本文選題：點(diǎn)云去噪 + 參數(shù)��； 參考：《西北農(nóng)林科技大學(xué)》2017年碩士論文

【摘要】：作物模型三維重建以及可視化是當(dāng)前國(guó)內(nèi)外農(nóng)業(yè)信息化研究的重點(diǎn)領(lǐng)域,為了獲得高質(zhì)量三維點(diǎn)云數(shù)據(jù),點(diǎn)云去噪成為熱門的研究領(lǐng)域。目前,點(diǎn)云去噪方面的算法都是將圖像去噪方法移植到點(diǎn)云模型上,而單一的某種算法難以滿足多種形態(tài)點(diǎn)云的去噪要求。基于此,本文針對(duì)玉米葉片,研究其去噪問(wèn)題,并結(jié)合PC端與移動(dòng)端設(shè)計(jì)并開發(fā)了一款玉米葉片點(diǎn)云去噪軟件。本文主要的研究?jī)?nèi)容如下:(1)提出了一種移動(dòng)端和PC端結(jié)合的點(diǎn)云去噪方法。針對(duì)點(diǎn)云數(shù)量過(guò)多,離群點(diǎn)太多,導(dǎo)致運(yùn)行效率慢,無(wú)法直接在移動(dòng)端進(jìn)行去噪等問(wèn)題,分析點(diǎn)云精簡(jiǎn)算法和去噪算法,結(jié)合玉米葉片和平臺(tái)的特點(diǎn),在點(diǎn)云精簡(jiǎn)方面采用體素化網(wǎng)格下采樣簡(jiǎn)化算法;PC端去噪采用K近鄰點(diǎn)距離統(tǒng)計(jì)去噪算法,該方法可以通過(guò)多次調(diào)整K鄰近點(diǎn)的個(gè)數(shù)和閾值來(lái)達(dá)到去除明顯噪聲點(diǎn)的效果。移動(dòng)端去噪采用雙邊濾波去噪算法,該方法可以在保持葉片邊緣特征的情況下去除小尺度噪聲點(diǎn)。(2)設(shè)計(jì)和開發(fā)點(diǎn)云去噪軟件。針對(duì)去噪和精簡(jiǎn)算法的參數(shù)選擇范圍太廣,普通用戶無(wú)法選擇合適參數(shù)的問(wèn)題,本文使用數(shù)量不同的點(diǎn)云數(shù)據(jù)進(jìn)行去噪實(shí)驗(yàn),結(jié)果表明閾值的選擇對(duì)點(diǎn)云去噪有較大的影響,閾值選擇過(guò)大,達(dá)不到去噪的效果,選擇過(guò)小,會(huì)導(dǎo)致去噪程度過(guò)大出現(xiàn)大量的孔洞;而鄰近點(diǎn)數(shù)量在閾值選取合理范圍內(nèi)會(huì)起到保護(hù)葉片形態(tài)的作用。當(dāng)玉米葉片為80000左右的時(shí)候,體素化網(wǎng)格邊長(zhǎng)選擇1.2～2.6之間,玉米葉片點(diǎn)云精簡(jiǎn)率為30%～60%,此時(shí)閾值選擇1.2～1.6之間,鄰近點(diǎn)數(shù)量為80時(shí)在PC端去除離群點(diǎn)的效果較好,然后在移動(dòng)端進(jìn)行小尺度噪聲去除,觀察法向量方向,去噪處理后,雜亂的法向量變得有序,去噪時(shí)間在15.3s以內(nèi),在效果和時(shí)間上均得到較為理想的結(jié)果。(3)軟件測(cè)試。針對(duì)軟件存在的潛在問(wèn)題,編寫了較為詳細(xì)的測(cè)試用例,對(duì)軟件進(jìn)行數(shù)據(jù)輸入測(cè)試和功能測(cè)試,測(cè)試結(jié)果表明軟件在輸入不合理的或者非法的數(shù)值不會(huì)使程序中止,而輸入合理范圍內(nèi)的數(shù)值會(huì)得到相應(yīng)的結(jié)果,對(duì)超出程序范圍的輸入給出提示,不同形態(tài)、不同數(shù)量的玉米葉片點(diǎn)云去噪效果均可滿足要求,在移動(dòng)端測(cè)試時(shí),數(shù)據(jù)量不合理會(huì)給出相應(yīng)的提示。
[Abstract]:Three-dimensional reconstruction and visualization of crop models are the key areas of agricultural information research at home and abroad. In order to obtain high-quality 3D point cloud data point cloud denoising has become a hot research field. At present, the image denoising method is transplanted to the point cloud model, but a single algorithm is difficult to meet the needs of a variety of morphological point cloud de-noising. Based on this, this paper studies the problem of corn leaf de-noising, and designs and develops a corn leaf point cloud denoising software combined with PC and mobile side. The main contents of this paper are as follows: 1) A point cloud denoising method combining mobile and PC is proposed. In view of the problems of too many point clouds and too many outliers, which result in slow operation efficiency and the inability to carry out de-noising directly at the mobile end, this paper analyzes the point cloud reduction algorithm and denoising algorithm, combining with the characteristics of maize leaves and platforms. In the aspect of point cloud reduction, a voxel mesh sampling simplification algorithm is used to de-noise the PC end. The K-nearest neighbor point distance statistical de-noising algorithm is adopted. This method can remove obvious noise points by adjusting the number and threshold of K adjacent points several times. The two-sided filter denoising algorithm is used in the mobile end denoising. This method can remove the small scale noise point while keeping the edge feature of the blade. (2) the point cloud denoising software is designed and developed. Aiming at the problem that the parameter selection range of the denoising and reduction algorithms is too wide and ordinary users can not choose the appropriate parameters, this paper uses different number of point cloud data to carry out the denoising experiment. The results show that the choice of threshold has a great influence on the point cloud denoising. If the threshold value is too large, the effect of de-noising can not be achieved, and too small a choice will lead to a large number of holes in the denoising degree, and the number of adjacent points will protect the leaf morphology within a reasonable range of threshold selection. When the maize leaves were about 80000, the volumetric grid length was 1.22.6.The point cloud reduction rate of maize leaves was 300.600.When the threshold value was between 1.2 and 1.6, and the number of adjacent points was 80, the effect of removing outliers at the PC end was better when the threshold value was between 1.2 and 1.6, and when the number of adjacent points was 80, it was better to remove outliers at the PC end. Then the small scale noise removal is carried out at the mobile end, the direction of the normal vector is observed. After denoising, the chaotic normal vector becomes orderly, the denoising time is less than 15.3s, and the result of software testing is satisfactory in both effect and time. Aiming at the potential problems of the software, a more detailed test case is written to test the data input and function of the software. The test results show that the software does not suspend the program in the input of unreasonable or illegal values. And the values within a reasonable range of input will get the corresponding results, the input beyond the scope of the program to give a hint, different shapes, different quantities of corn leaf point cloud denoising effect can meet the requirements, in the mobile side test, Unreasonable amount of data will give a corresponding hint.
【學(xué)位授予單位】：西北農(nóng)林科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：S513;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 何東健;邵小寧;王丹;胡少軍;;Kinect獲取植物三維點(diǎn)云數(shù)據(jù)的去噪方法[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2016年01期

2 王勇;唐靖;饒勤菲;袁巢燕;;一種新的散亂點(diǎn)云快速去噪算法[J];計(jì)算機(jī)應(yīng)用與軟件;2015年07期

3 李博陽(yáng);耿楠;張志毅;;基于機(jī)器視覺(jué)的激光條紋掃描系統(tǒng)[J];計(jì)算機(jī)仿真;2015年06期

4 宋陽(yáng);李昌華;馬宗方;李智杰;;應(yīng)用于三維點(diǎn)云數(shù)據(jù)去噪的改進(jìn)C均值算法[J];計(jì)算機(jī)工程與應(yīng)用;2015年12期

5 葉珉?yún)?花向紅;陳西江;魏成;;基于正交整體最小二乘平面擬合的點(diǎn)云數(shù)據(jù)去噪方法研究[J];測(cè)繪通報(bào);2013年11期

6 陳璋雯;達(dá)飛鵬;;基于模糊熵迭代的三維點(diǎn)云精簡(jiǎn)算法[J];光學(xué)學(xué)報(bào);2013年08期

7 孫金虎;周來(lái)水;安魯陵;;應(yīng)用最小生成樹實(shí)現(xiàn)點(diǎn)云分割[J];中國(guó)圖象圖形學(xué)報(bào);2012年07期

8 郝慧麗;劉先勇;;含噪點(diǎn)云預(yù)處理技術(shù)研究[J];微型機(jī)與應(yīng)用;2012年12期

9 葛寶臻;項(xiàng)晨;田慶國(guó);彭博;;基于曲率特征混合分類的高密度點(diǎn)云去噪方法[J];納米技術(shù)與精密工程;2012年01期

10 張巧英;陳浩;朱爽;;密度聚類算法在連續(xù)分布點(diǎn)云去噪中的應(yīng)用[J];地理空間信息;2011年06期

相關(guān)博士學(xué)位論文 前2條

1 陳杰;空間離散點(diǎn)集三維建模及簡(jiǎn)化算法研究[D];昆明理工大學(xué);2012年

2 肖春霞;三維點(diǎn)采樣模型的數(shù)字幾何處理技術(shù)研究[D];浙江大學(xué);2006年

相關(guān)碩士學(xué)位論文 前8條

1 馬福峰;基于鄰域幾何特征約束的植株點(diǎn)云配準(zhǔn)算法研究[D];西北農(nóng)林科技大學(xué);2016年

2 姚洋;點(diǎn)云法向量估算研究[D];昆明理工大學(xué);2015年

3 張育鋒;三維數(shù)據(jù)點(diǎn)云的去噪及其檢測(cè)[D];南京信息工程大學(xué);2014年

4 王增濤;三維點(diǎn)云數(shù)據(jù)處理平臺(tái)設(shè)計(jì)[D];大連理工大學(xué);2014年

5 齊南;基于圖像序列的目標(biāo)三維重建技術(shù)研究[D];北京工業(yè)大學(xué);2013年

6 董艷;基于重要度的保形三角網(wǎng)格簡(jiǎn)化方法研究[D];西北農(nóng)林科技大學(xué);2013年

7 李丹;基于遠(yuǎn)程的線激光掃描3D表面重建技術(shù)研究[D];西北農(nóng)林科技大學(xué);2013年

8 劉洋;Android平臺(tái)下基于OpenGL ES的圖片瀏覽器的設(shè)計(jì)與實(shí)現(xiàn)[D];哈爾濱工業(yè)大學(xué);2012年

，

本文編號(hào)：2023732