基于CSK的目標跟蹤穩(wěn)健算法
發(fā)布時間：2019-03-20 15:45
【摘要】：近些年,針對視頻幀圖像的目標跟蹤技術成為計算機視覺研究的熱點,通過目標檢測實現(xiàn)目標跟蹤的方法備受青睞,機器學習的思想被應用于模型更新,基于核相關濾波理論的目標跟蹤算法在跟蹤精度和實時性等方面取得了突出的成果。然而,光照劇烈變化、目標尺度變化、目標被完全遮擋以及目標在幀間發(fā)生大位移等來源于復雜實際環(huán)境的不可控因素仍然是目標跟蹤研究的難點與挑戰(zhàn)。本文基于循環(huán)結(jié)構(gòu)核(Circulant Structure Kernels,CSK)跟蹤方法對上述問題進行深入研究,取得如下成果:(1)通過對圖像特征進行研究分析,并對CSK跟蹤算法在頻域進行多通道擴展,使算法能應用梯度方向直方圖(Histogram of Oriented Gridients,HOG)、顏色名(Color Name,CN)、局部二值模式(Local Binary Pattern,LBP)等更優(yōu)秀的視覺特征,增強算法對目標的表觀能力,削弱光學變化和幾何變化對目標跟蹤的影響。(2)通過對源圖像縮放變換構(gòu)建圖像金字塔,然后分層提取HOG特征,構(gòu)建基于HOG特征的金字塔樣本集,訓練金字塔核相關濾波分類器(Pyramid Kernel Correlation Filter,PKCF),實現(xiàn)目標尺度檢測,并根據(jù)目標的尺度變化調(diào)整跟蹤矩形框和采樣窗口的尺度,減小目標模型的誤差積累,提高目標跟蹤精度,完成CSK的尺度自適應改進。(3)在CSK跟蹤流程中引入Kalman濾波器,充分利用目標運動狀態(tài)信息,對目標在下一幀中可能出現(xiàn)的位置進行初步預測,然后再利用PKCF在預測位置附近進行目標中心位置校準和尺度檢測,實現(xiàn)目標檢測自適應,改進CSK跟蹤算法當前幀目標檢測區(qū)域固定在上一幀目標中心位置附近的缺陷,解決目標被完全遮擋和幀間大位移的問題。(4)對于Kalman濾波器與PKCF的更新,將離線更新與在線更新相結(jié)合,實現(xiàn)目標模型和分類器參數(shù)的自適應更新。首先利用跟蹤效果好的目標模型和分類器參數(shù)建立備選方案,當跟蹤精度下降或目標被完全遮擋時,啟用備選方案代替在線目標模型和分類器參數(shù)離線更新PKCF。Kalman濾波器對當前幀進行位置預測的狀態(tài)輸入是上一幀PKCF獲得的校準目標位置,即利用上一幀PKCF的輸出對當前幀Kalman濾波器進行狀態(tài)更新。(5)將尺度自適應、檢測自適應以及更新自適應的思想與遮擋處理機制相結(jié)合,提出本文的最終算法:基于預測—校準—更新的目標跟蹤穩(wěn)健算法。最后從標準測試集VOT和實景拍攝的視頻集中選取幾組具有光照變化、尺度變化、目標遮擋等不同挑戰(zhàn)的視頻進行對比實驗。本文算法與CSK算法的對比實驗結(jié)果表明,本文算法成功實現(xiàn)尺度自適應改進,在.一定程度上解決了目標被完全遮擋和幀間大位移的問題,另外,跟蹤精度和成功率也大幅提高。本文算法與CSK、KCF、CN、MOSSE、TLD、Struck算法在整體性能上做對比實驗,結(jié)果表明,文本算法在中心位置誤差、跟蹤精度和成功率方面表現(xiàn)最優(yōu),在跟蹤幀率方面表現(xiàn)不足。
[Abstract]:In recent years, target tracking technology for video frame images has become a hot topic in computer vision research. The method of target tracking through target detection has been favored, and the idea of machine learning has been applied to model updating. The target tracking algorithm based on kernel correlation filtering theory has achieved outstanding results in tracking accuracy and real-time performance. However, the uncontrollable factors such as intense illumination, change of target scale, complete occlusion of target and large displacement between frames are still the difficulties and challenges in the research of target tracking. Based on the cyclic structure kernel (Circulant Structure Kernels,CSK) tracking method, the above problems are deeply studied in this paper. The results are as follows: (1) through the research and analysis of the image features, the multi-channel expansion of CSK tracking algorithm in the frequency domain is carried out. It enables the algorithm to apply better visual features such as gradient direction histogram (Histogram of Oriented Gridients,HOG), color name (Color Name,CN), local binary pattern (Local Binary Pattern,LBP), and enhance the apparent ability of the algorithm to the target. The influence of optical and geometric changes on target tracking is weakened. (2) the pyramid of the source image is constructed by scaling and transforming the source image, and then the HOG feature is extracted by layers, and the pyramid sample set based on HOG feature is constructed. The pyramid kernel correlation filter classifier (Pyramid Kernel Correlation Filter,PKCF (pyramid kernel correlation filter classifier) is trained to realize target scale detection and adjust the scale of tracking rectangle box and sampling window according to the target scale change to reduce the error accumulation of the target model. The precision of target tracking is improved and the scale adaptive improvement of CSK is completed. (3) the Kalman filter is introduced into the CSK tracking flow to make full use of the moving state information of the target to predict the possible position of the target in the next frame. Then we use PKCF to calibrate and measure the center position of the target near the predicted position to realize the self-adaptation of the target detection, and improve the defect of the CSK tracking algorithm that the detection area of the current frame target is fixed near the center position of the target in the previous frame. The problem of complete occlusion of target and large displacement between frames is solved. (4) for the updating of Kalman filter and PKCF, off-line updating and on-line updating are combined to realize adaptive updating of target model and classifier parameters. Firstly, an alternative scheme is established by using the target model with good tracking effect and classifier parameters. When the tracking accuracy is reduced or the target is completely occluded, Enabling alternatives instead of on-line target models and classifier parameters offline updates the status input of the PKCF.Kalman filter to predict the position of the current frame is the position of the calibrated target obtained by the previous frame of PKCF. That is to say, the output of the previous frame PKCF is used to update the current frame Kalman filter. (5) the idea of scale adaptation, detection adaptation and update adaptation is combined with occlusion processing mechanism. The final algorithm of this paper: robust target tracking algorithm based on prediction-calibration-update. Finally, several sets of video with different challenges, such as illumination change, scale change and object occlusion, are selected from the standard test set VOT and the real-time video set to carry on the contrast experiment. The comparison between the proposed algorithm and the CSK algorithm shows that the proposed algorithm has successfully implemented the scale adaptive improvement. To some extent, the problem of complete occlusion and large displacement between frames is solved. In addition, the tracking accuracy and success rate are also greatly improved. The performance of the proposed algorithm is compared with that of the CSK,KCF,CN,MOSSE,TLD,Struck algorithm. The results show that the text algorithm has the best performance in the center position error, tracking accuracy and success rate, and underperforms in the tracking frame rate.
【學位授予單位】：昆明理工大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41
本文編號：2444360
[Abstract]:In recent years, target tracking technology for video frame images has become a hot topic in computer vision research. The method of target tracking through target detection has been favored, and the idea of machine learning has been applied to model updating. The target tracking algorithm based on kernel correlation filtering theory has achieved outstanding results in tracking accuracy and real-time performance. However, the uncontrollable factors such as intense illumination, change of target scale, complete occlusion of target and large displacement between frames are still the difficulties and challenges in the research of target tracking. Based on the cyclic structure kernel (Circulant Structure Kernels,CSK) tracking method, the above problems are deeply studied in this paper. The results are as follows: (1) through the research and analysis of the image features, the multi-channel expansion of CSK tracking algorithm in the frequency domain is carried out. It enables the algorithm to apply better visual features such as gradient direction histogram (Histogram of Oriented Gridients,HOG), color name (Color Name,CN), local binary pattern (Local Binary Pattern,LBP), and enhance the apparent ability of the algorithm to the target. The influence of optical and geometric changes on target tracking is weakened. (2) the pyramid of the source image is constructed by scaling and transforming the source image, and then the HOG feature is extracted by layers, and the pyramid sample set based on HOG feature is constructed. The pyramid kernel correlation filter classifier (Pyramid Kernel Correlation Filter,PKCF (pyramid kernel correlation filter classifier) is trained to realize target scale detection and adjust the scale of tracking rectangle box and sampling window according to the target scale change to reduce the error accumulation of the target model. The precision of target tracking is improved and the scale adaptive improvement of CSK is completed. (3) the Kalman filter is introduced into the CSK tracking flow to make full use of the moving state information of the target to predict the possible position of the target in the next frame. Then we use PKCF to calibrate and measure the center position of the target near the predicted position to realize the self-adaptation of the target detection, and improve the defect of the CSK tracking algorithm that the detection area of the current frame target is fixed near the center position of the target in the previous frame. The problem of complete occlusion of target and large displacement between frames is solved. (4) for the updating of Kalman filter and PKCF, off-line updating and on-line updating are combined to realize adaptive updating of target model and classifier parameters. Firstly, an alternative scheme is established by using the target model with good tracking effect and classifier parameters. When the tracking accuracy is reduced or the target is completely occluded, Enabling alternatives instead of on-line target models and classifier parameters offline updates the status input of the PKCF.Kalman filter to predict the position of the current frame is the position of the calibrated target obtained by the previous frame of PKCF. That is to say, the output of the previous frame PKCF is used to update the current frame Kalman filter. (5) the idea of scale adaptation, detection adaptation and update adaptation is combined with occlusion processing mechanism. The final algorithm of this paper: robust target tracking algorithm based on prediction-calibration-update. Finally, several sets of video with different challenges, such as illumination change, scale change and object occlusion, are selected from the standard test set VOT and the real-time video set to carry on the contrast experiment. The comparison between the proposed algorithm and the CSK algorithm shows that the proposed algorithm has successfully implemented the scale adaptive improvement. To some extent, the problem of complete occlusion and large displacement between frames is solved. In addition, the tracking accuracy and success rate are also greatly improved. The performance of the proposed algorithm is compared with that of the CSK,KCF,CN,MOSSE,TLD,Struck algorithm. The results show that the text algorithm has the best performance in the center position error, tracking accuracy and success rate, and underperforms in the tracking frame rate.
【學位授予單位】：昆明理工大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41
【參考文獻】
相關期刊論文 前8條
1 錢堂慧;羅志清;李果家;李應蕓;李顯凱;;核相關濾波跟蹤算法的尺度自適應改進[J];計算機應用;2017年03期
2 張雷;王延杰;孫宏海;姚志軍;吳培;;采用核相關濾波器的自適應尺度目標跟蹤[J];光學精密工程;2016年02期
3 高文;朱明;賀柏根;吳笑天;;目標跟蹤技術綜述[J];中國光學;2014年03期
4 李英明;夏海宏;;雙二次B-樣條插值圖像縮放[J];中國圖象圖形學報;2011年10期
5 張娟;毛曉波;陳鐵軍;;運動目標跟蹤算法研究綜述[J];計算機應用研究;2009年12期
6 李富棟;;機載紅外搜索與跟蹤系統(tǒng)的現(xiàn)狀與發(fā)展[J];激光與紅外;2008年05期
7 趙文彬;張艷寧;;角點檢測技術綜述[J];計算機應用研究;2006年10期
8 涂承勝;刁力力;魯明羽;陸玉昌;;Boosting家族AdaBoost系列代表算法[J];計算機科學;2003年03期
相關博士學位論文 前1條
1 陳東成;基于機器學習的目標跟蹤技術研究[D];中國科學院研究生院(長春光學精密機械與物理研究所);2015年
相關碩士學位論文 前2條
1 吳志達;一個基于Unity3d游戲引擎的體感游戲研究與實現(xiàn)[D];中山大學;2012年
2 夏海宏;圖像縮放及其GPU實現(xiàn)[D];浙江大學;2010年
，本文編號：2444360
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2444360.html
最近更新
教材專著
