基于改進(jìn)粒子濾波的目標(biāo)跟蹤方法研究
發(fā)布時間：2018-07-14 11:58
【摘要】：運(yùn)動目標(biāo)跟蹤是計算機(jī)視覺領(lǐng)域中的一個十分重要的研究方向,隨著對運(yùn)動目標(biāo)跟蹤技術(shù)的研究工作得到廣泛開展,運(yùn)動目標(biāo)跟蹤技術(shù)得到了快速發(fā)展。與此同時,人們對于運(yùn)動目標(biāo)跟蹤技術(shù)的要求也是與日俱增,如何對各種復(fù)雜場景中的運(yùn)動目標(biāo)進(jìn)行準(zhǔn)確和穩(wěn)定的跟蹤一直是運(yùn)動目標(biāo)跟蹤領(lǐng)域的難點。本課題的研究工作主要包括以下幾個方面:1、針對多區(qū)域采樣目標(biāo)跟蹤方法容易出現(xiàn)的區(qū)域多樣性喪失、跟蹤精度下降和跟蹤不穩(wěn)定等問題,通過引入?yún)^(qū)域優(yōu)化權(quán)值及改進(jìn)子區(qū)域重采樣方法,給出基于優(yōu)化權(quán)值的多區(qū)域采樣目標(biāo)跟蹤算法。該方法利用區(qū)域優(yōu)化權(quán)值優(yōu)化各個子區(qū)域的區(qū)域置信度適當(dāng)增加低置信度區(qū)域在重采樣階段所分配到的粒子數(shù)量,在保證粒子根據(jù)區(qū)域置信度大小有效分配的前提下,抑制了區(qū)域多樣性喪失現(xiàn)象發(fā)生。該方法在子區(qū)域內(nèi)引入粒子權(quán)重優(yōu)化權(quán)值并設(shè)定重采樣閾值,緩解粒子貧化充分利用有效粒子信息。實驗結(jié)果表明,該方法能有效提高目標(biāo)跟蹤精度,改善目標(biāo)跟蹤穩(wěn)定性。2、針對傳統(tǒng)粒子濾波算法粒子重采樣產(chǎn)生的粒子貧化現(xiàn)象及單一特征目標(biāo)跟蹤算法魯棒性較差的問題,給出一種基于信息保留的自適應(yīng)多特征融合目標(biāo)跟蹤算法。該算法的信息保留策略在粒子重采樣階段通過優(yōu)化粒子權(quán)重值分布來適當(dāng)提高小權(quán)重粒子的權(quán)重并改進(jìn)了粒子重采樣方法,有效抑制了粒子貧化現(xiàn)象,保留更多粒子信息。根據(jù)環(huán)境變化對特征有效性的影響及不同特征對目標(biāo)的貢獻(xiàn)度,自適應(yīng)調(diào)節(jié)多特征模型中各特征分量的權(quán)重。實驗結(jié)果表明,該算法能有效應(yīng)對目標(biāo)形變、目標(biāo)部分遮擋、背景相似物體干擾等復(fù)雜情況,具有良好的跟蹤精度和魯棒性。3、針對運(yùn)動目標(biāo)跟蹤過程中容易受到復(fù)雜環(huán)境及目標(biāo)遮擋影響的問題,給出一種結(jié)合全局特征融合和局部均值漂移的目標(biāo)跟蹤算法。該算法將目標(biāo)區(qū)域劃分為多個子區(qū)域,將粒子濾波方法和均值漂移方法分別應(yīng)用于目標(biāo)的全局區(qū)域和局部子區(qū)域的跟蹤中。采用改進(jìn)的粒子濾波方法并融合顏色和FDF特征進(jìn)行目標(biāo)全局區(qū)域跟蹤,利用均值漂移算法并融合顏色和紋理特征進(jìn)行目標(biāo)子區(qū)域跟蹤。該算法通過目標(biāo)受到遮擋程度來自適應(yīng)調(diào)節(jié)全局信息和局部信息在目標(biāo)跟蹤中的貢獻(xiàn),提高了目標(biāo)跟蹤算法應(yīng)對遮擋場景的適應(yīng)性,融合多特征改善了目標(biāo)跟蹤算法對復(fù)雜跟蹤場景的魯棒性。實驗結(jié)果表明,該算法能有效應(yīng)對目標(biāo)形變、目標(biāo)遮擋和復(fù)雜背景干擾等影響,具有良好的跟蹤穩(wěn)定性和精確度。
[Abstract]:Moving target tracking is a very important research direction in the field of computer vision. With the development of moving target tracking technology, moving target tracking technology has been developed rapidly. At the same time, the requirement of moving target tracking technology is increasing day by day. How to track moving targets accurately and stably in various complex scenes is always a difficult point in the field of moving target tracking. The research work of this subject mainly includes the following several aspects: 1, aiming at the problems such as the loss of regional diversity, the decline of tracking accuracy and the instability of tracking, which are easy to appear in the multi-region sampling target tracking method. By introducing regional optimization weights and improved subregion resampling method, a multi-region sampling target tracking algorithm based on optimal weights is presented. In this method, the regional confidence of each sub-region is optimized by using the regional optimization weights to increase the number of particles assigned to the low-confidence region in the resampling stage, while ensuring the effective distribution of the particles according to the confidence level of the region. The loss of regional diversity was restrained. In this method, the particle weight optimization value is introduced into the sub-region and the resampling threshold is set so as to reduce particle dilution and make full use of the effective particle information. The experimental results show that the proposed method can effectively improve the tracking accuracy and the stability of target tracking. Aiming at the problem of particle dilution caused by particle resampling in traditional particle filter algorithm and the poor robustness of single feature target tracking algorithm, the proposed method can effectively improve the tracking accuracy. An adaptive multi-feature fusion target tracking algorithm based on information reservation is presented. In the phase of particle resampling, the information retention strategy of the algorithm can appropriately increase the weight of small weight particles and improve the method of particle resampling by optimizing the distribution of particle weight values, which can effectively suppress the phenomenon of particle dilution and retain more particle information. According to the effect of environmental change on feature validity and the contribution of different features to the target, the weight of each feature component in the multi-feature model is adjusted adaptively. The experimental results show that the algorithm can effectively deal with complex situations such as target deformation, partial occlusion of the target, background similar object interference and so on. It has good tracking accuracy and robustness. Aiming at the problem that moving target tracking is easily affected by complex environment and target occlusion, a target tracking algorithm combining global feature fusion and local mean shift is proposed. The algorithm divides the target region into several subregions and applies the particle filter method and the mean shift method to the tracking of the global region and the local subregion of the target, respectively. The improved particle filter method is used to track the target global region by combining color and FDF features, and the mean shift algorithm is used to track the target subregion with the fusion of color and texture features. The algorithm adaptively adjusts the contribution of global and local information in target tracking by the degree of occlusion, and improves the adaptability of the target tracking algorithm to the occlusion scene. Fusion of multiple features improves the robustness of the target tracking algorithm to complex tracking scenarios. Experimental results show that the algorithm can effectively deal with the effects of target deformation, target occlusion and complex background interference, and has good tracking stability and accuracy.
【學(xué)位授予單位】：江南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41
本文編號：2121574
[Abstract]:Moving target tracking is a very important research direction in the field of computer vision. With the development of moving target tracking technology, moving target tracking technology has been developed rapidly. At the same time, the requirement of moving target tracking technology is increasing day by day. How to track moving targets accurately and stably in various complex scenes is always a difficult point in the field of moving target tracking. The research work of this subject mainly includes the following several aspects: 1, aiming at the problems such as the loss of regional diversity, the decline of tracking accuracy and the instability of tracking, which are easy to appear in the multi-region sampling target tracking method. By introducing regional optimization weights and improved subregion resampling method, a multi-region sampling target tracking algorithm based on optimal weights is presented. In this method, the regional confidence of each sub-region is optimized by using the regional optimization weights to increase the number of particles assigned to the low-confidence region in the resampling stage, while ensuring the effective distribution of the particles according to the confidence level of the region. The loss of regional diversity was restrained. In this method, the particle weight optimization value is introduced into the sub-region and the resampling threshold is set so as to reduce particle dilution and make full use of the effective particle information. The experimental results show that the proposed method can effectively improve the tracking accuracy and the stability of target tracking. Aiming at the problem of particle dilution caused by particle resampling in traditional particle filter algorithm and the poor robustness of single feature target tracking algorithm, the proposed method can effectively improve the tracking accuracy. An adaptive multi-feature fusion target tracking algorithm based on information reservation is presented. In the phase of particle resampling, the information retention strategy of the algorithm can appropriately increase the weight of small weight particles and improve the method of particle resampling by optimizing the distribution of particle weight values, which can effectively suppress the phenomenon of particle dilution and retain more particle information. According to the effect of environmental change on feature validity and the contribution of different features to the target, the weight of each feature component in the multi-feature model is adjusted adaptively. The experimental results show that the algorithm can effectively deal with complex situations such as target deformation, partial occlusion of the target, background similar object interference and so on. It has good tracking accuracy and robustness. Aiming at the problem that moving target tracking is easily affected by complex environment and target occlusion, a target tracking algorithm combining global feature fusion and local mean shift is proposed. The algorithm divides the target region into several subregions and applies the particle filter method and the mean shift method to the tracking of the global region and the local subregion of the target, respectively. The improved particle filter method is used to track the target global region by combining color and FDF features, and the mean shift algorithm is used to track the target subregion with the fusion of color and texture features. The algorithm adaptively adjusts the contribution of global and local information in target tracking by the degree of occlusion, and improves the adaptability of the target tracking algorithm to the occlusion scene. Fusion of multiple features improves the robustness of the target tracking algorithm to complex tracking scenarios. Experimental results show that the algorithm can effectively deal with the effects of target deformation, target occlusion and complex background interference, and has good tracking stability and accuracy.
【學(xué)位授予單位】：江南大學(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10條
1 夏瑜;吳小俊;李菊;周立凡;;基于多特征自適應(yīng)融合的分類采樣跟蹤算法[J];光電子·激光;2016年03期
2 Minggang Gan;Yulong Cheng;Yanan Wang;Jie Chen;;Hierarchical particle filter tracking algorithm based on multi-feature fusion[J];Journal of Systems Engineering and Electronics;2016年01期
3 種衍文;王澤文;陳蓉;王瑩瑩;;一種多特征自適應(yīng)融合的粒子濾波紅外目標(biāo)跟蹤方法[J];武漢大學(xué)學(xué)報(信息科學(xué)版);2016年05期
4 夏瑜;吳小俊;;多區(qū)域采樣目標(biāo)跟蹤算法[J];光電工程;2014年11期
5 張彥超;許宏麗;;遮擋目標(biāo)的分片跟蹤處理[J];中國圖象圖形學(xué)報;2014年01期
6 李遠(yuǎn)征;盧朝陽;李靜;;一種基于多特征融合的視頻目標(biāo)跟蹤方法[J];西安電子科技大學(xué)學(xué)報;2012年04期
7 劉晴;唐林波;趙保軍;劉嘉駿;翟威龍;;基于自適應(yīng)多特征融合的均值遷移紅外目標(biāo)跟蹤[J];電子與信息學(xué)報;2012年05期
8 左軍毅;張怡哲;梁彥;;自適應(yīng)不完全重采樣粒子濾波器[J];自動化學(xué)報;2012年04期
9 宋丹;趙保軍;唐林波;;融合角點特征與顏色特征的Mean-Shift目標(biāo)跟蹤算法[J];系統(tǒng)工程與電子技術(shù);2012年01期
10 相入喜;李見為;;多特征自適應(yīng)融合的粒子濾波跟蹤算法[J];計算機(jī)輔助設(shè)計與圖形學(xué)學(xué)報;2012年01期
相關(guān)博士學(xué)位論文 前3條
1 夏瑜;視覺跟蹤新方法及其應(yīng)用研究[D];江南大學(xué);2013年
2 徐偉杰;基于視覺的微小型無人直升機(jī)位姿估計與目標(biāo)跟蹤研究[D];浙江大學(xué);2012年
3 李榮華;面向機(jī)器人跟蹤的視覺注意模型與應(yīng)用研究[D];大連理工大學(xué);2011年
，本文編號：2121574
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2121574.html
最近更新
教材專著
