本文選題：HOG　切入點(diǎn)：降噪　出處：《大連海事大學(xué)》2017年碩士論文

【摘要】：在水路交通中,航行船舶類型日益多樣化,船舶航行軌跡日益復(fù)雜化。監(jiān)控船舶活動(dòng)需要對船舶目標(biāo)做到實(shí)時(shí)的跟蹤,還要能夠識別船舶目標(biāo),而傳統(tǒng)的船舶視頻目標(biāo)跟蹤方法存在跟蹤計(jì)算時(shí)耗大、跟蹤準(zhǔn)確率有限、缺少識別能力等缺陷,這對于有效及時(shí)的指揮調(diào)度船舶帶來了困難。因此有必要設(shè)計(jì)一種實(shí)時(shí)、誤差率小、具有識別能力的船舶目標(biāo)跟蹤算法。本文的研究包括目標(biāo)的特征提取、分類識別、跟蹤三個(gè)方面。在目標(biāo)特征提取方面,通過對各種圖像特征的優(yōu)缺點(diǎn)對比,本論文選定提取船舶目標(biāo)的HOG特征以減少水域環(huán)境中其他干擾背景對船舶識別的影響。在目標(biāo)分類識別方面,SVM模型對目標(biāo)的原始HOG特征有一定的分類識別能力,但并不是所有的目標(biāo)HOG特征位包含的都為有效特征,其中摻雜了噪聲存在著冗余,并且模型復(fù)雜過高,因此本論文引進(jìn)序列前向選取法對原始的船舶目標(biāo)HOG特征進(jìn)行了降噪和特征再選取。但是由于在處理訓(xùn)練樣本數(shù)據(jù)集的時(shí)候采取的是交叉驗(yàn)證方法,并且序列前向選取法存在只能加入不能去除特征的缺陷,因此由其選取的最優(yōu)特征具有不確定性并且關(guān)聯(lián)性強(qiáng)。針對上述缺陷,在序列前向選取法的基礎(chǔ)上,本文提出了一種特征位得分系統(tǒng)從而挑選出了船舶HOG特征中的最優(yōu)特征位。在目標(biāo)跟蹤方面,本論文引進(jìn)STC算法來對船舶目標(biāo)進(jìn)行定位。雖然STC跟蹤算法計(jì)算速度快并且跟蹤準(zhǔn)確率高,但是當(dāng)目標(biāo)被遮擋時(shí),會發(fā)生跟蹤目標(biāo)跳變的情況。本論文通過模板匹配算法對跟蹤目標(biāo)進(jìn)行檢測,改善了 STC的這一缺陷,從而提升了其跟蹤性能。實(shí)驗(yàn)證實(shí),本文船舶識別與跟蹤算法能夠?qū)崟r(shí)、穩(wěn)定且準(zhǔn)確地識別跟蹤船舶目標(biāo)。
[Abstract]:In waterway traffic, the types of navigation ships are becoming more and more diversified, and the ship trajectory is becoming more and more complicated. Monitoring ship activities requires real-time tracking of ship targets and the ability to identify ship targets. However, the traditional ship video target tracking method has many disadvantages, such as large amount of tracking calculation, limited tracking accuracy, lack of recognition ability and so on, which brings difficulties to the effective and timely command and dispatch of ships, so it is necessary to design a real-time system. The research of this paper includes three aspects: target feature extraction, classification recognition and tracking. In the aspect of target feature extraction, the advantages and disadvantages of various image features are compared. In this paper, the HOG features of ship targets are selected to reduce the influence of other interference background on ship recognition. In the aspect of target classification and recognition, the HOG model has a certain ability to classify and recognize the original HOG features of the target. However, not all the target HOG feature bits contain valid features, in which the doped noise is redundant and the model is too complex. So this paper introduces the method of forward selection of sequence to reduce the noise and re-select the features of the original ship target HOG. However, the cross-validation method is adopted in the processing of the training sample data set. And the method of sequence forward selection can only add the defect that can not be removed, so the optimal feature selected by it has uncertainty and strong correlation. In view of the above defects, based on the method of sequence forward selection, In this paper, a feature bit scoring system is proposed to select the optimal feature bits in ship HOG features. In this paper, STC algorithm is introduced to locate the ship target. Although the STC tracking algorithm is fast and accurate, but when the target is occluded, In this paper, the template matching algorithm is used to detect the tracking target, which improves the performance of STC and improves the tracking performance. The experiments show that the algorithm of ship identification and tracking can be used in real time. Identify and track ship targets stably and accurately.
【學(xué)位授予單位】：大連海事大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 李暢;魏東;;一個(gè)基于像素編組和逐級質(zhì)量控制的線段檢測算子[J];紅外與毫米波學(xué)報(bào);2016年06期

2 冉歡歡;黃自力;;融合攝像機(jī)位姿信息的模板匹配跟蹤算法[J];計(jì)算機(jī)應(yīng)用;2013年01期

相關(guān)博士學(xué)位論文 前3條

1 王保憲;復(fù)雜背景下的視頻目標(biāo)跟蹤算法研究[D];北京理工大學(xué);2016年

2 王愛平;視頻目標(biāo)跟蹤技術(shù)研究[D];國防科學(xué)技術(shù)大學(xué);2011年

3 曹輝;船舶監(jiān)控中的視頻穩(wěn)像與目標(biāo)跟蹤的研究[D];大連海事大學(xué);2008年

相關(guān)碩士學(xué)位論文 前2條

1 白雪里;基于多尺度多特征模板集和自適應(yīng)動(dòng)態(tài)模型的物體跟蹤算法[D];上海交通大學(xué);2015年

2 姜百寧;機(jī)器學(xué)習(xí)中的特征選擇算法研究[D];中國海洋大學(xué);2009年

，

本文編號：1684775