【摘要】：智能化的交通解決方案已經(jīng)成為緩解交通壓力的有效手段,人工智能和大數(shù)據(jù)的蓬勃發(fā)展,給智能交通領(lǐng)域帶來了新的活力和發(fā)展。與此同時(shí),基于交通監(jiān)控的智能化算法是當(dāng)前交通信息采集的前沿發(fā)展方向和熱點(diǎn)問題,而基于視頻的車輛檢測和跟蹤任務(wù)則是交通信息采集的基礎(chǔ)和關(guān)鍵工作,是多樣交通參數(shù)獲取的基礎(chǔ)數(shù)據(jù)支撐。由于交通場景的復(fù)雜性,造成了車輛檢測和跟蹤中存在諸多挑戰(zhàn),例如遮擋、光照變化以及實(shí)時(shí)性要求等問題。近年來,深度學(xué)習(xí)技術(shù)在計(jì)算機(jī)視覺等領(lǐng)域取得了突破性進(jìn)展,也使得通過視頻分析方法實(shí)現(xiàn)交通狀態(tài)分析和理解成為了可能。隨著交通監(jiān)控設(shè)備的大量應(yīng)用,具有豐富交通信息的視頻數(shù)據(jù)井噴式增長,因此快速、準(zhǔn)確地車輛檢測和跟蹤方法對(duì)于交通信息獲取,交通運(yùn)行管理具有重要意義。本文基于實(shí)際道路中多維度的交通視頻監(jiān)控場景,以目前優(yōu)秀的目標(biāo)檢測和跟蹤算法為基礎(chǔ),對(duì)實(shí)現(xiàn)準(zhǔn)確高效的車輛跟蹤算法進(jìn)行了深入研究,提出了多模塊融合的車輛跟蹤框架。本文主要完成了以下工作:首先,提出了基于深度神經(jīng)網(wǎng)絡(luò)的車輛檢測方法。依據(jù)車輛及其周圍環(huán)境信息,以候選區(qū)域提出網(wǎng)絡(luò)和檢測網(wǎng)絡(luò)組成的網(wǎng)絡(luò)結(jié)構(gòu)為基礎(chǔ),利用深度學(xué)習(xí)框架Caffe,訓(xùn)練得到了魯棒的車輛檢測器。實(shí)驗(yàn)驗(yàn)證了算法在多種天氣和交通場景中取得了良好的效果。其次,針對(duì)核化相關(guān)濾波跟蹤方法在模型更新方面的缺陷,提出一種基于增量學(xué)習(xí)的模型更新方法。通過建立早期跟蹤模型的快照集合,結(jié)合近鄰幀收集的模型,采用增量更新的方式,構(gòu)建了包含早期以及當(dāng)前目標(biāo)信息的主成分的跟蹤模型。通過與多種模型更新方法對(duì)比,證明了增量更新的魯棒性和適應(yīng)性。最后,在車輛檢測和相關(guān)濾波跟蹤算法的基礎(chǔ)上,提出了車輛跟蹤算法。車輛檢測器用于初始化多尺度的相關(guān)濾波跟蹤算法和糾正跟蹤失敗。相關(guān)濾波跟蹤算法用于實(shí)現(xiàn)短時(shí)間單車輛跟蹤。通過基于軌跡片段置信度的關(guān)聯(lián)方法,實(shí)現(xiàn)了檢測和跟蹤模塊的有機(jī)融合,形成了更加完整的車輛軌跡,實(shí)現(xiàn)了復(fù)雜交通環(huán)境下的車輛跟蹤。實(shí)驗(yàn)證明該跟蹤框架實(shí)現(xiàn)了車輛速度和準(zhǔn)確性的平衡,在實(shí)際道路監(jiān)控視頻中取得了優(yōu)秀的效果。
[Abstract]:Intelligent traffic solution has become an effective means to relieve traffic pressure. The vigorous development of artificial intelligence and big data has brought new vitality and development to the intelligent transportation field. At the same time, the intelligent algorithm based on traffic monitoring is the forward development direction and hot issue of traffic information collection, and the task of vehicle detection and tracking based on video is the basis and key work of traffic information collection. It is the basic data support for obtaining various traffic parameters. Because of the complexity of traffic scene, there are many challenges in vehicle detection and tracking, such as occlusion, illumination change and real-time requirements. In recent years, deep learning technology has made a breakthrough in the field of computer vision, which makes it possible to realize traffic state analysis and understanding by means of video analysis. With the extensive application of traffic monitoring equipment, the video data with abundant traffic information is increasing rapidly and accurately, so it is very important for traffic information acquisition and traffic operation management to detect and track vehicles quickly and accurately. Based on the multi-dimensional traffic video surveillance scene in the actual road, based on the current excellent target detection and tracking algorithm, this paper makes a deep research on the realization of accurate and efficient vehicle tracking algorithm. A vehicle tracking framework based on multi-module fusion is proposed. The main work of this paper is as follows: firstly, a method of vehicle detection based on depth neural network is proposed. Based on the information of vehicle and its surrounding environment, and based on the network structure composed of candidate network and detection network, the robust vehicle detector is obtained by using the deep learning framework (Caffe,) training. Experiments show that the algorithm has achieved good results in various weather and traffic scenarios. Secondly, a model updating method based on incremental learning is proposed to overcome the defects of kernel correlation filter tracking method in model updating. By establishing the snapshot set of the early tracking model and combining the model collected by the nearest neighbor frame, the tracking model containing the principal components of the early and current target information is constructed by incremental updating. The robustness and adaptability of incremental updating are proved by comparison with other model updating methods. Finally, on the basis of vehicle detection and correlation filter tracking algorithm, vehicle tracking algorithm is proposed. Vehicle detectors are used to initialize multi-scale correlation filtering tracking algorithms and to correct tracking failures. Correlation filter tracking algorithm is used to realize short time single vehicle tracking. By using the correlation method based on the confidence degree of trajectory segment, the detection and tracking modules are integrated, and a more complete vehicle trajectory is formed, and the vehicle tracking in complex traffic environment is realized. The experimental results show that the tracking framework achieves the balance between vehicle speed and accuracy, and achieves excellent results in the actual road surveillance video.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：U495;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 ;車輛跟蹤軟件[J];全球定位系統(tǒng);2004年02期

2 卞建勇;徐建閩;裴海龍;;基于強(qiáng)化學(xué)習(xí)的視頻車輛跟蹤[J];華南理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年10期

3 張曉媚;陳偉海;劉敬猛;趙志文;;基于柔性曲桿的車輛跟蹤算法設(shè)計(jì)與實(shí)現(xiàn)[J];北京航空航天大學(xué)學(xué)報(bào);2011年07期

4 甘玲;潘小雷;;一種應(yīng)用于交通環(huán)境中的運(yùn)動(dòng)車輛跟蹤方法[J];重慶郵電大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年03期

5 郭鋒;王秉政;楊晨暉;;復(fù)雜背景下車輛跟蹤的改進(jìn)算法及逆行檢測[J];圖學(xué)學(xué)報(bào);2013年04期

6 魏玉強(qiáng);王成儒;;多車輛跟蹤時(shí)分割粘連車輛的方法[J];電視技術(shù);2009年11期

7 王文龍;李清泉;;基于蒙特卡羅算法的車輛跟蹤方法[J];測繪學(xué)報(bào);2011年02期

8 李t，

本文編號(hào)：2246220