基于多特征Mean Shift的人脸跟踪算法

张涛; 蔡灿辉

doi:10.3724/SP.J.1146.2008.01094

基于多特征Mean Shift的人脸跟踪算法

doi: 10.3724/SP.J.1146.2008.01094

张涛,
蔡灿辉

基金项目:

国家自然科学基金(60772164)，福建省自然科学基金(A0710009)和福建省科技计划项目(2005H034)资助课题

计量
- 文章访问数: 3910
- HTML全文浏览量: 74
- PDF下载量: 1882
- 被引次数: 0
出版历程
- 收稿日期: 2008-09-04
- 修回日期: 2009-03-09
- 刊出日期: 2009-08-19

A Face Tracking Algorithm Based on Multiple Feature Mean Shift

摘要

摘要: 该文把局部三值模式(Local Ternary Patterns, LTP)纹理特征引入Mean Shift跟踪算法，提出了基于多特征的Mean Shift人脸跟踪算法以解决Mean shift跟踪算法的鲁棒性问题。通过对LTP纹理特征的分析、研究，提出了一个LTP关键纹理模型，既增强了目标的关键纹理信息，又简化了LTP纹理模型。在此基础上，提出一种基于LTP关键纹理特征和肤色特征的Mean Shift人脸跟踪算法，有效地解决了Mean Shift算法的鲁棒性问题。为进一步提高对快速运动目标的跟踪速度和跟踪性能，该文引入了卡尔曼滤波器对目标进行预测。实验结果表明，该文的算法在目标定位的准确性和跟踪性能上比Mean Shift算法均有明显的提高。
- 人脸跟踪;卡尔曼滤波;Mean Shift算法;局部三值模式
Abstract: In this paper, an improved Mean Shift face tracking algorithm based on Local Ternary Patterns (LTP) of texture and color features is proposed to improve the robustness of the Mean Shift algorithm. Based on the study of LTP texture features, an LTP key texture pattern is introduced to enhance the important features of an object and reduce the computational complexity of the LPT texture model. A multiple feature Mean Shift face tracking algorithm is then proposed based on the LTP key texture and complexion features, and the robustness of Mean Shift algorithm is significantly enhanced. Furthermore, in order to improve the tracking speed and robustness, the Kalman filter is introduced to predict the position of the object window. Experimental results show that compared with the original Mean Shift algorithm, the proposed multiple feature face tracking algorithm has significantly improved the tracking performance.

HTML全文

参考文献(1)

Comaniciu D, Ramesh V, and Meer P. Real time tracking ofnon-rigid objects using mean shift[C]. Computer Vision andPattern Recognition, Hilton Head Island, SC, USA, Jun.13-15, 2000, Vol. 2: 142-149.[2]Wu Y and Huang T S. Robust visual tracking by integratingmultiple cues based on co-inference learning[J].InternationalJournal of Computer Vision.2004, 58(1):55-71[3]Triesch J and Von der Malsburg C. Self-organized integrationof adaptive visual cues for face tracking[C]. Automatic Faceand Gesture Recognition, Grenoble, France, Mar. 28-30, 2000:102-107.[4]Xu X and Li B. Head tracking using particle filter withintensity gradient and color histogram[C]. Conference onMultimedia and Expo, Amsterdam, Netherlands, Jul. 6-9,2005: 888-891.[5]Ojala T, Pietikainen M, and Harwood D. A comparativestudy of texture measures with classification based on featuredistribution[J].Pattern Recognition.1996, 29(1):51-59[6]Nguyen Q A, Antonio R K, and Shen C H. Enhancedkernel-based tracking for monochromatic and thermographicvideo[C]. Advanced Video and Signal Based Surveillance,Sydney, Australia, Nov. 11, 2006: 28.[7]王永忠, 梁彦, 赵春晖, 等. 基于多特征自适应融合的核跟踪方法[J]. 自动化学报, 2008, 34(1): 393-399.Wang Y Z, Liang Y, and Zhao C H, et al.. Kernel-basedtracking based on adaptive fusion of multiple cues[J]. ActaAutomatica Sinica, 2008, 34(4): 393-399.[8]宁纪锋, 吴成柯. 一种基于纹理模型的目标跟踪算法[J]. 模式识别与人工智能, 2007, 20(5): 612-618.Ning J F and Wu C K. A mean shift tracking algorithm basedon texture model[J]. Pattern Recognition and ArtificialIntelligence, 2007, 20(5): 612-618.[9]Tan X Y and Bill T. Enhanced local texture feature sets forface recognition under difficult lighting conditions[C].Analysis and Modeling of Faces and Gestures, Rio de Janeiro,Brazil, Oct. 20, 2007: 168-182.[10]Comaniciu D, Ramesh V, and Meer P. Kernel-based objecttracking[J].Pattern Analysis and Machine Intelligence.2003,25(5):564-577[11]Jiang Z L, Li S F, and Gao D F. An adaptive mean shifttracking method using multiscale image[C]. Wavelet Analysisand Pattern Recognition, Beijing, China, Nov. 2-4, 2007, Vol.3: 1060-1066.[12]Ojala T, Pietikainen M, and Maenpaa T. Multiresolutiongray-scale and rotation invariant texture classification withlocal binary patterns[J].Pattern Analysis and MachineIntelligence.2002, 24(7):971-987[13]Dellaert F and Thorpe C. Robust car tracking using kalmanfiltering and bayesian templates[C]. Conference on IntelligentTransportation Systems, Pittsburgh PA, Etats-Unis, Oct.15-17, 1997, Vol. 3207: 72-83.

施引文献

资源附件(0)

访问统计