發(fā)布時(shí)間：2018-04-11 11:20

  本文選題：相關(guān)性濾波器 + 多尺度�。� 參考：《昆明理工大學(xué)》2017年碩士論文

【摘要】：運(yùn)動(dòng)目標(biāo)跟蹤是計(jì)算機(jī)視覺中的重要環(huán)節(jié),在軍用、公共安全和自動(dòng)駕駛等領(lǐng)域有著廣泛的運(yùn)用。檢測(cè)技術(shù)的發(fā)展早于跟蹤技術(shù),已經(jīng)有許多效果突出且理論基礎(chǔ)完善的算法。借助檢測(cè)技術(shù)的實(shí)時(shí)檢測(cè)跟蹤(Tracking by Detection)是近年突起的一類跟蹤方法,在每一幀檢測(cè)到目標(biāo)以實(shí)現(xiàn)連續(xù)視頻序列目標(biāo)的跟蹤,具有較好的跟蹤性能。其代表是Kernelized Correlation Filter算法,通過訓(xùn)練一個(gè)相關(guān)性濾波器進(jìn)行相關(guān)性濾波以實(shí)現(xiàn)檢測(cè)。本文的研究重點(diǎn)是相關(guān)性濾波器的多尺度跟蹤以及模板漂移時(shí)的持續(xù)跟蹤。提出一種多尺度的內(nèi)核化相關(guān)性濾波器ACF算法�，F(xiàn)有改進(jìn)方法多是基于MOSSE的多尺度改進(jìn)方法,本文將其擴(kuò)展至KCF,利用KCF循環(huán)結(jié)構(gòu)對(duì)角化的性質(zhì)進(jìn)行高效、高精度的位置濾波。再利用目標(biāo)尺度金字塔對(duì)目標(biāo)進(jìn)行多尺度表達(dá),利用卷積定理在傅里葉域中對(duì)目標(biāo)進(jìn)行尺度濾波,并根據(jù)上一幀檢測(cè)結(jié)果的尺度變化率,適時(shí)地調(diào)用尺度優(yōu)先策略或位置優(yōu)先策略,使得跟蹤器在權(quán)衡尺度變化與位移變化時(shí)更具魯棒性。對(duì)于模板漂移的持久跟蹤,提出一種持續(xù)目標(biāo)模板——CUR濾波器。CUR濾波器以矩陣降維技術(shù)為核心,使用CUR分解中構(gòu)建R矩陣的方法,從包含了所有成功檢測(cè)目標(biāo)信息的歷史矩陣Q中構(gòu)建CUR濾波器,最大程度地保留目標(biāo)的特征信息,實(shí)現(xiàn)目標(biāo)的持續(xù)性表達(dá)。當(dāng)跟蹤器跟蹤失敗時(shí),使用CUR濾波器作為下一幀檢測(cè)的目標(biāo)外觀模型,由于CUR具有目標(biāo)持續(xù)表達(dá)的特性,因此,能夠不受跟蹤失敗幀的影響,實(shí)現(xiàn)目標(biāo)的持續(xù)跟蹤。
[Abstract]:Moving target tracking is an important part of computer vision, which is widely used in military, public safety and autopilot fields.The development of detection technology is earlier than that of tracking technology, and there are many algorithms with outstanding effect and perfect theoretical foundation.Tracking by Detection with the help of detection technology is a kind of tracking method which has been raised in recent years. In order to realize the tracking of continuous video sequences, the target is detected in every frame, and it has good tracking performance.It is represented by Kernelized Correlation Filter algorithm, which can be detected by training a correlation filter for correlation filtering.The emphasis of this paper is the multi-scale tracking of correlation filter and the continuous tracking of template drift.A multi-scale kernel correlation filter (ACF) algorithm is proposed.Most of the existing improvement methods are based on MOSSE. In this paper, we extend them to KCFs and use the diagonalization property of KCF cyclic structure to carry out efficient and high-precision position filtering.Then the multi-scale representation of the target is performed by using the target scale pyramid, and the scale filtering is carried out in the Fourier domain by using convolution theorem, and the scale change rate of the detection result of the previous frame is calculated according to the scale change rate of the detection result.The scale-first strategy or location-first strategy is called in time, which makes the tracker more robust in balancing the scale change with the displacement change.For the persistent tracking of template drift, a method of constructing R-matrix by using CUR decomposition is proposed, which is based on matrix dimension reduction technology.The CUR filter is constructed from the history matrix Q which contains all the information of the successful target detection. The feature information of the target is preserved to the maximum extent and the persistent expression of the target is realized.When the tracker fails, the CUR filter is used as the target appearance model for the next frame detection. Because CUR has the feature of continuous expression of the target, it can realize the continuous tracking of the target without the influence of the tracking failed frame.
【學(xué)位授予單位】：昆明理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 曾巧玲;文貢堅(jiān);;運(yùn)動(dòng)目標(biāo)跟蹤綜述[J];重慶理工大學(xué)學(xué)報(bào)(自然科學(xué));2016年07期

2 劉威;趙文杰;李成;徐忠林;李婷;;粒子濾波理論框架及在目標(biāo)跟蹤中的應(yīng)用[J];自動(dòng)化與儀器儀表;2016年03期

3 王法勝;魯明羽;趙清杰;袁澤劍;;粒子濾波算法[J];計(jì)算機(jī)學(xué)報(bào);2014年08期

4 孔軍;湯心溢;蔣敏;葛運(yùn)建;;基于多尺度特征提取的均值漂移目標(biāo)跟蹤算法[J];計(jì)算機(jī)工程;2011年22期

5 孔軍;湯心溢;蔣敏;劉士建;李丹;;基于多尺度特征提取的Kalman濾波跟蹤[J];紅外與毫米波學(xué)報(bào);2011年05期

6 王建東;王亞飛;張晶;;基于卡爾曼濾波器的運(yùn)動(dòng)目標(biāo)跟蹤算法[J];數(shù)字通信;2009年06期

7 薛陳;朱明;劉春香;;遮擋情況下目標(biāo)跟蹤算法綜述[J];中國(guó)光學(xué)與應(yīng)用光學(xué);2009年05期

8 羅寰;于雷;廖俊;穆中林;;復(fù)雜背景下紅外弱小多目標(biāo)跟蹤系統(tǒng)[J];光學(xué)學(xué)報(bào);2009年06期

，

本文編號(hào)：1735806