發(fā)布時(shí)間：2018-04-12 16:35

  本文選題：相關(guān)性濾波 + 接力跟蹤　； 參考：《華中科技大學(xué)》2016年碩士論文

【摘要】：視覺目標(biāo)跟蹤是計(jì)算機(jī)視覺領(lǐng)域的重要課題。為處理復(fù)雜跟蹤場(chǎng)景,越來(lái)越多跟蹤算法將跟蹤與檢測(cè)相結(jié)合。其中比較突出的是判別式相關(guān)性濾波(Discriminant Correlation Filter,DCF)跟蹤算法。但此類跟蹤算法大多以全局特征構(gòu)建目標(biāo)表觀模型,忽略尺度變化,并使用單一的跟蹤器對(duì)目標(biāo)表觀更新。在面對(duì)遮擋和較嚴(yán)重形變等跟蹤場(chǎng)景時(shí),算法的魯棒性大大降低。針對(duì)全局特征KCF算法在目標(biāo)尺度變化或遮擋時(shí)性能下降問題,提出基于顯著性檢測(cè)分塊的多尺度多線索KCF跟蹤方法(Salient Patch-based visual Tracking with Multi-cues Integration,SPMCI)。分析了低層、中層和高層結(jié)構(gòu)對(duì)目標(biāo)表觀的影響,采用中層目標(biāo)塊構(gòu)建表觀模型。常用均勻分塊方法會(huì)產(chǎn)生過多目標(biāo)塊,引入不必要背景干擾,同時(shí)增大計(jì)算量。為此使用目標(biāo)顯著圖作為分塊的先驗(yàn)信息,控制目標(biāo)塊(patch)的分布和數(shù)目。進(jìn)而結(jié)合塊的圖像金字塔對(duì)目標(biāo)尺度估計(jì)。為進(jìn)一步提高跟蹤算法準(zhǔn)確性,融合目標(biāo)塊表觀、空間分布和運(yùn)動(dòng)軌跡線索進(jìn)行目標(biāo)定位。實(shí)驗(yàn)表明SPMCI算法有效提高了跟蹤的準(zhǔn)確性和對(duì)不同場(chǎng)景的適應(yīng)能力。如何處理目標(biāo)長(zhǎng)時(shí)遮擋帶來(lái)的表觀污染和較大形變是跟蹤算法的一大難點(diǎn)。以SPMCI算法為基礎(chǔ),提出了基于表觀變化檢測(cè)的多跟蹤器接力跟蹤算法(Apparent Change Detection based Visual Tracking with Multi-trackers Relay,MTR)。MTR使用顏色直方圖匹配進(jìn)行表觀變化檢測(cè),采用PSR(Peak to Sidelobe Ratio)指標(biāo)對(duì)目標(biāo)形變和遮擋進(jìn)行區(qū)分。根據(jù)表觀變化更新模板或?qū)Ω櫰鬟M(jìn)行替換與選擇。通過不同跟蹤器接力跟蹤,應(yīng)對(duì)目標(biāo)較大形變和長(zhǎng)時(shí)全遮擋等惡劣場(chǎng)景。實(shí)驗(yàn)表明MTR算法提高了對(duì)長(zhǎng)時(shí)遮擋和較大形變場(chǎng)景的適應(yīng)能力。
[Abstract]:Visual target tracking is an important subject in the field of computer vision.In order to deal with complex tracking scenarios, more and more tracking algorithms combine tracking with detection.The discriminant Correlation filter tracking algorithm is prominent.However, most of these tracking algorithms are based on global features to construct the target visual model, ignore the scale changes, and use a single tracer to update the target view.The robustness of the algorithm is greatly reduced when tracking scenes such as occlusion and severe deformation are faced with.Aiming at the performance degradation of global feature KCF algorithm when the target scale changes or shading, a multi-scale and multi-clue KCF tracking method based on salience detection block is proposed.The influence of low level, middle layer and high level structure on the target's appearance is analyzed, and the surface model is constructed by using the middle level target block.The common uniform partitioning method will produce too many target blocks, introduce unnecessary background interference, and increase the computational complexity at the same time.In order to control the distribution and number of target patchs, the target saliency map is used as a priori information.Then the image pyramid of the block is used to estimate the target scale.In order to further improve the accuracy of the tracking algorithm, target location is carried out by fusion of target block representation, spatial distribution and motion trajectory clues.Experiments show that the SPMCI algorithm can effectively improve the accuracy of tracking and adaptability to different scenes.How to deal with the apparent pollution and large deformation caused by long time occlusion is one of the most difficult problems in tracking algorithm.Based on the SPMCI algorithm, a new relay tracking algorithm named Apparent Change Detection based Visual Tracking with Multi-trackers Relayn MTRN based on apparent change detection is proposed to detect the apparent change using color histogram matching.The target deformation and occlusion are distinguished by PSR(Peak to Sidelobe Ratio.Update templates based on apparent changes or replace and select trackers.Through the relay tracking of different tracker, it can deal with the bad scene such as large deformation of target and long time complete occlusion.Experiments show that the MTR algorithm improves the adaptability to long time occlusion and large deformation scenes.
【學(xué)位授予單位】：華中科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 余禮楊;范春曉;明悅;;改進(jìn)的核相關(guān)濾波器目標(biāo)跟蹤算法[J];計(jì)算機(jī)應(yīng)用;2015年12期

，

本文編號(hào)：1740549