the multiple images with overlapped region were obtained by UAV. The complete images of the experimental region and the verification region were obtained by Agisoft photoscan software. The image spatial resolution of the experimental region was 0.04 m and the verification region was 0.02 m. The multiresolution segmentation algorithm of eCognition Developer 9 software was used to segment the complete image of the experimental region and the verification region to obtain several objects and calculate the spectral, geometric, and texture features of each object. Using multiresolution segmentation algorithm to segment the image, the scale parameter of experimental region: scale=480, shape=0.1, compact=0.1, and the total number of objects after the segmentation were 880. The scale parameter of experimental region: scale=1 500, shape=0.1, compact=0.3, a total of 240 split object after segmentation. Subjects in the experimental region and the verification region were divided into training samples and verification samples. Training samples in the experimental region were used to extract characteristic indexes for identifying rice, binary logistic model training samples for identifying rice, and establishment and verification of characteristic indexes. The sample was used to test the race recognition model. The characteristics indexes of race identified in this study were shape index, red mean, red standard deviation Max.diff (maximum difference), GLCM contrast (gray-level co-occurrence matrix contrast) and GLCM dissimilarity(gray-level co-occurrence matrix contrast dissimilarity). The red mean was the index for distinguishing vegetation cover (rice, grassland, tree) and non-vegetation covered objects (bare land, water body, building); red standard deviation and Max.diff (maximum difference) value depicted the color change of rice and grassland; and the color of rice was relatively uniform, with uneven growth and relatively large changes in color. The color of rice and tree changes was small, but the border of the tree was fragmented, the shape index was larger, and the shape index can effectively distinguish between the color mean and the change of rice and tree body. The texture features reflected the slowly-changing or periodically changing structure and arrangement properties of the land surface. Rice, tree, grassland, bare land, water body, and building all had certain differences. It was reasonable to distinguish the six characteristic indexes from the test area and the verification area based on the mechanism analysis, including shape index, red mean, red standard deviation, Max.diff (maximum difference). Based on GLCM contrast (gray-level co-occurrence matrix contrast) and GLCM dissimilarity (gray-level co-occurrence matrix contrast dissimilarity), six characteristic indexes Logistic model of discriminating two classifications of rice land lots, experimental region’s identification of training sample set the correct rate was 100%, the correct rate of validation sample set was 97%, and the overall correct rate was 98%. When the correct rate of training sample set was 100%, the correct rate of validation sample set was 99%, the overall correct rate was 99% on the verification region. Based on the image pixel method, the area of rice was measured and the area error was less than 3.5% compared with the result of visual interpretation. This method had a good effect in identifying paddy fields and high accuracy in area estimation. Therefore, this study had some applicability to the use of UAV visible light remote sensing imagery to survey rice planting information, and had certain reference value for rice census. The results showed that the growth period of paddy rice in the wrongly classified rice lags behind and had not been closed yet. Therefore, this method identified the influence of paddy field growth period on paddy fields and carries out multiple surveys at different times to further improve the method of identifying paddy rice plots the effective way to correct rate.

unmanned aerial vehicle; remote sensing; crops; visible; rice; multi-feature

2017-10-28

2018-01-10

湖南省創(chuàng)新平臺(tái)與人才計(jì)劃(2017RS3061);長(zhǎng)沙市高新技術(shù)產(chǎn)業(yè)發(fā)展專項(xiàng)重點(diǎn)項(xiàng)目(K1508073-11);湖南省技術(shù)創(chuàng)新引導(dǎo)計(jì)劃(2016GK4123);基于無(wú)人機(jī)數(shù)據(jù)采集平臺(tái)水稻水肥精準(zhǔn)管理關(guān)鍵技術(shù)的研究與示范(2017NK2382)

李 明,博士后,教授,博士生導(dǎo)師,主要從事精準(zhǔn)農(nóng)業(yè)及機(jī)器人研究。Email:liming@hunau.net。中國(guó)農(nóng)業(yè)工程學(xué)會(huì)會(huì)員:李明(E041200580S)。

10.11975/j.issn.1002-6819.2018.04.013

S127

A

1002-6819(2018)-04-0108-07

李 明,黃愉淇,李緒孟,彭冬星,謝景鑫. 基于無(wú)人機(jī)遙感影像的水稻種植信息提取[J]. 農(nóng)業(yè)工程學(xué)報(bào),2018,34(4):108-114.doi:10.11975/j.issn.1002-6819.2018.04.013 http://www.tcsae.org

Li Ming, Huang Yuqi, Li Xumeng, Peng Dongxing, Xie Jingxin. Extraction of rice planting information based on remote sensing image from UAV[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(4): 108-114. (in Chinese with English abstract) doi:10.11975/j.issn.1002-6819.2018.04.013 http://www.tcsae.org

猜你喜歡
正確率試驗(yàn)區(qū)灰度
采用改進(jìn)導(dǎo)重法的拓?fù)浣Y(jié)構(gòu)灰度單元過(guò)濾技術(shù)
基于灰度拉伸的圖像水位識(shí)別方法研究
門診分診服務(wù)態(tài)度與正確率對(duì)護(hù)患關(guān)系的影響
18個(gè)自貿(mào)試驗(yàn)區(qū)
商周刊(2019年19期)2019-10-17 03:23:44
各試驗(yàn)區(qū)先行先試 探索創(chuàng)造模范做法
我國(guó)自由貿(mào)易試驗(yàn)區(qū)發(fā)展現(xiàn)狀以及未來(lái)展望
基于最大加權(quán)投影求解的彩色圖像灰度化對(duì)比度保留算法
生意
品管圈活動(dòng)在提高介入手術(shù)安全核查正確率中的應(yīng)用
基于灰度線性建模的亞像素圖像抖動(dòng)量計(jì)算
404 Not Found

404 Not Found


nginx
宁国市| 三明市| 湟中县| 徐州市| 繁峙县| 张掖市| 进贤县| 朝阳区| 灵山县| 和顺县| 辉县市| 炉霍县| 新源县| 肥东县| 怀宁县| 普安县| 武清区| 五原县| 石景山区| 阜城县| 中卫市| 康马县| 仁怀市| 安多县| 湘阴县| 安阳县| 阿拉善左旗| 永和县| 江口县| 五大连池市| 宽甸| 肥西县| 龙胜| 安丘市| 区。| 塔河县| 从江县| 碌曲县| 昌宁县| 富源县| 濮阳市|