本文選題：目標(biāo)跟蹤　切入點(diǎn)：相關(guān)濾波　出處：《安徽大學(xué)》2017年碩士論文

【摘要】：作為計(jì)算機(jī)視覺領(lǐng)域最具挑戰(zhàn)的關(guān)鍵技術(shù)之一,目標(biāo)跟蹤在視頻監(jiān)控、導(dǎo)航、軍事、人機(jī)交互、虛擬現(xiàn)實(shí)、智能機(jī)器人、自動(dòng)駕駛等多個(gè)領(lǐng)域都有著廣泛的應(yīng)用。經(jīng)過三十多年的研究,目標(biāo)跟蹤領(lǐng)域相繼涌現(xiàn)了大量經(jīng)典、優(yōu)秀的跟蹤算法,但受限于現(xiàn)實(shí)環(huán)境以及目標(biāo)運(yùn)動(dòng)的復(fù)雜性,當(dāng)前的跟蹤算法在準(zhǔn)確性、魯棒性以及實(shí)時(shí)性上難以滿足實(shí)際的應(yīng)用需求。準(zhǔn)確、魯棒、高效的目標(biāo)跟蹤算法仍然是極具挑戰(zhàn)的研究課題。相關(guān)濾波跟蹤(correlationtracking)自提出以來,其就以兼顧準(zhǔn)確性和速度的優(yōu)勢,吸引了大量研究者的關(guān)注。相關(guān)濾波器通過傅里葉變換將濾波器操作轉(zhuǎn)換到頻域,極大提升了算法運(yùn)行速度,實(shí)現(xiàn)了目標(biāo)位置中心的快速檢測,并且其重新采樣在線更新濾波器,保證了算法的準(zhǔn)確度和實(shí)時(shí)性。本文深入研究了基于相關(guān)濾波的目標(biāo)跟蹤算法,針對(duì)特征融合、尺度估計(jì)以及濾波器更新策略進(jìn)行改進(jìn),并在此基礎(chǔ)之上,結(jié)合相關(guān)濾波器跟蹤狀態(tài)判斷和級(jí)聯(lián)目標(biāo)檢測,實(shí)現(xiàn)了穩(wěn)定的長時(shí)間目標(biāo)跟蹤。本文主要的研究內(nèi)容和創(chuàng)新點(diǎn)總結(jié)如下:(1)首先介紹了目標(biāo)跟蹤領(lǐng)域的研究背景與意義、發(fā)展現(xiàn)狀以及技術(shù)挑戰(zhàn),并歸納總結(jié)當(dāng)前目標(biāo)跟蹤領(lǐng)域主流的算法框架,然后概述相關(guān)濾波器的基本概念及其在目標(biāo)跟蹤上的應(yīng)用原理。(2)為了提高相關(guān)濾波跟蹤的精度和成功率,提出了基于相關(guān)濾波的尺度和學(xué)習(xí)率自適應(yīng)跟蹤算法。首先算法融合了高效的特征提取方法作為濾波器輸入目標(biāo)樣本的外觀表示;針對(duì)相關(guān)濾波器不能應(yīng)對(duì)目標(biāo)尺度變化的限制,結(jié)合光流跟蹤的思路,根據(jù)相鄰幀之間可靠關(guān)鍵點(diǎn)的位移變化估計(jì)目標(biāo)尺度;并采用學(xué)習(xí)率自適應(yīng)方法,改進(jìn)相關(guān)濾波器的更新策略。通過高效的特征提取、尺度估計(jì)以及學(xué)習(xí)率自適應(yīng)方法的綜合運(yùn)用,大幅提升了跟蹤準(zhǔn)確度,同時(shí)也相對(duì)節(jié)省了算法運(yùn)算量,保證跟蹤器的實(shí)時(shí)性。在ObjectTrackingBenchmark上進(jìn)行算法的對(duì)比實(shí)驗(yàn)、成分分析實(shí)驗(yàn)以及定性評(píng)估實(shí)驗(yàn),以驗(yàn)證算法改進(jìn)的有效性。(3)針對(duì)長時(shí)間跟蹤過程中面臨的難題和挑戰(zhàn),提出了基于相關(guān)濾波和級(jí)聯(lián)檢測的長時(shí)間目標(biāo)跟蹤算法。首先采用基于相關(guān)濾波跟蹤的改進(jìn)算法作為基礎(chǔ)跟蹤器,并結(jié)合跟蹤目標(biāo)狀態(tài)判斷、級(jí)聯(lián)檢測丟失目標(biāo)的策略,組成長時(shí)間跟蹤的算法框架。其中級(jí)聯(lián)檢測器分別包括基于顏色模型的局部檢測、最近鄰檢測以及微調(diào)三個(gè)模塊,高效的跟蹤目標(biāo)狀態(tài)判斷方法則是能夠及時(shí)啟動(dòng)級(jí)聯(lián)檢測器的關(guān)鍵。通過級(jí)聯(lián)檢測逐層篩選搜索樣本,找回丟失的跟蹤目標(biāo),提升了算法在長時(shí)間跟蹤中的穩(wěn)定性。
[Abstract]:As one of the most challenging key technologies in the field of computer vision, target tracking in video surveillance, navigation, military, human-computer interaction, virtual reality, intelligent robot, Autopilot and other fields have been widely used. After more than 30 years of research, a large number of classic and excellent tracking algorithms have emerged in the field of target tracking, but limited by the real environment and the complexity of target motion. The current tracking algorithms are difficult to meet the practical application requirements in accuracy, robustness and real-time. Accurate, robust and efficient target tracking algorithm is still a challenging research topic. With the advantage of both accuracy and speed, it has attracted the attention of a large number of researchers. The correlation filter transforms the filter operation into frequency domain by Fourier transform, which greatly improves the speed of the algorithm. The fast detection of target location center is realized, and its resampling online update filter ensures the accuracy and real-time of the algorithm. In this paper, the target tracking algorithm based on correlation filter is studied in depth, aiming at feature fusion. Scale estimation and filter update strategy are improved, and based on this, correlation filter tracking state judgment and cascade target detection are combined. The main research contents and innovations of this paper are summarized as follows: first, the background and significance of the research in the field of target tracking, the current situation of development and the technical challenges are introduced. Then the basic concept of correlation filter and its application in target tracking are summarized. In order to improve the accuracy and success rate of correlation filter tracking, the paper summarizes the main algorithm framework in the field of target tracking, and then summarizes the basic concept of correlation filter and its application in target tracking. The scale and learning rate adaptive tracking algorithm based on correlation filter is proposed. Firstly, the efficient feature extraction method is used as the appearance representation of the filter input target sample. In view of the fact that the correlation filter can not cope with the limitation of the change of target scale, combined with the idea of optical flow tracking, the target scale is estimated according to the displacement change of reliable key points between adjacent frames, and the learning rate adaptive method is adopted. The updating strategy of correlation filter is improved. By using efficient feature extraction, scale estimation and adaptive learning rate method, the tracking accuracy is greatly improved, and the computational complexity of the algorithm is also saved. In order to verify the effectiveness of the improved algorithm, the real-time performance of the tracker is verified by the contrast experiment of algorithm, component analysis experiment and qualitative evaluation experiment on ObjectTrackingBenchmark to solve the problems and challenges in the long time tracking process. A long time target tracking algorithm based on correlation filtering and concatenated detection is proposed. Firstly, the improved algorithm based on correlation filter is used as the basic tracker. The cascade detector consists of three modules: local detection based on color model, nearest neighbor detection and fine tuning. The efficient tracking target state judgment method is the key to start the cascade detector in time. Through cascading detection to filter the search samples layer by layer, the missing target can be retrieved, and the stability of the algorithm in the long time tracking is improved.
【學(xué)位授予單位】：安徽大學(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)期刊論文 前1條

1 胡昭華;邢衛(wèi)國;何軍;張秀再;;多通道核相關(guān)濾波的實(shí)時(shí)跟蹤方法[J];計(jì)算機(jī)應(yīng)用;2015年12期

，

本文編號(hào)：1664590