【摘要】：目標(biāo)跟蹤在現(xiàn)代機(jī)器視覺(jué)起著重要作用。最近基于核相關(guān)濾波的跟蹤達(dá)到很好的效果,但仍有改進(jìn)的必要,本文對(duì)其進(jìn)行了全面分析,提出兩個(gè)改進(jìn)方案。為了解決遮擋引起的跟蹤丟失問(wèn)題,建立一個(gè)目標(biāo)檢測(cè)模塊。首先通過(guò)對(duì)當(dāng)前一些檢測(cè)算法的分析,確定檢測(cè)方案。通過(guò)提取目標(biāo)模板與當(dāng)前幀的SURF特征點(diǎn)進(jìn)行匹配,運(yùn)用改進(jìn)的RANSAC算法過(guò)濾匹配對(duì),計(jì)算變換矩陣,來(lái)定位當(dāng)前幀的目標(biāo)位置,以達(dá)到檢測(cè)目的。同時(shí)建立模板集合來(lái)增加魯棒性。建立了判斷機(jī)制,通過(guò)在當(dāng)前幀訓(xùn)練跟蹤器,進(jìn)行反向跟蹤,然后比較結(jié)果判斷是否啟動(dòng)檢測(cè),同時(shí)修改了模板更新方法。針對(duì)核濾波跟蹤無(wú)法適應(yīng)目標(biāo)尺度變化的問(wèn)題,通過(guò)引入目標(biāo)候選框算法來(lái)產(chǎn)生尺度不同的方框。通過(guò)結(jié)構(gòu)化隨機(jī)森林引出提取目標(biāo)候選框的edge box算法,同時(shí)修改了算法以適應(yīng)需要。用原算法進(jìn)行粗跟蹤,在結(jié)果位置處提取區(qū)域,在該區(qū)域運(yùn)行edge box以產(chǎn)生目標(biāo)候選方框,將一些評(píng)分高的方框提取出來(lái),結(jié)合原跟蹤框進(jìn)行篩選后,再變換回初始大小,然后代入KCF進(jìn)行評(píng)估,綜合原結(jié)果得出當(dāng)前幀最合適的跟蹤框。同時(shí)融合了多種特征以進(jìn)一步提高整體跟蹤效果。本文同時(shí)論述了跟蹤評(píng)估方式,評(píng)估兩種改進(jìn)方案時(shí)從OTB數(shù)據(jù)集中分別選取29個(gè)遮擋屬性的視頻與28個(gè)尺度屬性視頻,分別通過(guò)定性與定量實(shí)驗(yàn)與原算法以及Stuck與TLD進(jìn)行了對(duì)比。實(shí)驗(yàn)結(jié)果表明,本算法在成功率圖與精確度圖排名上均優(yōu)于原KCF,TLD,struck算法。與原方法相比,改進(jìn)后的方法能更好地適用于有尺度變化與遮擋的跟蹤,能夠廣泛應(yīng)用于目標(biāo)跟蹤領(lǐng)域。
[Abstract]:Target tracking plays an important role in modern machine vision. Recently, the tracking based on kernel correlation filter has achieved good results, but there is still a need for improvement. This paper makes a comprehensive analysis of it and puts forward two improved schemes. In order to solve the problem of tracking loss caused by occlusion, a target detection module is established. First of all, through the analysis of some current detection algorithms, the detection scheme is determined. By extracting the target template to match the SURF feature points of the current frame, the improved RANSAC algorithm is used to filter the matching pairs, and the transform matrix is calculated to locate the target position of the current frame so as to achieve the purpose of detection. At the same time, the template set is established to increase robustness. A judgment mechanism is established, and the method of template updating is modified by training the tracker in the current frame for reverse tracking, then comparing the results to judge whether the detection is initiated or not. In order to solve the problem that the kernel filter tracking can not adapt to the change of target scale, the target candidate algorithm is introduced to generate different scale boxes. The edge box algorithm for extracting target candidate is obtained by structured random forest, and the algorithm is modified to meet the needs. The original algorithm is used for rough tracking, the region is extracted at the result location, the edge box is run in this region to produce the target candidate box, and some highly graded boxes are extracted. After the original tracking box is filtered, the initial size is then transformed back to the initial size. Then the KCF is used to evaluate the current frame and the most suitable tracking box is obtained by synthesizing the original results. At the same time, a variety of features are fused to further improve the overall tracking effect. At the same time, this paper discusses the method of tracking and evaluation. When evaluating the two improved schemes, the video of 29 occlusion attributes and 28 scale attribute videos are selected from the OTB dataset, respectively. The qualitative and quantitative experiments are compared with the original algorithm, and the Stuck and TLD are compared. The experimental results show that the proposed algorithm is superior to the original KCFC TLDLD-struck algorithm in the ranking of the success rate diagram and the accuracy chart. Compared with the original method, the improved method is more suitable for tracking with scale variation and occlusion, and can be widely used in the field of target tracking.
【學(xué)位授予單位】：西南科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 馬進(jìn);田濤;;基于聯(lián)合變換相關(guān)的目標(biāo)跟蹤方法[J];應(yīng)用光學(xué);2012年05期

2 尤小泉;彭映杰;;一種基于指令預(yù)測(cè)的目標(biāo)跟蹤方法[J];電視技術(shù);2010年02期

3 邵文坤;黃愛民;韋慶;;目標(biāo)跟蹤方法綜述[J];影像技術(shù);2006年01期

4 梁德群;阮文;;基于模型的線性組合目標(biāo)跟蹤方法[J];模式識(shí)別與人工智能;1995年04期

5 王思，

本文編號(hào)：2195162