本文選題：無(wú)人機(jī) + 魚眼矯正��； 參考：《電子科技大學(xué)》2017年碩士論文

【摘要】：近年來(lái),無(wú)人機(jī)憑借使用方便、成本低廉的優(yōu)點(diǎn),成為了各領(lǐng)域應(yīng)用的“新寵”,如環(huán)境監(jiān)測(cè)、媒體報(bào)道、電商快遞等。由于外界環(huán)境復(fù)雜,無(wú)人機(jī)的GPS信號(hào)存在丟失或者干擾的可能,此時(shí)基于視覺(jué)的導(dǎo)航方式就顯得尤為重要。目前已有許多針對(duì)視覺(jué)導(dǎo)航的研究,但已實(shí)地應(yīng)用的方法較少。本文基于無(wú)人機(jī)自主飛行項(xiàng)目撰寫,工作重點(diǎn)之一為研究圖像畸變矯正方法和圖像拼接技術(shù),工作重點(diǎn)之二是自主降落階段的地標(biāo)設(shè)計(jì)與識(shí)別。針對(duì)無(wú)人機(jī)利用航拍相機(jī)采集的圖片容易產(chǎn)生畸變的問(wèn)題,本文首先分析了相機(jī)的成像原理,選用張正友標(biāo)定法對(duì)相機(jī)進(jìn)行標(biāo)定。先制作棋盤格標(biāo)定板,用航拍相機(jī)采集標(biāo)定版不同方位角的圖像,提取Harris角點(diǎn),計(jì)算得到相機(jī)的內(nèi)外參數(shù)矩陣和畸變系數(shù),再利用極大似然估計(jì)對(duì)內(nèi)外參數(shù)和畸變系數(shù)進(jìn)行優(yōu)化。最后,利用畸變系數(shù)矯正圖像,得到較好的矯正結(jié)果。圖像拼接時(shí),本文采用基于SIFT特征的圖像拼接技術(shù),先提取待拼接地圖的SIFT特征點(diǎn),生成128維的特征向量描述子,計(jì)算兩張待拼接圖片的特征點(diǎn)匹配情況。為了過(guò)濾誤匹配點(diǎn),首先采用最小距離和次小距離的比值進(jìn)行篩選,對(duì)篩選出來(lái)的候選匹配點(diǎn)對(duì),再利用RANSAC算法進(jìn)行優(yōu)化,誤匹配點(diǎn)比例降低了74.74%。根據(jù)選出的匹配點(diǎn)對(duì)計(jì)算得到代表圖像變換關(guān)系的單應(yīng)性矩陣,用單應(yīng)性矩陣將待拼接圖像像素變換到基準(zhǔn)圖像坐標(biāo)系,生成拼接圖。本文提出了平均融合法和加權(quán)平均融合法對(duì)圖像的重合區(qū)域進(jìn)行像素融合,均得到了較好的拼接結(jié)果。最后,本文實(shí)現(xiàn)了多幅地圖的自動(dòng)拼接算法。自主降落部分,本文設(shè)計(jì)了簡(jiǎn)單易識(shí)別的H地標(biāo),對(duì)獲取的降落圖像進(jìn)行預(yù)處理得到灰度圖,再將自適應(yīng)閾值法應(yīng)用到灰度圖的二值化中,提取圖像中的輪廓,依據(jù)輪廓的長(zhǎng)度和面積等信息,過(guò)濾出非地標(biāo)輪廓。最后在候選輪廓中,利用形狀的Hu不變矩判斷是否是降落標(biāo)志輪廓。本項(xiàng)目改進(jìn)了H地標(biāo),增加輪廓邊緣,并且將自適應(yīng)閾值法應(yīng)用于圖像二值化中,增強(qiáng)了地標(biāo)在各種環(huán)境下的魯棒性。本文還提出了一套能夠?qū)崿F(xiàn)低空小范圍內(nèi)視覺(jué)降落的四旋翼無(wú)人機(jī)軟硬件方案,并在電子科技大學(xué)清水河校區(qū)驗(yàn)證了視覺(jué)自主降落系統(tǒng)的可行性、穩(wěn)定性和準(zhǔn)確性,實(shí)驗(yàn)表明降落精度能夠達(dá)到設(shè)計(jì)要求的1米。
[Abstract]:In recent years, unmanned aerial vehicles (UAVs) have become "new favorites" for various applications, such as environmental monitoring, media reports, e-commerce couriers and so on, because of their advantages of convenience and low cost.Because of the complexity of the external environment, the GPS signal of UAV may be lost or interfered, so the vision-based navigation is particularly important.At present, there have been many researches on visual navigation, but few methods have been applied in the field.Based on UAV autonomous flight project, one of the key tasks is to study image distortion correction method and image splicing technology, and the second is to design and identify landmarks in autonomous landing stage.Aiming at the problem that the images collected by aerial camera are easily distorted, this paper first analyzes the imaging principle of the camera, and uses the calibration method of Zhang Zhengyou to calibrate the camera.First, the checkerboard was made, and the images of different azimuth angles of the calibration plate were collected by aerial camera. The Harris corner was extracted, and the internal and external parameter matrix and distortion coefficient of the camera were calculated.Then the maximum likelihood estimation is used to optimize the internal and external parameters and distortion coefficients.Finally, the distortion coefficient is used to correct the image, and a better correction result is obtained.In this paper, the image stitching technique based on SIFT features is used to extract the SIFT feature points of the map to be stitched, and a 128-dimensional feature vector descriptor is generated to calculate the matching of the feature points of the two images to be stitched.In order to filter the mismatched points, the ratio of the minimum distance to the sub-small distance is first used to screen the candidate matching points, and then the RANSAC algorithm is used to optimize the mismatch points. The ratio of the mismatched points is reduced by 74.74 points.According to the selected matching point pairs, the monogram matrix representing the image transformation relationship is obtained, and the pixels of the image to be stitched are transformed into the reference image coordinate system by the homotropic matrix to generate the splicing image.In this paper, an average fusion method and a weighted average fusion method are proposed for pixel fusion of the overlapped region of an image, and good results are obtained.Finally, this paper realizes the automatic mosaic algorithm of multiple maps.In the part of autonomous landing, we design a simple and easily recognizable H landmark, preprocess the landing image to get the gray image, and then apply the adaptive threshold method to the binarization of the gray image to extract the contour of the image.According to the length and area of the contour, the non-Landmark contour is filtered out.Finally, in the candidate contour, Hu invariant moment of shape is used to judge whether it is a descent mark contour.In this project, the H landmarks are improved, the contour edges are increased, and the adaptive threshold method is applied to the binarization of images, which enhances the robustness of the landmarks in various environments.This paper also proposes a software and hardware scheme of four-rotor UAV which can achieve visual landing in low altitude and small range, and verifies the feasibility, stability and accuracy of the visual autonomous landing system in Qingshuihe Campus of the University of Electronic Science and Technology.The experiment shows that the precision of landing can meet the design requirement of 1 meter.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：V279;TP391.41

【相似文獻(xiàn)】

相關(guān)博士學(xué)位論文 前4條

1 劉篤晉;面向植被識(shí)別的無(wú)人機(jī)圖像處理關(guān)鍵技術(shù)研究[D];成都理工大學(xué);2016年

2 賈樹蔥;智能交通網(wǎng)絡(luò)中資源競(jìng)爭(zhēng)與合作機(jī)制研究[D];北京郵電大學(xué);2017年

3 穆悅;戈壁表面多尺度礫石特征參數(shù)估算及其空間分布規(guī)律研究[D];中國(guó)林業(yè)科學(xué)研究院;2017年

4 袁建清;基于多尺度遙感的寒地水稻稻瘟病信息提取與識(shí)別研究[D];東北農(nóng)業(yè)大學(xué);2017年

相關(guān)碩士學(xué)位論文 前10條

1 溫爾雅;無(wú)人機(jī)圖像處理關(guān)鍵技術(shù)的研究與實(shí)現(xiàn)[D];電子科技大學(xué);2017年

2 李洪向;基于無(wú)人車和無(wú)人機(jī)協(xié)作的動(dòng)態(tài)降落研究[D];哈爾濱工業(yè)大學(xué);2017年

3 麥貴林;電力巡線無(wú)人機(jī)的測(cè)向與定位技術(shù)研究[D];哈爾濱工業(yè)大學(xué);2017年

4 雷雨默;多旋翼無(wú)人機(jī)堆狀體航空攝影測(cè)量[D];西安科技大學(xué);2017年

5 魏江鵬;小型多功能無(wú)人機(jī)設(shè)計(jì)優(yōu)化與控制[D];長(zhǎng)安大學(xué);2017年

6 郭倩倩;無(wú)人機(jī)天線自動(dòng)跟蹤系統(tǒng)的設(shè)計(jì)[D];杭州電子科技大學(xué);2017年

7 劉見禮;基于無(wú)人機(jī)立體影像數(shù)據(jù)的森林結(jié)構(gòu)參數(shù)調(diào)查研究[D];中國(guó)科學(xué)院大學(xué)(中國(guó)科學(xué)院遙感與數(shù)字地球研究所);2017年

8 王斌;八旋翼電動(dòng)植保無(wú)人機(jī)的研制與試驗(yàn)分析[D];吉林農(nóng)業(yè)大學(xué);2017年

9 張紀(jì)敏;面向空中—水面協(xié)作的自主起降系統(tǒng)設(shè)計(jì)及控制[D];沈陽(yáng)理工大學(xué);2017年

10 莫德強(qiáng);基于無(wú)人機(jī)平臺(tái)的道路車輛違章超速行為檢測(cè)算法研究[D];哈爾濱工業(yè)大學(xué);2017年

，

本文編號(hào)：1753924