在計(jì)算機(jī)視覺領(lǐng)域,多目標(biāo)跟蹤（MOT）一直是困難且具有挑戰(zhàn)性的研究。在該領(lǐng)域中,計(jì)算數(shù)據(jù)量很大,并且算法的處理速度要求很高,因此跟蹤速度、效率和精度常常難以很好地平衡。由于這個(gè)原因,將單目標(biāo)跟蹤中使用的具有通道和空間可靠性的判別相關(guān)濾波器（DCF-CSR）用于MOT,以在保持跟蹤速度的同時(shí)確保跟蹤效果。本文分為以下四個(gè)部分:（1）目標(biāo)檢測(cè)。由于2D MOT 2015和MOT16數(shù)據(jù)集目標(biāo)的檢測(cè)存在錯(cuò)漏,提出將基于更快區(qū)域的卷積神經(jīng)網(wǎng)絡(luò)（Faster R-CNN）用于目標(biāo)檢測(cè),并且將數(shù)據(jù)集提供的結(jié)果替換為網(wǎng)絡(luò)檢測(cè)的結(jié)果。（2）目標(biāo)跟蹤。為了在MOT中添加目標(biāo)外觀數(shù)據(jù),并結(jié)合速度和準(zhǔn)確性因素,本文使用DCF模型。但是,已經(jīng)發(fā)現(xiàn)執(zhí)行多目標(biāo)跟蹤數(shù)據(jù)集時(shí)跟蹤結(jié)果并不理想,因?yàn)镈CF算法不支持多尺度。為克服此困難,本文解決了計(jì)算檢測(cè)目標(biāo)框和預(yù)測(cè)目標(biāo)框之間的交并比（IOU）并使用檢測(cè)目標(biāo)框代替預(yù)測(cè)的方法。₃數(shù)據(jù)關(guān)聯(lián)。對(duì)于第（2）部分的IOU的計(jì)算,這是一批檢測(cè)框和一組預(yù)測(cè)框之間的相互計(jì)算問題,本質(zhì)上是任務(wù)分配和優(yōu)化問題。為此,匈牙利算法被用于確定目標(biāo)之間的最佳相關(guān)性。（4）對(duì)象... 

【文章來源】：大連海事大學(xué)遼寧省 211工程院校

【文章頁數(shù)】：77 頁

【學(xué)位級(jí)別】：碩士

【文章目錄】：
摘要
Abstract
1 Introduction
    1.1 Background and significance of the topic
    1.2 Research Status of target tracking in China and Abroad
        1.2.1 Research Status of Single-target tracking with correlation filtering
        1.2.2 Research Status of Multi-target tracking with correlation filtering
    1.3 Research content and chapter arrangement
        1.3.1 Research content
        1.3.2 Chapter Arrangement
2 Multi-target tracking pre-detection
    2.1 Introduction of Multi-target tracking data sets
        2.1.1 2D MOT 2015 dataset
        2.1.2 MOT16 Data Set
        2.1.3 Comparison of differences between data sets
        2.1.4 Inaccurate target detection
    2.2 Target detection models
        2.2.1 Traditional models
    2.3 Evaluation of target detection model
        2.3.1 Target detection and evaluation indicators
        2.3.2 Comparative analysis of test results
    2.4 Summary of this chapter
3 Discriminative Correlation Filter Tracker with Channel and Spatial Reliability
    3.1 Spatially constrained correlation filters
    3.2 Constructing spatial reliability map
    3.3 Channel detection reliability
    3.4. Channel reliability estimation
    3.5. Tracking with channel and spatial reliability
    3.6. Spatial and channel reliability ablation study
        3.6.1 The OTB 100 benchmark
        3.6.2. The VOT2015 benchmark
        3.6.3. The VOT2016 benchmark
    3.7 Inadequacies
    3.8 Summary of this chapter
4 Core-related filter tracking incorporating data association strategies
    4.1 Target transition status process
    4.2 Target Association Strategy
        4.2.1 Calculating the correlation matrix
        4.2.2 Determining the optimal association
    4.3 Target similarity judgment method
    4.4 Algorithm Flow
        4.4.1 Troubleshooting
        4.4.2 Outline of proposed algorithm
    4.5 Summary of this chapter
5 Multi-target tracking experiments
    5.1 Experimental Environment
    5.2 Experimental analysis
        5.2.1. Implementation details and parameters
        5.2.2 Non-axis-aligned target initialization robustness
    5.3 Evaluation indicators
    5.4 Summary of this chapter
6 Summary and Outlook
    6.1 Summary of work in this thesis
    6.2 Future work prospects
References
DECLARATION
ACKNOWLEDGEMENT



本文編號(hào)：3105900