基于立體視覺(jué)的無(wú)人機(jī)感知與規(guī)避研究
發(fā)布時(shí)間：2018-10-17 17:24
【摘要】：無(wú)人機(jī)(Unmanned Aerial Vehicle,UAV)是目前國(guó)內(nèi)外的研究熱點(diǎn)。隨著無(wú)人機(jī)的廣泛使用,無(wú)人機(jī)的自主安全飛行提出了要求,無(wú)人機(jī)感知與規(guī)避(Sense and Avoid,SAA)能力是保證無(wú)人機(jī)進(jìn)入空域飛行、保障無(wú)人機(jī)飛行安全的先決條件。輕小型無(wú)人機(jī)系統(tǒng)因載荷、任務(wù)、成本等限制,無(wú)法搭載大型感知設(shè)備如雷達(dá)、激光雷達(dá)等,基于視覺(jué)傳感器的SAA系統(tǒng)在質(zhì)量、功耗、成本方面的優(yōu)勢(shì)使其更易在輕小型系統(tǒng)集成和應(yīng)用。本文針對(duì)輕小型無(wú)人機(jī)的視覺(jué)感覺(jué)與規(guī)避進(jìn)行研究。考慮單目視覺(jué)只能得到目標(biāo)的二維平面運(yùn)動(dòng)信息,本文采用基于立體視覺(jué)的感知與規(guī)避技術(shù),實(shí)現(xiàn)目標(biāo)精確感知、可靠威脅評(píng)估和障礙物規(guī)避,克服了單目視覺(jué)難以獲取目標(biāo)的深度信息的缺點(diǎn)。本文主要研究工作如下:1.從體系方案、政策標(biāo)準(zhǔn)、技術(shù)研究等方面分析了SAA。系統(tǒng)全面分析了SAA技術(shù)發(fā)展史,SAA技術(shù)研究史。分析了無(wú)人機(jī)SAA的意義以及各國(guó)對(duì)無(wú)人機(jī)SAA技術(shù)研究情況。對(duì)無(wú)人機(jī)SAA進(jìn)行層次分解和技術(shù)分解,分析了無(wú)人機(jī)SAA方法。根據(jù)SAA技術(shù)100年發(fā)展史以及基于無(wú)人機(jī)SAA的研究現(xiàn)狀,提出SAA技術(shù)下一步發(fā)展并對(duì)SAA的未來(lái)關(guān)鍵技術(shù)進(jìn)行分析。2.圍繞輕小型無(wú)人機(jī)的應(yīng)用特點(diǎn)和能力屬性出發(fā),分析并搭建了一套低成本、低功耗感知與規(guī)避系統(tǒng)。針對(duì)小型無(wú)人機(jī)系統(tǒng)載荷小、飛行速度低等約束,從環(huán)境數(shù)據(jù)感知、機(jī)載數(shù)據(jù)處理、障礙規(guī)避控制等方面分別進(jìn)行等硬件系統(tǒng)設(shè)計(jì);針對(duì)感知與規(guī)避系統(tǒng)能力要求,對(duì)立體視覺(jué)感知系統(tǒng)進(jìn)行建模和標(biāo)定。3.針對(duì)低空無(wú)人機(jī)環(huán)境復(fù)雜多變的特點(diǎn),設(shè)計(jì)了多模式無(wú)人機(jī)感知與規(guī)避算法。針對(duì)無(wú)人機(jī)飛行環(huán)境的不同,無(wú)人機(jī)在不同空域環(huán)境下不同的遭遇環(huán)境進(jìn)行相應(yīng)的建模。在低空環(huán)境,通過(guò)重構(gòu)三維環(huán)境,采用UV視差法進(jìn)行障礙物檢測(cè);在高空環(huán)境,背景相對(duì)簡(jiǎn)單、空域障礙物多為運(yùn)動(dòng)的、微小的、特征點(diǎn)少,采用背景分割與弱小目標(biāo)檢測(cè)算法進(jìn)行障礙物檢測(cè)并通過(guò)三角定位法對(duì)障礙物進(jìn)行測(cè)距。采用安全包絡(luò)法對(duì)運(yùn)動(dòng)目標(biāo)進(jìn)行威脅評(píng)估,根據(jù)威脅評(píng)估結(jié)果,采用目標(biāo)規(guī)避點(diǎn)方法對(duì)障礙物進(jìn)行規(guī)避。實(shí)驗(yàn)結(jié)果表明,基于立體視覺(jué)的無(wú)人機(jī)感知與規(guī)避系統(tǒng)能夠?qū)崿F(xiàn)不同空域環(huán)境下的障礙物避撞,保障無(wú)人機(jī)的飛行安全。
[Abstract]:Unmanned aerial vehicle (Unmanned Aerial Vehicle,UAV) is a research hotspot at home and abroad. With the wide use of UAV, the autonomous safety flight of UAV is required. The ability of UAV to perceive and evade (Sense and Avoid,SAA is the prerequisite to ensure the UAV to fly into airspace and to ensure the UAV flight safety. Because of the limitation of load, task, cost and so on, the light and small UAV system can not carry large sensing equipment such as radar, lidar and so on. The SAA system based on vision sensor has high quality and power consumption. Cost advantages make it easier to integrate and apply in light and small systems. In this paper, the visual perception and avoidance of light and small UAV are studied. Considering that monocular vision can only obtain two-dimensional planar motion information of the target, this paper uses stereo vision based perception and circumvention technology to realize target accurate perception, reliable threat assessment and obstacle avoidance. It overcomes the disadvantage that monocular vision is difficult to obtain depth information of target. The main work of this paper is as follows: 1. This paper analyzes SAA. from the aspects of system scheme, policy standard, technology research and so on. The development history of SAA technology and the history of SAA technology research are systematically analyzed. The significance of UAV SAA and the research of UAV SAA technology are analyzed. The SAA of UAV is decomposed by hierarchical decomposition and technical decomposition, and the SAA method of UAV is analyzed. According to the 100-year history of SAA technology and the research status of UAV SAA, this paper puts forward the next development of SAA technology and analyzes the key technology of SAA in the future. 2. Based on the application characteristics and capability attributes of light and small UAV, a set of low cost, low power sensing and evading system is analyzed and built. Aiming at the small UAV system with small load and low flight speed, the hardware system is designed from the aspects of environmental data perception, airborne data processing, obstacle avoidance control, etc. Modeling and calibration of stereo vision perception system. 3. In view of the complex and changeable environment of low altitude UAV, a multi-mode UAV perception and avoidance algorithm is designed. According to the different flight environment of UAV, the UAV has different encounter environment in different airspace environment. In low altitude environment, by reconstruction of 3D environment, UV parallax method is used to detect obstacles. In high altitude environment, the background is relatively simple, and the obstacles in airspace are mostly moving, small and few feature points. Background segmentation and small and weak target detection algorithms are used to detect obstacles and the distance of obstacles is measured by triangulation. The method of security envelope is used to evaluate the threat of moving target, and according to the result of threat assessment, the method of avoidance point is used to circumvent the obstacle. The experimental results show that the UAV perception and avoidance system based on stereo vision can avoid obstacles in different airspace environment and ensure the flight safety of UAV.
【學(xué)位授予單位】：西北工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：V279
本文編號(hào)：2277406
[Abstract]:Unmanned aerial vehicle (Unmanned Aerial Vehicle,UAV) is a research hotspot at home and abroad. With the wide use of UAV, the autonomous safety flight of UAV is required. The ability of UAV to perceive and evade (Sense and Avoid,SAA is the prerequisite to ensure the UAV to fly into airspace and to ensure the UAV flight safety. Because of the limitation of load, task, cost and so on, the light and small UAV system can not carry large sensing equipment such as radar, lidar and so on. The SAA system based on vision sensor has high quality and power consumption. Cost advantages make it easier to integrate and apply in light and small systems. In this paper, the visual perception and avoidance of light and small UAV are studied. Considering that monocular vision can only obtain two-dimensional planar motion information of the target, this paper uses stereo vision based perception and circumvention technology to realize target accurate perception, reliable threat assessment and obstacle avoidance. It overcomes the disadvantage that monocular vision is difficult to obtain depth information of target. The main work of this paper is as follows: 1. This paper analyzes SAA. from the aspects of system scheme, policy standard, technology research and so on. The development history of SAA technology and the history of SAA technology research are systematically analyzed. The significance of UAV SAA and the research of UAV SAA technology are analyzed. The SAA of UAV is decomposed by hierarchical decomposition and technical decomposition, and the SAA method of UAV is analyzed. According to the 100-year history of SAA technology and the research status of UAV SAA, this paper puts forward the next development of SAA technology and analyzes the key technology of SAA in the future. 2. Based on the application characteristics and capability attributes of light and small UAV, a set of low cost, low power sensing and evading system is analyzed and built. Aiming at the small UAV system with small load and low flight speed, the hardware system is designed from the aspects of environmental data perception, airborne data processing, obstacle avoidance control, etc. Modeling and calibration of stereo vision perception system. 3. In view of the complex and changeable environment of low altitude UAV, a multi-mode UAV perception and avoidance algorithm is designed. According to the different flight environment of UAV, the UAV has different encounter environment in different airspace environment. In low altitude environment, by reconstruction of 3D environment, UV parallax method is used to detect obstacles. In high altitude environment, the background is relatively simple, and the obstacles in airspace are mostly moving, small and few feature points. Background segmentation and small and weak target detection algorithms are used to detect obstacles and the distance of obstacles is measured by triangulation. The method of security envelope is used to evaluate the threat of moving target, and according to the result of threat assessment, the method of avoidance point is used to circumvent the obstacle. The experimental results show that the UAV perception and avoidance system based on stereo vision can avoid obstacles in different airspace environment and ensure the flight safety of UAV.
【學(xué)位授予單位】：西北工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：V279
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 吳成東;張潤(rùn);劉寶德;房卓群;;基于無(wú)人機(jī)航拍圖像拼接算法的優(yōu)化[J];沈陽(yáng)建筑大學(xué)學(xué)報(bào)(自然科學(xué)版);2015年01期
2 韓靜雅;王宏倫;劉暢;雷玉鵬;;基于視覺(jué)的無(wú)人機(jī)感知與規(guī)避系統(tǒng)設(shè)計(jì)[J];戰(zhàn)術(shù)導(dǎo)彈技術(shù);2014年05期
3 張洋;王新龍;;一種地標(biāo)點(diǎn)修正的高精度雙目視覺(jué)導(dǎo)航方法[J];北京航空航天大學(xué)學(xué)報(bào);2014年09期
4 常于敏;;無(wú)人機(jī)技術(shù)研究現(xiàn)狀及發(fā)展趨勢(shì)[J];電子技術(shù)與軟件工程;2014年01期
5 蔡志浩;楊麗曼;王英勛;李新軍;;無(wú)人機(jī)全空域飛行影響因素分析[J];北京航空航天大學(xué)學(xué)報(bào);2011年02期
6 高峰;魏少華;王學(xué)通;;基于SIFT特征點(diǎn)的圖像匹配算法[J];現(xiàn)代電子技術(shù);2010年18期
7 張寧;張友彬;張召才;王向軍;;基于同視場(chǎng)參考點(diǎn)的落點(diǎn)坐標(biāo)測(cè)量系統(tǒng)的設(shè)計(jì)與應(yīng)用[J];計(jì)量技術(shù);2008年04期
8 張青竹;張軍;劉偉;朱衍波;;民航空管應(yīng)用ADS-B的關(guān)鍵問(wèn)題分析[J];電子技術(shù)應(yīng)用;2007年09期
9 文貢堅(jiān),周秀芝;基于視差點(diǎn)的大遮擋檢測(cè)和立體匹配方法[J];軟件學(xué)報(bào);2005年05期
10 崔紅霞,林宗堅(jiān),孫杰;無(wú)人機(jī)遙感監(jiān)測(cè)系統(tǒng)研究[J];測(cè)繪通報(bào);2005年05期
相關(guān)碩士學(xué)位論文 前1條
1 唐志豪;基于雙目立體視覺(jué)的測(cè)量技術(shù)研究[D];江蘇大學(xué);2006年
，本文編號(hào)：2277406
本文鏈接：http://sikaile.net/kejilunwen/hangkongsky/2277406.html
最近更新
教材專著
