【摘要】：水下機(jī)器人是復(fù)雜海洋環(huán)境工作中的重要運(yùn)載工具,隨著世界各國(guó)對(duì)海洋資源開(kāi)發(fā)的日益重視,水下機(jī)器人在海洋礦產(chǎn)勘探、海底地形探測(cè)和深�；A(chǔ)設(shè)施檢查等的應(yīng)用需求越來(lái)越大。而水下光視覺(jué)可以在水下機(jī)器人近距離觀測(cè)作業(yè)中提供更豐富的高分辨率信息,受到國(guó)內(nèi)外學(xué)者的廣泛關(guān)注。因此開(kāi)展基于視覺(jué)的小型水下航行器控制系統(tǒng)研究,對(duì)于提高水下機(jī)器人自主能力及智能化水平,具有重要地理論研究意義和實(shí)際應(yīng)用價(jià)值。在對(duì)水下航行器的光視覺(jué)目標(biāo)檢測(cè)方法研究中。首先,針對(duì)水下圖像降質(zhì)問(wèn)題,建立水下光傳播的衰減模型和水下成像系統(tǒng)模型,通過(guò)水介質(zhì)中光的衰減對(duì)顏色進(jìn)行恢復(fù)的算法來(lái)復(fù)原圖像完成預(yù)處理工作;然后,采用基于HSV的自適應(yīng)彩色圖像分割方法來(lái)對(duì)水下目標(biāo)物體進(jìn)行分割,并通過(guò)區(qū)域幾何形狀特征參數(shù)約束提取方法,最終實(shí)現(xiàn)對(duì)運(yùn)動(dòng)目標(biāo)區(qū)域的提取。最后,對(duì)動(dòng)目標(biāo)跟蹤方法的研究中,采用基于Kalman預(yù)測(cè)器結(jié)合動(dòng)態(tài)檢測(cè)窗口的目標(biāo)跟蹤算法,通過(guò)提取圖像中目標(biāo)質(zhì)心位置信息來(lái)實(shí)時(shí)對(duì)預(yù)測(cè)結(jié)果進(jìn)行更新校正,并進(jìn)行了水下航行器動(dòng)目標(biāo)跟蹤實(shí)驗(yàn)研究,以驗(yàn)證所用的目標(biāo)跟蹤方法的實(shí)時(shí)性和有效性。在水下航行器光視覺(jué)目標(biāo)識(shí)別跟蹤系統(tǒng)的基礎(chǔ)上,對(duì)其控制系統(tǒng)進(jìn)行研究和設(shè)計(jì),首先,對(duì)控制系統(tǒng)的總體結(jié)構(gòu)及其通信總線進(jìn)行了設(shè)計(jì);然后,分別詳細(xì)設(shè)計(jì)了分布式系統(tǒng)的各個(gè)子系統(tǒng),包括主控計(jì)算機(jī)系統(tǒng)、通信系統(tǒng)、推進(jìn)器控制系統(tǒng)、電源管理與安全系統(tǒng)和傳感器信息采集系統(tǒng);并對(duì)控制系統(tǒng)的軟件結(jié)構(gòu)進(jìn)行了設(shè)計(jì),最終形成了由軟硬件系統(tǒng)組成的基于視覺(jué)的分布式控制系統(tǒng)。在基于視覺(jué)的控制系統(tǒng)基礎(chǔ)上,為了實(shí)現(xiàn)水下航行器的自主目標(biāo)跟蹤功能,對(duì)其運(yùn)動(dòng)控制系統(tǒng)進(jìn)行了仿真研究。首先,本文對(duì)所設(shè)計(jì)的小型水下航行器的艇體結(jié)構(gòu)及各傳感器分布進(jìn)行介紹;然后,對(duì)所研究的水下航行器的六自由度運(yùn)動(dòng)模型進(jìn)行了分析,并解耦升沉和航向的動(dòng)力學(xué)方程表達(dá)式;最后對(duì)解耦的航向子系統(tǒng)與升沉子系統(tǒng)的控制進(jìn)行了設(shè)計(jì)與仿真,為后文的水下目標(biāo)識(shí)別跟蹤控制實(shí)驗(yàn)做了理論上的鋪墊工作。最后,對(duì)該小型水下航行器進(jìn)行了大量的水池實(shí)驗(yàn),包括傳感器濾波實(shí)驗(yàn),深度、航向控制實(shí)驗(yàn),結(jié)合本文研究的基于光視覺(jué)的目標(biāo)識(shí)別跟蹤系統(tǒng)設(shè)計(jì)了自主水下目標(biāo)跟蹤撞球?qū)嶒?yàn),驗(yàn)證本文所設(shè)計(jì)的基于視覺(jué)的控制系統(tǒng)的實(shí)時(shí)性和穩(wěn)定性。
[Abstract]:Underwater vehicle is an important vehicle in the work of complex marine environment. With the increasing attention paid to the exploitation of marine resources by countries all over the world, underwater vehicles are being explored in marine mineral resources. The application needs of submarine topography exploration and deep-sea infrastructure inspection are increasing. Underwater light vision can provide more high resolution information in the close observation operation of underwater vehicle, and it has been widely concerned by scholars at home and abroad. Therefore, the research on the control system of small underwater vehicle based on vision has important theoretical research significance and practical application value for improving the autonomous ability and intelligent level of underwater vehicle. In the research of optical visual target detection method for underwater vehicle. Firstly, aiming at the degradation problem of underwater image, the attenuation model of underwater light propagation and the model of underwater imaging system are established, and the image preprocessing is completed by the algorithm of color restoration by the attenuation of light in water medium. Then, adaptive color image segmentation method based on HSV is used to segment underwater object, and the geometric feature parameter constraint extraction method is used to extract the moving object region. Finally, in the research of moving target tracking method, the target tracking algorithm based on Kalman predictor and dynamic detection window is used to update and correct the prediction results by extracting the target centroid position information from the image. Experimental research on moving target tracking of underwater vehicle is carried out to verify the real time and effectiveness of the target tracking method. Based on the optical visual target recognition and tracking system of underwater vehicle, the control system is studied and designed. Firstly, the overall structure of the control system and its communication bus are designed. Then, each subsystem of the distributed system is designed in detail, including the main control computer system, the communication system, the propeller control system, the power management and safety system and the sensor information collection system. The software structure of the control system is designed and a distributed control system based on vision is formed. In order to realize the autonomous target tracking function of underwater vehicle, the motion control system of underwater vehicle is simulated on the basis of the control system based on vision. Firstly, the hull structure and sensor distribution of the designed small underwater vehicle are introduced in this paper. Then, the six-degree-of-freedom motion model of underwater vehicle is analyzed, and the dynamic equations of heave and heading are decoupled. Finally, the control of decoupled heading subsystem and heave subsystem is designed and simulated, which lays the groundwork for the later underwater target recognition and tracking control experiment. Finally, a large number of experiments are carried out on the small underwater vehicle, including sensor filtering experiment, depth control experiment and course control experiment. Combined with the object recognition and tracking system based on optical vision studied in this paper, an autonomous underwater target tracking and billiard experiment is designed, which verifies the real-time and stability of the visual based control system designed in this paper.
【學(xué)位授予單位】：哈爾濱工程大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類(lèi)號(hào)】：TP391.41;TP242

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 龐碩;糾海峰;;智能水下機(jī)器人研究進(jìn)展[J];科技導(dǎo)報(bào);2015年23期

2 楊?lèi)?ài)萍;鄭佳;王建;何宇清;;基于顏色失真去除與暗通道先驗(yàn)的水下圖像復(fù)原[J];電子與信息學(xué)報(bào);2015年11期

3 靳曉園;馬穎勁;;基于CAN總線技術(shù)的通訊類(lèi)軟件設(shè)計(jì)方法[J];航天控制;2015年05期

4 楊培培;趙詩(shī)雅;劉瑞勇;付登昊;李闖;;基于CAN總線的UUV通信系統(tǒng)與仿真[J];通信電源技術(shù);2015年05期

5 趙欣慰;金韜;池灝;曲嵩;;不同光照條件下水下成像背景光的建模與研究[J];物理學(xué)報(bào);2015年10期

6 魏延輝;田海寶;杜振振;劉鑫;郭志軍;趙大威;;微小型自主式水下機(jī)器人系統(tǒng)設(shè)計(jì)及試驗(yàn)[J];哈爾濱工程大學(xué)學(xué)報(bào);2014年05期

7 郭相鳳;賈建芳;楊瑞峰;葛中峰;;基于水下圖像光學(xué)成像模型的清晰化算法[J];計(jì)算機(jī)應(yīng)用;2012年10期

8 張河新;王曉輝;黃曉東;;基于STM32和CAN總線的智能數(shù)據(jù)采集節(jié)點(diǎn)設(shè)計(jì)[J];化工自動(dòng)化及儀表;2012年01期

9 高振會(huì);史先鵬;;深海技術(shù)與可持續(xù)發(fā)展[J];海洋開(kāi)發(fā)與管理;2011年07期

10 張榮;安志勇;孫敏;張倩索;;基于CAN總線的足球機(jī)器人通訊系統(tǒng)設(shè)計(jì)[J];長(zhǎng)春理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年02期

相關(guān)博士學(xué)位論文 前1條

1 孫飛飛;水下圖像增強(qiáng)和復(fù)原方法研究[D];中國(guó)海洋大學(xué);2011年

相關(guān)碩士學(xué)位論文 前10條

1 侯大力;水下航行器動(dòng)力學(xué)仿真[D];山東大學(xué);2014年

2 賀姣;基于色差模型的彩色圖像灰度化算法研究[D];西安電子科技大學(xué);2014年

3 王剛;基于多傳感器的AUV控制系統(tǒng)[D];哈爾濱工程大學(xué);2013年

4 向曄;深水自主水下航行器導(dǎo)航與運(yùn)動(dòng)控制系統(tǒng)的設(shè)計(jì)與研究[D];天津大學(xué);2012年

5 何焱;基于視頻的運(yùn)動(dòng)人物檢測(cè)[D];西安電子科技大學(xué);2013年

6 王同蘇;深海無(wú)人潛器高效推進(jìn)器的設(shè)計(jì)研究[D];哈爾濱工程大學(xué);2012年

7 趙宇熙;一種小型AUV的控制系統(tǒng)研究[D];哈爾濱工程大學(xué);2012年

8 張晶晶;基于遠(yuǎn)程遙操作的水下運(yùn)載器的控制器設(shè)計(jì)[D];上海交通大學(xué);2011年

9 張秉正;基于保留色度信息灰度化編碼的彩色圖像識(shí)別方法研究[D];東北師范大學(xué);2010年

10 杜剛;基于CAN總線的防爆遠(yuǎn)程I/O系統(tǒng)設(shè)計(jì)及硬件實(shí)現(xiàn)[D];上海交通大學(xué);2009年

，

本文編號(hào)：2401069