發(fā)布時(shí)間：2018-03-18 09:05

  本文選題：運(yùn)動(dòng)車輛檢測(cè)　切入點(diǎn)：改進(jìn)的ViBe算法　出處：《天津工業(yè)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著人工智能的發(fā)展,在智能交通系統(tǒng)中,計(jì)算機(jī)視覺技術(shù)已經(jīng)融入到智能交通視頻的分析中。但由于交通視頻中背景復(fù)雜,噪聲較多,車輛運(yùn)動(dòng)目標(biāo)不規(guī)律,使得運(yùn)動(dòng)目標(biāo)的檢測(cè)和車輛的多目標(biāo)跟蹤仍然面臨著諸多具有挑戰(zhàn)性的問題。同時(shí)在越來越多的車輛視頻信息中,如何對(duì)檢測(cè)跟蹤到的車輛做有效的特征提取和方便快捷的檢索比對(duì)。這都成了智能交通信息領(lǐng)域迫切需要解決的問題。本文對(duì)交通視頻中運(yùn)動(dòng)目標(biāo)檢測(cè)、車輛多目標(biāo)跟蹤以及目標(biāo)特征提取和檢索等問題進(jìn)行了研究。在運(yùn)動(dòng)車輛檢測(cè)方面,針對(duì)目前常用的ViBe算法在檢測(cè)中出現(xiàn)明顯鬼影區(qū)域、緩慢目標(biāo)殘影難以消除、檢測(cè)精確度和魯棒性不足的問題,本文提出改進(jìn),利用灰度信息為像素建立生命長(zhǎng)度矩陣,使鬼影或殘影快速融入背景樣本得以消除。結(jié)合最大類間方差法設(shè)置自適應(yīng)閾值,加入良好后處理抑制動(dòng)態(tài)噪音。引入分類算法的統(tǒng)計(jì)指標(biāo),對(duì)車輛檢測(cè)效果做定性、定量質(zhì)量評(píng)價(jià)和分析,實(shí)驗(yàn)結(jié)果表明,改進(jìn)算法在較少幀數(shù)內(nèi)去除了鬼影,抑制了運(yùn)動(dòng)目標(biāo)殘影,提高了運(yùn)動(dòng)車輛檢測(cè)的整體性能,這為車輛的多目標(biāo)跟蹤和特征提取奠定了良好基礎(chǔ)。在車輛多目標(biāo)跟蹤方面,針對(duì)目標(biāo)遮擋、粘連分離,相似物干擾,目標(biāo)運(yùn)動(dòng)不規(guī)律影響跟蹤穩(wěn)定性的問題,提出了一種級(jí)聯(lián)分類檢測(cè)和SVM分類器再識(shí)別的區(qū)域匹配跟蹤算法。在有效提取運(yùn)動(dòng)檢測(cè)得到的目標(biāo)連通區(qū)域的基礎(chǔ)上,根據(jù)基于HOG特征的級(jí)聯(lián)分類算法有效識(shí)別車輛跟蹤區(qū)域,減少車輛連通域粘連的影響,并且加入基于LBP特征的SVM分類算法二次識(shí)別去掉干擾物和相似物,根據(jù)區(qū)域匹配關(guān)聯(lián)算法保證了跟蹤框能夠穩(wěn)定跟蹤,通過多組實(shí)驗(yàn)驗(yàn)證了本文多目標(biāo)跟蹤算法可以對(duì)車輛持續(xù)穩(wěn)定地跟蹤,并且具有較高的準(zhǔn)確性。在目標(biāo)特征和檢索方面,本文設(shè)計(jì)了一個(gè)基于車輛特征的交通視頻檢索比對(duì)框架,首先對(duì)多目標(biāo)跟蹤車輛特征做分析,根據(jù)HSV非均勻量化原理提取目標(biāo)車輛的主區(qū)域顏色,利用樸素貝葉斯分類器對(duì)車型特征作識(shí)別分類。之后將跟蹤車輛的特征作結(jié)構(gòu)化存儲(chǔ),同時(shí)提出了基于顏色和車型融合的雙特征相似車輛檢索比對(duì)模式,根據(jù)倒排索引進(jìn)行檢索比對(duì),快速定位所需要查找的相似車輛。通過實(shí)驗(yàn)驗(yàn)證了特征提取和檢索比對(duì)的有效性和準(zhǔn)確性。
[Abstract]:With the development of artificial intelligence, computer vision technology has been integrated into the analysis of intelligent transportation video in intelligent transportation system. The detection of moving targets and the multi-target tracking of vehicles are still facing many challenging problems. At the same time, in more and more vehicle video information, How to do effective feature extraction and convenient and quick retrieval comparison for the vehicles detected and tracked has become an urgent problem in the field of intelligent traffic information. In this paper, moving target detection in traffic video is discussed. The problems of vehicle multi-target tracking and target feature extraction and retrieval are studied in this paper. In the aspect of moving vehicle detection, there are obvious ghost regions in the detection of moving vehicle based on the commonly used ViBe algorithm, so it is difficult to eliminate the residual image of slow target. In this paper, we propose an improved method, in which the gray information is used to build the life length matrix for pixels, so that the ghost or remnant image can be quickly incorporated into the background sample, and the adaptive threshold is set in combination with the maximum inter-class variance method. Adding good post-processing to suppress dynamic noise. Introducing the statistical index of classification algorithm, qualitative, quantitative quality evaluation and analysis of vehicle detection results show that the improved algorithm in less frame number to remove ghost, It can suppress the residual image of moving object, improve the overall performance of moving vehicle detection, which lays a good foundation for vehicle multi-target tracking and feature extraction. In the aspect of vehicle multi-target tracking, the target occlusion, adhesion separation, similar disturbance, etc. In this paper, a region matching tracking algorithm based on cascade classification detection and SVM classifier rerecognition is proposed. The concatenated classification algorithm based on HOG features can effectively identify the vehicle tracking area, reduce the influence of vehicle connectivity, and add the SVM classification algorithm based on LBP feature to remove the interference and similarity. According to the region matching association algorithm, the tracking frame can be tracked stably. The multi-target tracking algorithm in this paper is proved to be able to track vehicles steadily and steadily, and has high accuracy in target feature and retrieval. In this paper, a traffic video retrieval and comparison framework based on vehicle features is designed. Firstly, the multi-target tracking vehicle features are analyzed, and the main region color of the target vehicle is extracted according to the principle of HSV non-uniform quantization. Using naive Bayesian classifier to identify and classify vehicle features, then the tracking vehicle features are stored as structured storage, and a dual-feature similar vehicle retrieval and alignment model based on color and vehicle model fusion is proposed. The efficiency and accuracy of feature extraction and retrieval alignment are verified by experiments.
【學(xué)位授予單位】：天津工業(yè)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

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李斌;姚康澤;王巖;慈林林;萬建偉;;基于灰關(guān)聯(lián)的分類信息輔助多目標(biāo)跟蹤[J];信號(hào)處理;2009年03期

2 王汝夯;黃建國;張群飛;;基于網(wǎng)絡(luò)層次分析的水下多目標(biāo)跟蹤排序方法[J];西北工業(yè)大學(xué)學(xué)報(bào);2009年05期

3 陳炳和;雷達(dá)多目標(biāo)跟蹤的數(shù)學(xué)表示[J];電子學(xué)報(bào);1988年02期

4 余少波,胡守仁,劉孟仁;雷達(dá)多目標(biāo)跟蹤的神經(jīng)網(wǎng)絡(luò)方法[J];電子學(xué)報(bào);1992年04期

5 王順奎;多目標(biāo)跟蹤用的多傳感器信息融合技術(shù)[J];紅外與激光技術(shù);1994年04期

6 E.W.Kamen ,劉勝厚;基于對(duì)稱測(cè)量方程的多目標(biāo)跟蹤[J];艦船指揮控制系統(tǒng);1996年03期

7 劉維亭,張冰,朱志宇;多目標(biāo)跟蹤中的目標(biāo)位置及速度數(shù)據(jù)融合[J];船舶工程;2003年01期

8 路紅;費(fèi)樹岷;鄭建勇;張濤;;基于行為和部分觀測(cè)的多目標(biāo)跟蹤(英文)[J];Journal of Southeast University(English Edition);2008年04期

9 蔣戀華;甘朝暉;蔣e，

本文編號(hào)：1628900