本文關(guān)鍵詞：復(fù)雜交通視頻場景中的車輛軌跡提取及行為分析　出處：《長安大學(xué)》2016年博士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 車輛軌跡提取 行為分析 視頻檢測 局部特征 光流法 相似性度量 Dirichlet過程混合模型

【摘要】：基于視頻的車輛運(yùn)動軌跡提取及行為分析作為一個多學(xué)科交叉融合形成的研究領(lǐng)域,涵蓋了數(shù)字圖像處理技術(shù)、人工智能以及模式識別等多學(xué)科知識。然而,由于該領(lǐng)域研究對象復(fù)雜,涉及學(xué)科眾多,目前仍有很多難點問題亟待解決。復(fù)雜交通場景中運(yùn)動車輛檢測、跟蹤和行為識別一直是該領(lǐng)域研究的熱點和難點,許多方法和技術(shù)還不夠成熟和完善。本文圍繞基于視頻的車輛軌跡提取與行為分析中的目標(biāo)車輛檢測、運(yùn)動車輛跟蹤、車輛軌跡相似性度量和軌跡聚類等關(guān)鍵問題進(jìn)行了深入研究,取得了以下主要研究成果:1)針對復(fù)雜交通場景下的車輛目標(biāo)檢測,本文提出一種基于車輛對稱特征和陰影特征的車輛目標(biāo)檢測方法。該方法在SURF特征提取算法的基礎(chǔ)上,利用水平鏡像矩陣構(gòu)造新的SURF特征描述算子。由于視覺上具有對稱特性的特征點處于不同尺度時,其匹配誤差會比較大。因此,本文從減少Haar特征累加次數(shù)和降低尺度對特征點表示的影響兩方面入手,對S-SURF算法進(jìn)行改進(jìn)和優(yōu)化。然后采用優(yōu)化的S-SURF算法對車輛的對稱特征進(jìn)行提取,并利用車輛對稱特性對車輛的中心位置進(jìn)行定位,最后,根據(jù)車輛底部陰影特征對車輛目標(biāo)進(jìn)行識別和區(qū)域定位。實驗結(jié)果表明,該方法利用局部不變特征集合來描述車輛目標(biāo),有效地避免了復(fù)雜場景下的目標(biāo)分割難題,同時簡化了局部特征檢測方法中的聚類問題,復(fù)雜度較低,且具有較高的準(zhǔn)確性。2)運(yùn)動車輛的可靠穩(wěn)定跟蹤是車輛軌跡提取的關(guān)鍵。本文提出一種融合特征匹配和光流法的車輛目標(biāo)跟蹤方法,該方法在基于雙向可逆性約束的KLT算法的基礎(chǔ)上,構(gòu)造新的偏移量估算方法,對穩(wěn)定性較差的特征點進(jìn)行剔除,提高了特征點跟蹤的可靠性和穩(wěn)定性。同時,采用SURF特征匹配算法作為補(bǔ)償機(jī)制對目標(biāo)特征點集進(jìn)行更新和校正。最后,結(jié)合初始幀中特征點之間相對位置和相對角度的關(guān)系,確定當(dāng)前幀中目標(biāo)的尺度變化和旋轉(zhuǎn)變化,并采用層次聚類的方法,對特征點進(jìn)行聚類,以此刪除異常特征點,從而確定當(dāng)前幀中的目標(biāo)區(qū)域。該算法將兩個匹配策略相結(jié)合,既提高了跟蹤算法的穩(wěn)定性,也很好地解決了目標(biāo)在被跟蹤過程中發(fā)生的形變、部分遮擋等問題,對目標(biāo)的尺度和旋轉(zhuǎn)變化也具有較強(qiáng)的魯棒性。3)運(yùn)動軌跡的相似性度量是軌跡聚類過程中的一個核心問題,由于車輛軌跡的復(fù)雜性和多樣性,現(xiàn)有度量方法都有其局限性。本文提出一種融合多特征和編輯距離的軌跡相似性度量方法。該方法在EDR編輯距離的基礎(chǔ)上,結(jié)合軌跡點的速度和方向特征,對軌跡進(jìn)行分段處理,并給具有不同特征意義的分段賦予不同的編輯操作代價值。最后,對基于分段表示的IEDR算法進(jìn)行了進(jìn)一步的定義和分析。該算法保留了EDR算法的允許時間伸縮、抗噪性等優(yōu)點的同時,將軌跡點的位置、速度和方向特征合理地融入到車輛運(yùn)動軌跡的相似性度量中,進(jìn)一步提高了軌跡相似性度量的準(zhǔn)確性和魯棒性。4)車輛行為模式學(xué)習(xí)的目的是提取出具體交通場景的常態(tài)運(yùn)動模式,從而為車輛異常行為識別研究提供前提條件。本文提出一個基于增量式DPMM的貝葉斯最大后驗概率估計方法的軌跡聚類模型。該方法采用DFT系數(shù)作為軌跡的特征表示方法,提出一種基于DPMM的軌跡聚類方法,并在此基礎(chǔ)上,對Gibbs抽樣過程進(jìn)行改進(jìn),以已分類軌跡作為先驗知識,對新增軌跡類別進(jìn)行劃分。同時,在分類過程中,學(xué)習(xí)軌跡的常態(tài)運(yùn)動模式,通過運(yùn)動模式和方向模式匹配策略,對車輛異常行為進(jìn)行判別。該算法不需要訓(xùn)練樣本,而且隨著新增軌跡的到來而變化,聚類模型能夠?qū)崿F(xiàn)自適應(yīng)變化及模型參數(shù)學(xué)習(xí)和分類數(shù)目自動更新的任務(wù),很好地解決了由于交通異常行為的不可預(yù)知、不常發(fā)生性引起的數(shù)據(jù)稀疏情況下的模型訓(xùn)練困難問題。同時,利用已有聚類結(jié)果,將每次新增軌跡劃分到已有類別或新類中,不需要每次對所有軌跡進(jìn)行重新聚類,聚類效率大大提高。
[Abstract]:Video based vehicle motion trajectory extraction and behavior analysis is a research field formed by multidisciplinary fusion, which covers multidisciplinary knowledge such as digital image processing technology, AI and pattern recognition. However, because of the complexity of the research object in this field and many subjects, there are still many difficult problems to be solved. Moving vehicle detection, tracking and behavior recognition in complex traffic scenes has been a hot and difficult topic in the field. Many methods and technologies are not mature enough. This paper focuses on the analysis of the target vehicle vehicle trajectory extraction and behavior in video detection, vehicle tracking, vehicle trajectory similarity measure and the key problem of trajectory clustering based on in-depth research, the main results are as follows: 1) for vehicle target detection under complex traffic scene, this paper proposes a vehicle detection method for target the vehicle features and shadow features based on symmetry. On the basis of the SURF feature extraction algorithm, this method constructs a new SURF feature description operator by using the horizontal mirror matrix. Because the feature points of the visual symmetry are in different scales, the matching error will be larger. Therefore, this paper improves and optimizes the S-SURF algorithm from two aspects: reducing the number of Haar feature accumulating times and reducing the impact of the scale on the representation of the feature points. Then, the optimized S-SURF algorithm is used to extract the symmetrical characteristics of the vehicle, and the vehicle's central location is located by the symmetry characteristics of the vehicle. Finally, the vehicle's target is identified and located according to the shadow feature of the vehicle bottom. The experimental results show that the proposed method uses local invariant feature set to describe vehicle targets, effectively avoids the problem of target segmentation in complex scenes, and simplifies the clustering problem in local feature detection, with low complexity and high accuracy. 2) the reliable and stable tracking of the moving vehicles is the key to the vehicle trajectory extraction. The vehicle target tracking method this paper proposes a fusion feature matching and optical flow method, the method based on KLT algorithm of bidirectional reversible constraints on the structure of the new method to estimate the offset, poor stability of feature points are removed, improves the feature tracking reliability and stability. At the same time, the SURF feature matching algorithm is used as compensation mechanism to update and correct the target set of feature points. Finally, combined with the relationship between the feature points in the initial frame relative position and angle of the scale change to determine the target in the current frame and rotation, and the method of hierarchical clustering, clustering of feature points, in order to remove abnormal points, so as to determine the area of the object in the current frame. The algorithm combines two matching strategies, which not only improves the stability of tracking algorithm, but also solves the problems of deformation and partial occlusion during target tracking. It also has strong robustness to the scale and rotation of targets. 3) the similarity measurement of trajectory is a core problem in trajectory clustering. Due to the complexity and diversity of vehicle trajectories, existing metric methods have their limitations. In this paper, a method of trajectory similarity measurement is proposed, which combines multiple features and edit distance. Based on the edit distance of EDR, combined with the speed and direction characteristics of track points, the method segmented the trajectories and assigned different editing operations to different feature segments. Finally, the IEDR algorithm based on piecewise representation is further defined and analyzed. The algorithm preserves the advantages of EDR algorithm such as the allowed time expansion and noise immunity. Meanwhile, it integrates the location, velocity and direction characteristics of trajectories reasonably into the similarity measurement of vehicle trajectories, which further improves the accuracy and robustness of trajectory similarity measurement. 4) the purpose of vehicle behavior model learning is to extract the normal motion pattern of specific traffic scene, thus providing the precondition for the research of vehicle abnormal behavior recognition. This paper presents a trajectory clustering model based on an incremental DPMM based Bayesian maximum a posteriori probability estimation method. In this method, the DFT coefficient is used as the characteristic expression method of trajectory. A trajectory clustering method based on DPMM is proposed. Based on that, the Gibbs sampling process is improved, and the classified track is used as a priori knowledge to classify the new trajectory categories. At the same time, in the classification process, the normal motion model of learning trajectory is used to discriminate the abnormal behavior of the vehicle through the motion pattern and the direction pattern matching strategy. The algorithm does not need training samples, and changes with the arrival of new track, clustering model can realize adaptive and parameter learning and classification number of automatic update tasks, is a good solution to the traffic abnormal behavior is unpredictable, infrequent training difficult model data sparseness problem caused by the situation. At the same time, we use existing clustering results to divide every new trajectory into existing categories or new classes, and do not need to re track all trajectories at any time, so the clustering efficiency is greatly improved.
【學(xué)位授予單位】：長安大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 許宏科;秦嚴(yán)嚴(yán);陳會茹;;基于改進(jìn)ORB的圖像特征點匹配[J];科學(xué)技術(shù)與工程;2014年18期

2 宋琳;程詠梅;劉楠;劉夏雷;;采用多重約束的無人機(jī)導(dǎo)航KLT視覺跟蹤算法[J];紅外與激光工程;2013年10期

3 劉玉;王敬東;李鵬;;一種基于SIFT和KLT相結(jié)合的特征點跟蹤方法研究[J];宇航學(xué)報;2011年07期

4 趙有婷;李熙瑩;羅東華;;基于視頻車輛軌跡模型的交通事件自動檢測方法研究[J];中山大學(xué)學(xué)報(自然科學(xué)版);2011年04期

5 龔璽;裴韜;孫嘉;羅明;;時空軌跡聚類方法研究進(jìn)展[J];地理科學(xué)進(jìn)展;2011年05期

6 周建英;王飛躍;曾大軍;;分層Dirichlet過程及其應(yīng)用綜述[J];自動化學(xué)報;2011年04期

7 劉闖;龔聲蓉;崔志明;劉純平;夏侯玉嬌;;基于角點采樣的多目標(biāo)跟蹤方法[J];中國圖象圖形學(xué)報;2008年10期

8 劉o，

本文編號：1345018