本文選題：目標(biāo)識(shí)別 + 水下移動(dòng)對(duì)象　； 參考：《哈爾濱工程大學(xué)》2016年碩士論文

【摘要】：地理信息系統(tǒng)(Geographic Information System)和水聲傳感器網(wǎng)絡(luò)(Underwater Acoustic Sensor Networks)的快速發(fā)展使得水下移動(dòng)對(duì)象的跟蹤和監(jiān)測(cè)成為現(xiàn)實(shí)。然而在水下未知目標(biāo)識(shí)別的研究中,傳統(tǒng)方法針對(duì)惡劣的水下環(huán)境、復(fù)雜的水下移動(dòng)對(duì)象運(yùn)動(dòng)軌跡和目標(biāo)分類(lèi)識(shí)別還存在不足。本文主要針對(duì)以上不足,對(duì)水下移動(dòng)對(duì)象識(shí)別過(guò)程中的時(shí)空數(shù)據(jù)模型和識(shí)別方法進(jìn)行研究。主要內(nèi)容如下:1)系統(tǒng)地研究水下移動(dòng)對(duì)象的軌跡特征和屬性特征,并詳細(xì)分析這些特征對(duì)水下移動(dòng)對(duì)象識(shí)別精度的影響。2)針對(duì)水下移動(dòng)對(duì)象軌跡的時(shí)空特點(diǎn),建立水下移動(dòng)對(duì)象模型(Underwater Moving ObjectDatabase,UMOD)。首先,提出了基于球坐標(biāo)的軌跡分解方法,降低了軌跡的整體復(fù)雜程度;其次,UMOD模型采用移動(dòng)對(duì)象時(shí)空模型中的動(dòng)態(tài)屬性方法,提出了針對(duì)水下未知目標(biāo)的動(dòng)態(tài)閾值位置更新策略,輔助軌跡分解并對(duì)誤差點(diǎn)進(jìn)行排除;最后,提出了軌跡擬合策略,對(duì)水下移動(dòng)對(duì)象進(jìn)行全時(shí)域軌跡描述,從而系統(tǒng)地得到水下移動(dòng)對(duì)象運(yùn)動(dòng)過(guò)程中的軌跡識(shí)別特征。3)分析和研究水下移動(dòng)對(duì)象的軌跡特征和屬性特征,建立水下移動(dòng)對(duì)象特征數(shù)據(jù)庫(kù),同時(shí)提出水下移動(dòng)對(duì)象混合特征識(shí)別方法(Underwater Moving Objects Mixed Feat-ure Recognition Method,UMOMFRM)。首先,UMOMFRM通過(guò)模糊推理的方法排除目標(biāo)的最小概率分類(lèi);其次,采用貝葉斯分類(lèi)算法計(jì)算未知目標(biāo)對(duì)應(yīng)剩余項(xiàng)目的概率;最后,對(duì)這些概率進(jìn)行概率閾值篩選并進(jìn)行最大概率比較,若存在最大概率,則其所對(duì)應(yīng)的類(lèi)別為分類(lèi)結(jié)果,否則該目標(biāo)所屬類(lèi)別為其他類(lèi)。4)采用模擬數(shù)據(jù)集進(jìn)行對(duì)比實(shí)驗(yàn)。首先,根據(jù)本文提出的UMOD模型對(duì)軌跡數(shù)據(jù)進(jìn)行處理,驗(yàn)證UMOD模型的準(zhǔn)確性。最后,進(jìn)行UMOMFRM與傳統(tǒng)水下目標(biāo)識(shí)別方法的對(duì)比試驗(yàn),比較識(shí)別率,以驗(yàn)證UMOMFRM的準(zhǔn)確性和有效性。
[Abstract]:With the rapid development of Geographic Information system (GIS) and underwater Acoustic Sensor Networks (underwater Sensor Networks), the tracking and monitoring of underwater moving objects becomes a reality. However, in the research of underwater unknown target recognition, the traditional method is insufficient for the poor underwater environment, the complex underwater moving object moving track and the target classification recognition. In this paper, the spatiotemporal data model and recognition method of underwater moving object recognition are studied. The main contents are as follows: 1) systematically studying the trajectory and attribute characteristics of underwater moving objects, and analyzing in detail the influence of these characteristics on the recognition accuracy of underwater moving objects. 2) aiming at the space-time characteristics of underwater moving objects, An underwater moving object model was established. Firstly, a trajectory decomposition method based on spherical coordinates is proposed to reduce the overall complexity of the trajectory. Secondly, the UMOD model adopts the dynamic attribute method in the moving object space-time model. A dynamic threshold position updating strategy for underwater unknown targets is proposed to assist trajectory decomposition and eliminate error points. Finally, a trajectory fitting strategy is proposed to describe the trajectory of underwater moving object in full time domain. Thus, the trajectory identification features of underwater moving objects are obtained systematically. 3) the trajectory characteristics and attribute characteristics of underwater moving objects are analyzed and studied, and the feature database of underwater moving objects is established. At the same time, a hybrid feature recognition method for underwater moving objects is proposed. First, UMOMFRM eliminates the minimum probability classification of targets by fuzzy reasoning; secondly, Bayesian classification algorithm is used to calculate the probability of unknown targets corresponding to the remaining items; finally, These probabilities are screened by probability threshold and compared with the maximum probabilities. If there is a maximum probability, the corresponding category is the result of classification, otherwise, the target belongs to another class. 4) A comparison experiment is carried out by using simulated data sets. Firstly, the trajectory data are processed according to the proposed UMOD model to verify the accuracy of the UMOD model. Finally, the accuracy and validity of UMOMFRM are verified by comparing UMOMFRM with traditional underwater target recognition methods.
【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)】：U675.79;TP212.9;TN929.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 朱丹丹;應(yīng)捷;田謹(jǐn);;基于貝葉斯分類(lèi)器的車(chē)載多類(lèi)障礙物分類(lèi)[J];信息技術(shù);2016年01期

2 周晶;宋輝;;基于徑向基神經(jīng)網(wǎng)絡(luò)的船舶運(yùn)動(dòng)擬合方法研究[J];計(jì)算機(jī)與數(shù)字工程;2015年09期

3 孟慶昕;楊士莪;于盛齊;;基于波形結(jié)構(gòu)特征和支持向量機(jī)的水面目標(biāo)識(shí)別[J];電子與信息學(xué)報(bào);2015年09期

4 胡正平;高紅霄;趙淑歡;;基于低秩分解的聯(lián)合動(dòng)態(tài)稀疏表示多觀(guān)測(cè)樣本分類(lèi)算法[J];電子學(xué)報(bào);2015年03期

5 張玲玲;黃建國(guó);韓晶;唐成凱;;基于短時(shí)傅里葉變換的水聲通信自適應(yīng)OFDM均衡[J];系統(tǒng)工程與電子技術(shù);2015年04期

6 蒲劍蘇;屈華民;倪明選;;移動(dòng)軌跡數(shù)據(jù)的可視化[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2012年10期

7 陳錦陽(yáng);宋加濤;劉良旭;王讓定;;基于改進(jìn)Hausdorff距離的軌跡聚類(lèi)算法[J];計(jì)算機(jī)工程;2012年17期

8 石敏;徐襲;岳劍平;;基于小波變換和概率神經(jīng)網(wǎng)絡(luò)的水下目標(biāo)識(shí)別[J];艦船科學(xué)技術(shù);2012年01期

9 趙雄飛;劉永葆;賀星;劉建華;;基于統(tǒng)計(jì)學(xué)檢驗(yàn)指標(biāo)的燃?xì)廨啓C(jī)部件特性方程擬合次數(shù)的選擇[J];航空發(fā)動(dòng)機(jī);2011年05期

10 張霞;;移動(dòng)對(duì)象數(shù)據(jù)庫(kù)的索引和查詢(xún)[J];電腦知識(shí)與技術(shù);2011年27期

相關(guān)會(huì)議論文 前1條

1 翁敬農(nóng);;移動(dòng)對(duì)象及其時(shí)空模型的研究[A];中國(guó)地理信息系統(tǒng)協(xié)會(huì)第九屆年會(huì)論文集[C];2005年

相關(guān)博士學(xué)位論文 前4條

1 楊宇;水下多通道真彩色三維重建與顏色還原方法研究[D];中國(guó)海洋大學(xué);2014年

2 徐爭(zhēng)光;經(jīng)驗(yàn)?zāi)Ｊ椒纸獾臄?shù)學(xué)理論研究[D];華中科技大學(xué);2009年

3 汪海洋;基于可見(jiàn)光航空遙感的水下目標(biāo)自動(dòng)識(shí)別技術(shù)研究[D];南京理工大學(xué);2008年

4 程朋根;地礦三維空間數(shù)據(jù)模型及相關(guān)算法研究[D];武漢大學(xué);2005年

相關(guān)碩士學(xué)位論文 前5條

1 艾倩;三維模型構(gòu)建與動(dòng)態(tài)目標(biāo)識(shí)別算法設(shè)計(jì)與實(shí)現(xiàn)[D];東北大學(xué);2011年

2 楊欣穎;潛器光視覺(jué)目標(biāo)識(shí)別技術(shù)的研究與設(shè)計(jì)[D];哈爾濱工程大學(xué);2010年

3 高苗;水聲圖像特征提取技術(shù)研究[D];哈爾濱工程大學(xué);2009年

4 李明;基于高分辨率遙感影像中艦艇目標(biāo)的分割與提取技術(shù)研究[D];東北師范大學(xué);2008年

5 滕永富;空間移動(dòng)對(duì)象的軌跡和查詢(xún)研究[D];哈爾濱理工大學(xué);2008年

，

本文編號(hào)：1992487