本文選題：智能車 + 車輛檢測(cè)　； 參考：《吉林大學(xué)》2015年博士論文

【摘要】：本文圍繞著車輛主動(dòng)安全中的車輛檢測(cè)和車輛跟蹤技術(shù)中面臨的一些關(guān)鍵問題展開了深入的研究，并取得了一定的進(jìn)展，具體包括： 在基于車載相機(jī)的車輛檢測(cè)方面，通過對(duì)采集圖像中車輛的特征進(jìn)行分析，提出了一種基于水平邊緣車輛波的車輛檢測(cè)方法，該方法中的水平邊緣車輛波不但能很好地描述車輛的特征，同時(shí)也能排除大量干擾情況。方法的準(zhǔn)確率和處理效率都很高，且能同時(shí)應(yīng)用于前向和后向車輛檢測(cè)。另外，根據(jù)圖像中車輛尾燈的特點(diǎn)，，本文提出了一種車輛尾燈的車輛檢測(cè)方法，方法可作為多特征車輛檢測(cè)的一個(gè)判據(jù)。針對(duì)單一特征誤檢率高的問題，本文提出了兩種多特征融合的車輛檢測(cè)方法，一種是基于投票法的多特征融合車輛檢測(cè)方法，方法能極大程度地降低誤檢率。另一種是基于運(yùn)動(dòng)軌跡的多特征融合車輛檢測(cè)方法，方法使用軌跡判斷代替分類器判斷，解決了車輛檢測(cè)分類器依賴于樣本規(guī)模的問題。為了達(dá)到提高檢測(cè)率的同時(shí)降低誤檢率的要求，本文提出了兩種基于決策理論的多特征融合車輛檢測(cè)方法。首先將三個(gè)基于特征的車輛檢測(cè)方法（對(duì)稱性、車尾燈，HoG+AdaBoost分類器）的輸出結(jié)果進(jìn)行模糊化表達(dá)，之后分別使用Choquet模糊積分和D-S證據(jù)理論對(duì)模糊化的車輛特征算法結(jié)果進(jìn)行結(jié)果融合。通過特征融合，實(shí)現(xiàn)了多工況下的車輛魯棒性檢測(cè)，提升了基于車載視覺傳感器的車輛檢測(cè)算法的性能。 在多車輛跟蹤方面，本文重點(diǎn)解決了尺度不斷變化，目標(biāo)消失以及跟蹤過程中目標(biāo)部分或全部遮擋情況下的多車輛跟蹤問題。首先針對(duì)尺度不斷變化的多車輛跟蹤問題，本文提出了一種基于擴(kuò)展卡爾曼濾波以及基于On-line boosting的離線和在線學(xué)習(xí)相結(jié)合的跟蹤方法，在對(duì)車輛進(jìn)行跟蹤的過程中結(jié)合離線多尺度車輛表觀分類器及遮擋判斷機(jī)制來處理目標(biāo)消失以及目標(biāo)間的嚴(yán)重遮擋問題，試驗(yàn)結(jié)果表明，本文提出的算法在保證實(shí)時(shí)性的同時(shí)實(shí)現(xiàn)了尺寸不斷變化條件下的車輛跟蹤。除此之外，為解決現(xiàn)有的基于粒子濾波的目標(biāo)跟蹤方法不能滿足復(fù)雜工況下多車輛跟蹤的問題，本文提出了一種基于改進(jìn)粒子濾波的車輛跟蹤方法。方法中的適應(yīng)于移動(dòng)平臺(tái)下的多車輛跟蹤問題的粒子濾波狀態(tài)方程，基于歸一化MCRP面積的目標(biāo)初始和消失處理方法以及跟蹤過程中的目標(biāo)位置沖突處理方法保證了復(fù)雜工況下多車輛跟蹤方法的魯棒性。 通過在公開測(cè)試集和自行制作的測(cè)試集上對(duì)本文提出的基于車載視覺傳感器的車輛檢測(cè)和車輛跟蹤方法進(jìn)行測(cè)試，并與目前一些廣泛使用的方法進(jìn)行對(duì)比，驗(yàn)證了本文算法的有效性。
[Abstract]:In this paper, some key problems in vehicle detection and vehicle tracking technology in active vehicle safety are studied, and some progress has been made. In the aspect of vehicle detection based on vehicle camera, a vehicle detection method based on horizontal edge vehicle wave is proposed by analyzing the characteristics of the vehicle in the collected image. The vehicle waves at the horizontal edge in this method can not only describe the vehicle characteristics well, but also eliminate a large number of disturbances. The method has high accuracy and processing efficiency, and can be applied to both forward and backward vehicle detection. In addition, according to the characteristics of vehicle taillights in the image, this paper presents a vehicle detection method for vehicle taillights, which can be used as a criterion for multi-feature vehicle detection. Aiming at the problem of high false detection rate of single feature, this paper proposes two vehicle detection methods based on multi-feature fusion, one is multi-feature fusion vehicle detection method based on voting method, which can greatly reduce the false detection rate. The other is a multi-feature fusion vehicle detection method based on motion trajectory, which uses trajectory judgment instead of classifier to solve the problem that vehicle detection classifier depends on sample size. In order to improve the detection rate and reduce the false detection rate, two multi-feature fusion vehicle detection methods based on decision theory are proposed in this paper. Firstly, the output results of three feature-based vehicle detection methods (symmetry, tail light HoG AdaBoost classifier) are expressed by fuzzy method. Then Choquet fuzzy integral and D-S evidence theory are used to fuse the result of fuzzy vehicle feature algorithm. By means of feature fusion, vehicle robustness detection under multi-working conditions is realized, and the performance of vehicle detection algorithm based on vehicle vision sensor is improved. In the aspect of multi-vehicle tracking, the problem of multi-vehicle tracking with varying scales, vanishing targets and partially or totally occluded targets in the tracking process is solved in this paper. First of all, aiming at the problem of multi-vehicle tracking with changing scales, this paper proposes a tracking method based on extended Kalman filter and On-line boosting, which combines offline and online learning. In the process of vehicle tracking, the problem of object vanishing and serious occlusion between targets is dealt with by combining off-line multi-scale vehicle surface classifier and occlusion judgment mechanism. The experimental results show that, The algorithm proposed in this paper not only guarantees the real-time performance, but also realizes the vehicle tracking under the condition of constant size change. In addition, in order to solve the problem that the existing particle filter based target tracking method can not meet the problem of multi-vehicle tracking under complex operating conditions, a vehicle tracking method based on improved particle filter is proposed in this paper. The particle filter equation of state for multi-vehicle tracking on mobile platform is proposed in this paper. The target initial and vanishing methods based on normalized MCRP area and the target position conflict processing method in the tracking process ensure the robustness of the multi-vehicle tracking method under complex operating conditions. The vehicle detection and tracking methods proposed in this paper are tested on the open test set and the self-made test set, and compared with some widely used methods. The validity of the proposed algorithm is verified.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 齊美彬;潘燕;張銀霞;;基于車底陰影的前方運(yùn)動(dòng)車輛檢測(cè)[J];電子測(cè)量與儀器學(xué)報(bào);2012年01期

2 丁瑩;李文輝;范靜濤;楊華民;;基于Choquet模糊積分的運(yùn)動(dòng)目標(biāo)檢測(cè)算法[J];電子學(xué)報(bào);2010年02期

3 劉晨光;程丹松;劉家鋒;黃劍華;唐降龍;;一種基于交互式粒子濾波器的視頻中多目標(biāo)跟蹤算法[J];電子學(xué)報(bào);2011年02期

4 王瑩;李文輝;;基于多特征融合的高精度視頻火焰檢測(cè)算法[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2010年03期

5 李文輝;周強(qiáng);王瑩;張德才;;基于均值偏移粒子濾波的自適應(yīng)跟蹤[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2012年02期

6 解文華;肖進(jìn)勝;易本順;張亞琪;李明;;一種基于Mean Shift和C-V模型的車輛跟蹤算法[J];湖南大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年07期

相關(guān)博士學(xué)位論文 前1條

1 王楠;基于多視覺特征融合的后方車輛檢測(cè)技術(shù)研究[D];東北大學(xué)　;2009年

本文編號(hào)：2042610