本文關(guān)鍵詞： 壓縮感知 置信圖 超像素 目標(biāo)跟蹤　出處：《天津大學(xué)》2016年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：復(fù)雜場(chǎng)景下的目標(biāo)跟蹤是計(jì)算機(jī)視覺(jué)領(lǐng)域最熱點(diǎn)的課題之一。經(jīng)過(guò)幾十年的研究,目標(biāo)跟蹤技術(shù)有了長(zhǎng)足的發(fā)展,并在視頻監(jiān)控、智能交通、人機(jī)交互等民用和軍事領(lǐng)域上都有廣泛的應(yīng)用。但在實(shí)際應(yīng)用中,目標(biāo)跟蹤依然是很有挑戰(zhàn)的問(wèn)題,例如光照變化、目標(biāo)外觀變化,目標(biāo)被遮擋和復(fù)雜背景干擾等眾多因素。這些因素對(duì)目標(biāo)跟蹤算法的魯棒性和實(shí)時(shí)性提出很高的要求。當(dāng)前,基于壓縮感知理論的跟蹤算法通過(guò)應(yīng)用隨機(jī)測(cè)量矩陣去壓縮圖像信號(hào)來(lái)提取低維特征,極大地提高跟蹤算法的實(shí)時(shí)性且越來(lái)越引起人們注意。然而當(dāng)前景目標(biāo)和背景在形狀或者紋理相似時(shí),跟蹤結(jié)果可能并不準(zhǔn)確。針對(duì)此,本文提出基于超像素的壓縮感知跟蹤(Superpixel-based compressive tracking,SCT)算法,該算法根據(jù)新來(lái)的幀和目標(biāo)在超像素之間的相似性來(lái)構(gòu)建置信圖。超像素塊能把像素聚合成有意義原子區(qū)域,SCT算法吸收其優(yōu)點(diǎn)。置信圖提供很強(qiáng)的證據(jù)用來(lái)度量目標(biāo)出現(xiàn)的可能性,這能夠捕捉到在超像素級(jí)別目標(biāo)和背景局部外觀顏色的不同,同時(shí)改進(jìn)實(shí)時(shí)壓縮感知跟蹤(Fast compressive tracking,FCT)算法的粗粒度到細(xì)粒度搜索策略。綜上,本文提出基于超像素的壓縮感知跟蹤算法,該算法不僅考慮到目標(biāo)和背景在形狀或者紋理的不同,而且充分利用超像素級(jí)別判別性強(qiáng)的顏色描述子構(gòu)建的置信圖提供指導(dǎo)。在具挑戰(zhàn)性視頻序列上的實(shí)驗(yàn)結(jié)果表明就準(zhǔn)確性和魯棒性而言提出的算法優(yōu)于最新水平的算法。
[Abstract]:Target tracking in complex scenes is one of the hottest topics in the field of computer vision. After decades of research, target tracking technology has made great progress, and in video surveillance, intelligent transportation, It is widely used in civil and military fields, such as human-computer interaction. But in practical application, target tracking is still a challenging problem, such as illumination change, target appearance change, There are many factors, such as target occlusion and complex background interference. These factors require high robustness and real-time performance of target tracking algorithm. The tracking algorithm based on compressed sensing theory extracts low-dimensional features by using random measurement matrix to compress image signals. It greatly improves the real-time performance of the tracking algorithm and attracts more and more attention. However, when the foreground target and background are similar in shape or texture, the tracking results may not be accurate. In this paper, a super-pixel based compressive tracking algorithm is proposed. According to the similarity between the new frame and the target, the algorithm constructs the confidence chart. The superpixel block can aggregate the pixels into a meaningful atomic region and the SCT algorithm absorbs its advantages. The confidence chart provides a strong evidence for measurement. The possibility of a target, This can capture the difference in local appearance colors between targets and backgrounds at the super-pixel level, while improving the coarse-grained to fine-grained search strategy of the Fast compressive tracking algorithm for real-time compression awareness tracking. In this paper, a compression sensing tracking algorithm based on hyperpixel is proposed. This algorithm not only takes into account the difference of object and background in shape or texture. The experimental results on challenging video sequences show that the proposed algorithm is superior to the latest algorithm in terms of accuracy and robustness.
【學(xué)位授予單位】：天津大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類(lèi)號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前2條

1 周健;基于超像素的壓縮感知跟蹤[D];天津大學(xué);2016年

2 王君;近周期結(jié)構(gòu)性遮擋物檢測(cè)與去除[D];天津大學(xué);2016年

，

本文編號(hào)：1548173