基于外觀特征和交互信息的多目標(biāo)跟蹤
發(fā)布時(shí)間：2019-03-12 16:02
【摘要】：現(xiàn)代社會(huì),無(wú)處不在的攝像設(shè)備等使得視頻數(shù)據(jù)急劇增加,依靠人工處理的方式已無(wú)法滿足實(shí)際需求。如何采用機(jī)器處理的方式,高效、準(zhǔn)確地從這些視頻數(shù)據(jù)中獲取需要的信息已成為計(jì)算機(jī)視覺(jué)領(lǐng)域重要的研究任務(wù)。而目標(biāo)跟蹤,尤其是多目標(biāo)跟蹤已成為這些任務(wù)中重要且基礎(chǔ)的一個(gè)研究方向。在公共安全、智能交通等視頻數(shù)據(jù)的處理時(shí),都需要先獲取監(jiān)測(cè)到的各個(gè)目標(biāo)的運(yùn)行軌跡,再判斷是否有公共事件的發(fā)生或判斷交通違章情況。此外,在人機(jī)交互,自動(dòng)駕駛等場(chǎng)景下,目標(biāo)跟蹤也有廣泛的應(yīng)用。在對(duì)多個(gè)目標(biāo)進(jìn)行跟蹤的時(shí)候,需要面對(duì)各種復(fù)雜的情況,比如需要在目標(biāo)被遮擋、軌跡交叉、光照變化等情況下將不同的目標(biāo)分辨開(kāi)來(lái),持續(xù)跟蹤下去�，F(xiàn)在最常用的多目標(biāo)跟蹤的方法是先檢測(cè)后跟蹤的方法。先采用檢測(cè)算法對(duì)圖像區(qū)域進(jìn)行檢測(cè)獲取檢測(cè)結(jié)果,再利用跟蹤算法對(duì)目標(biāo)進(jìn)行持續(xù)的跟蹤,將檢測(cè)結(jié)果關(guān)聯(lián)成不同目標(biāo)的軌跡。在對(duì)目標(biāo)進(jìn)行跟蹤的時(shí)候,需要利用目標(biāo)的視覺(jué)信息,即目標(biāo)的各種特征。對(duì)這些特征的要求首先是具有良好的分辨能力,能夠很好的將屬于不同目標(biāo)的檢測(cè)結(jié)果分辨開(kāi);同時(shí)還要求其具有連續(xù)性,即在不同幀的屬于同一個(gè)目標(biāo)的檢測(cè)結(jié)果的特征要盡可能的相似。而現(xiàn)有的單一特征或單一種類特征的跟蹤方法很難同時(shí)滿足上述兩點(diǎn)要求。在目標(biāo)跟蹤過(guò)程中也經(jīng)常出現(xiàn)跟蹤的目標(biāo)被遮擋等情況,使目標(biāo)的視覺(jué)特征無(wú)法獲取,或目標(biāo)外觀發(fā)生變化等使單純依賴視覺(jué)特征的跟蹤無(wú)法繼續(xù)。而在跟蹤目標(biāo)為人的時(shí)候,例如行人跟蹤,多個(gè)目標(biāo)之間的運(yùn)動(dòng)模式是相互影響的,周圍目標(biāo)的運(yùn)動(dòng)模式有助于對(duì)當(dāng)前目標(biāo)的跟蹤,即目標(biāo)的交互信息可以提高跟蹤的性能。針對(duì)以上分析,本文的主要研究?jī)?nèi)容和創(chuàng)新點(diǎn)主要有以下兩點(diǎn):1.提出了一種基于全局和局部特征的實(shí)時(shí)多目標(biāo)跟蹤的方法。該方法是一種分兩步的,分別利用了全局特征和局部特征的同時(shí)對(duì)多個(gè)目標(biāo)進(jìn)行跟蹤的方法。全局跟蹤階段采用全局特征,即廣泛應(yīng)用的顏色直方圖以滿足對(duì)目標(biāo)特征連續(xù)性的要求;局部跟蹤階段采用了一種改進(jìn)的基于最大穩(wěn)定極值區(qū)域的局部特征,滿足對(duì)目標(biāo)特征分辨能力的要求。這樣便同時(shí)滿足跟蹤中對(duì)分辨能力和連續(xù)性的要求,且擁有比較低的計(jì)算復(fù)雜度,可以應(yīng)用于實(shí)時(shí)跟蹤。2.提出了一種基于隊(duì)列穩(wěn)定性的多目標(biāo)跟蹤方法。在F-Formation的基礎(chǔ)上提出了隊(duì)列穩(wěn)定性的概念并將隊(duì)列穩(wěn)定性用于提高半擁擠環(huán)境下多目標(biāo)跟蹤的性能,且將其嵌入傳統(tǒng)跟蹤框架中。在跟蹤的過(guò)程中,在利用傳統(tǒng)的視覺(jué)信息等之外,還需要保持兩段軌跡片段在關(guān)聯(lián)前后整個(gè)隊(duì)列的穩(wěn)定性,使其不發(fā)生大的變化,提高了跟蹤的性能。
[Abstract]:The modern society, the ubiquitous imaging equipment and so on make the video data increase dramatically, and the actual demand cannot be met by means of manual processing. How to adopt a machine-based approach to efficiently and accurately obtain the required information from these video data has become an important research task in the field of computer vision. Target tracking, especially multi-target tracking, has become an important and fundamental research direction in these tasks. In the process of processing video data such as public safety and intelligent traffic, it is necessary to first obtain the running track of each target monitored, and then judge whether there is a public event or judge the traffic violation condition. In addition, under the scene of man-machine interaction and automatic driving, the target tracking has a wide application. When tracking a plurality of targets, it is necessary to face a variety of complex situations, such as the need to distinguish different targets in the case of a target being blocked, a track crossing, a light change, and the like, and continue to follow. The most commonly used method of multi-target tracking is to detect post-tracking methods first. Firstly, a detection algorithm is adopted to detect the image area to obtain a detection result, and the target is continuously tracked by a tracking algorithm, and the detection result is correlated to a track of different targets. When tracking a target, it is necessary to take advantage of the visual information of the target, that is, the various features of the object. The requirements for these features are first to have good resolving power and to distinguish the detection results belonging to different targets well, and to have continuity, that is, the characteristics of the detection results belonging to the same object in different frames are to be as similar as possible. And the existing single-feature or single-type feature tracking method is difficult to meet the two-point requirements simultaneously. In the target tracking process, the target of the tracking is blocked and the like, so that the visual characteristics of the target can not be acquired, or the appearance of the target changes and the like, so that the tracking of the pure-dependent visual features can not be continued. While tracking the target as a person, such as pedestrian tracking, the motion pattern between the plurality of targets is interactive, and the motion pattern of the surrounding target contributes to the tracking of the current target, that is, the interaction information of the target can improve the performance of the tracking. For the above analysis, the main research content and innovation point of this paper have the following two points:1. A method for real-time multi-target tracking based on global and local features is presented. The method is a two-step method for tracking a plurality of targets at the same time using global features and local features, respectively. The global tracking stage adopts the global feature, that is, the widely used color histogram is used to meet the requirement of the continuity of the target feature; the local tracking stage adopts an improved local feature based on the maximum stable extreme value region, and meets the requirement of the target feature resolution capability. In that way, the requirements for resolution and continuity in the tracking are met at the same time, and the computational complexity of the tracking is relatively low, and the method can be applied to real-time tracking. A multi-target tracking method based on queue stability is proposed. On the basis of F-Formation, the concept of queue stability is proposed and the stability of the queue is used to improve the performance of multi-target tracking in a semi-crowded environment, and it is embedded in the traditional tracking framework. In the process of tracking, in addition to the traditional visual information and the like, the stability of the whole queue before and after the association is required to be maintained, so that the stability of the whole queue before and after the association is not changed, and the tracking performance is improved.
【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)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
本文編號(hào)：2438929
[Abstract]:The modern society, the ubiquitous imaging equipment and so on make the video data increase dramatically, and the actual demand cannot be met by means of manual processing. How to adopt a machine-based approach to efficiently and accurately obtain the required information from these video data has become an important research task in the field of computer vision. Target tracking, especially multi-target tracking, has become an important and fundamental research direction in these tasks. In the process of processing video data such as public safety and intelligent traffic, it is necessary to first obtain the running track of each target monitored, and then judge whether there is a public event or judge the traffic violation condition. In addition, under the scene of man-machine interaction and automatic driving, the target tracking has a wide application. When tracking a plurality of targets, it is necessary to face a variety of complex situations, such as the need to distinguish different targets in the case of a target being blocked, a track crossing, a light change, and the like, and continue to follow. The most commonly used method of multi-target tracking is to detect post-tracking methods first. Firstly, a detection algorithm is adopted to detect the image area to obtain a detection result, and the target is continuously tracked by a tracking algorithm, and the detection result is correlated to a track of different targets. When tracking a target, it is necessary to take advantage of the visual information of the target, that is, the various features of the object. The requirements for these features are first to have good resolving power and to distinguish the detection results belonging to different targets well, and to have continuity, that is, the characteristics of the detection results belonging to the same object in different frames are to be as similar as possible. And the existing single-feature or single-type feature tracking method is difficult to meet the two-point requirements simultaneously. In the target tracking process, the target of the tracking is blocked and the like, so that the visual characteristics of the target can not be acquired, or the appearance of the target changes and the like, so that the tracking of the pure-dependent visual features can not be continued. While tracking the target as a person, such as pedestrian tracking, the motion pattern between the plurality of targets is interactive, and the motion pattern of the surrounding target contributes to the tracking of the current target, that is, the interaction information of the target can improve the performance of the tracking. For the above analysis, the main research content and innovation point of this paper have the following two points:1. A method for real-time multi-target tracking based on global and local features is presented. The method is a two-step method for tracking a plurality of targets at the same time using global features and local features, respectively. The global tracking stage adopts the global feature, that is, the widely used color histogram is used to meet the requirement of the continuity of the target feature; the local tracking stage adopts an improved local feature based on the maximum stable extreme value region, and meets the requirement of the target feature resolution capability. In that way, the requirements for resolution and continuity in the tracking are met at the same time, and the computational complexity of the tracking is relatively low, and the method can be applied to real-time tracking. A multi-target tracking method based on queue stability is proposed. On the basis of F-Formation, the concept of queue stability is proposed and the stability of the queue is used to improve the performance of multi-target tracking in a semi-crowded environment, and it is embedded in the traditional tracking framework. In the process of tracking, in addition to the traditional visual information and the like, the stability of the whole queue before and after the association is required to be maintained, so that the stability of the whole queue before and after the association is not changed, and the tracking performance is improved.
【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)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)碩士學(xué)位論文 前2條
1 劉文;基于塊的多特征目標(biāo)跟蹤算法[D];大連理工大學(xué);2010年
2 柳濤;多通道圖像MSER局部不變特征提取算法研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2010年
，本文編號(hào)：2438929
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2438929.html
最近更新
教材專著
