發(fā)布時間：2018-03-02 07:32

  本文關(guān)鍵詞： 目標跟蹤 結(jié)構(gòu)化支持向量機 特征表示 優(yōu)化算法 異常檢測　出處：《西北農(nóng)林科技大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：目標跟蹤是計算機視覺的重要分支,融合了圖像處理、模式識別、機器學(xué)習(xí)等多個學(xué)科領(lǐng)域的結(jié)晶,并在軍事制導(dǎo)、視覺導(dǎo)航、安全監(jiān)控、人機交互等方面有廣闊的應(yīng)用前景。近年來,結(jié)構(gòu)化支持向量機(SSVM)跟蹤算法由于提供了一種新穎的判別式跟蹤模型及良好的性能表現(xiàn)而受到了廣泛的關(guān)注。本文以SSVM跟蹤算法為基礎(chǔ),從特征表示、優(yōu)化方法和異常檢測等三個方面進行研究,并在公開的目標跟蹤基準數(shù)據(jù)庫上對提出的方法進行有效性驗證,主要成果如下:(1)提出了一種基于彩色Haar-like特征和選擇性更新的改進Struck跟蹤算法。首先使用一種彩色Haar-like特征表示方法,能夠以微小的計算代價為Haar-like特征加入顏色信息。然后提出一種選擇性更新模式,使得Struck跟蹤器能夠檢測異常場景并停止對跟蹤模型的更新,從而減輕模型漂移問題。在OTB50上的實驗表明,使用了彩色Haar-like特征和選擇性更新模式的Struck算法,在OPE、TRE、SRE三種評價方法的精準度和成功率共6個指標上,分別提升了9.1%、4.6%、7.5%、4.1%、8.3%和4.5%。(2)提出了一種對偶線性SSVM跟蹤算法(DLSSVM)。本文使用了一種新的多特征目標表示方法,通過將局部秩變換(LRT)特征與Lab顏色特征相結(jié)合,能夠起到突顯圖像細節(jié)并抑制平滑部分的作用。隨后使用顯式特征映射將多層特征離散化,以達到使用線性核函數(shù)近似交叉核的效果。在魯棒性增強方面,采用多尺度目標檢測算法,以適應(yīng)目標的尺度變化。本部分創(chuàng)新性地使用了對偶坐標下降(DCD)算法求解SSVM跟蹤模型,與經(jīng)過顯式特征映射的LRT多層特征相結(jié)合,提出的DLSSVM跟蹤器性能顯著優(yōu)于同類型的Struck跟蹤算法。(3)提出一種加權(quán)間隔SSVM跟蹤模型(WMSSVM)。通過使用WMSSVM模型,能夠使得跟蹤器在訓(xùn)練更新時將樣本的置信度包含在內(nèi),從而自適應(yīng)地從異常場景中學(xué)習(xí)更新。在OTB100算法基準庫上,WMSSVM算法在OPE和TRE的精準度和成功率等四個指標上,成績高達82.7%、57.5%、83.5%和60.2%。綜上所述,本文從三個方面對SSVM跟蹤算法進行研究:在特征表示方面,使用了彩色Haar-like特征和LRT多特征;在模型求解方面,使用了DCD優(yōu)化算法;在魯棒性增強方面,使用了選擇性更新、尺度估計和加權(quán)間隔模型。以上三個方面均為SSVM跟蹤算法帶來了不同程度的性能提升。
[Abstract]:Target tracking is an important branch of computer vision, which combines the crystallization of image processing, pattern recognition, machine learning and other disciplines, and in military guidance, visual navigation, security monitoring, In recent years, human-computer interaction and other fields have broad application prospects. Structured support Vector Machine (SVM) tracking algorithm has attracted much attention because of its novel discriminant tracking model and good performance. Based on the SSVM tracking algorithm, this paper presents the feature representation of the algorithm. The optimization method and anomaly detection are studied, and the validity of the proposed method is verified on the open target tracking benchmark database. The main results are as follows: 1) an improved Struck tracking algorithm based on color Haar-like features and selective updating is proposed. Firstly, a color Haar-like feature representation method is used. The color information can be added to the Haar-like feature at a small computational cost. Then a selective update mode is proposed, which enables the Struck tracker to detect abnormal scenes and stop updating the tracking model. Experiments on OTB50 show that the Struck algorithm based on color Haar-like feature and selective updating mode is used to evaluate the accuracy and success rate of the three evaluation methods. This paper presents a dual linear SSVM tracking algorithm called DLSSVM.A new multi-feature target representation method is used in this paper, by combining the local rank transform (LRT) feature with the Lab color feature. It can highlight the details of the image and suppress the smooth part. Then the multi-layer features are discretized by explicit feature mapping to achieve the effect of using linear kernel function to approximate crossover kernels. A multi-scale target detection algorithm is adopted to adapt to the scale change of the target. In this part, the dual coordinate descent DCD algorithm is used to solve the SSVM tracking model, which is combined with the LRT multi-layer feature which is mapped by explicit features. The performance of the proposed DLSSVM tracker is significantly better than that of the Struck tracking algorithm of the same type. (3) A weighted spaced SSVM tracking model is proposed. By using the WMSSVM model, the tracker can include the confidence of the samples in the training update. In the OTB100 algorithm benchmark database, the accuracy and success rate of OPE and TRE are as high as 82.7% and 60.2%. In this paper, SSVM tracking algorithm is studied from three aspects: color Haar-like feature and LRT multi-feature are used in feature representation, DCD optimization algorithm is used in model solving, and selective update is used in robustness enhancement. Scale estimation and weighted interval model. The above three aspects have brought about different performance improvements for SSVM tracking algorithm.
【學(xué)位授予單位】：西北農(nóng)林科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前4條

1 寧紀鋒;趙耀博;石武禎;;多通道Haar-like特征多示例學(xué)習(xí)目標跟蹤[J];中國圖象圖形學(xué)報;2014年07期

2 楊戈;劉宏;;視覺跟蹤算法綜述[J];智能系統(tǒng)學(xué)報;2010年02期

3 朱翔;潘崢嶸;;基于OV7620的機器人視覺導(dǎo)航系統(tǒng)設(shè)計[J];電子測量技術(shù);2010年01期

4 鄒開其;;美國智能運輸系統(tǒng)(ITS)研究進展[J];數(shù)字社區(qū)&智能家居;2007年05期

相關(guān)碩士學(xué)位論文 前1條

1 江南春;肛管外病癥計算機輔助診斷的圖像分割和目標跟蹤[D];南昌大學(xué);2011年

，

本文編號：1555598