高斯核函数卷积神经网络跟踪算法
|
摘要
针对深度学习跟踪算法训练样本缺少、训练费时、算法复杂度高等问题,引入高斯核函数进行加速,提出一种无需训练的简化卷积神经网络跟踪算法。首先,对初始帧目标进行归一化处理并聚类提取一系列初始滤波器组,跟踪过程中结合目标背景信息与前景候选目标进行卷积;然后,提取目标简单抽象特征;最后,将简单层的卷积结果进行叠加得到目标的深层次特征表达。通过高斯核函数加速来提高算法中全部卷积运算的速度,利用目标的局部结构特征信息,对网络各阶段滤波器进行更新,结合粒子滤波跟踪框架实现跟踪。在CVPR2013跟踪数据集上的实验表明,本文方法脱离了繁琐深度学习运行环境,能克服低分辨率下目标局部遮挡与形变等问题,提高复杂背景下的跟踪效率。
In view of such defects existing in the depth learning tracking algorithm as lack of training samples, large time consumption, and high complexity, this paper proposed a simplified convolutional neural network tracking algorithm in which training is unnecessary. Moreover, the Gaussian kernel function can be applied to this algorithm to significantly lower the computing time. Firstly, the initial frame target was normalized and clustered to extract a series of initial filter banks; in the tracking process, the background information of the target and the candidate target for the foreground were convoluted; then the simple and abstract features of the target were extracted; finally, all the convolutions of a simple layer were superposed to form a deep-level feature representation. The Gaussian kernel function was used to speed-up the convolution operations; also, the local structural feature information of the target was used to update the filters in every stage of the network; in addition, the tracking was realized by combining the particle filter tracking framework. The experimental results on the CVPR2013 tracking datasets show that the method used in this paper can help avoid the typically cumbersome operational environment of deep learning, overcome local object occlusion and deformation at low resolution, and improve tracking efficiency under a complex background.
In view of such defects existing in the depth learning tracking algorithm as lack of training samples, large time consumption, and high complexity, this paper proposed a simplified convolutional neural network tracking algorithm in which training is unnecessary. Moreover, the Gaussian kernel function can be applied to this algorithm to significantly lower the computing time. Firstly, the initial frame target was normalized and clustered to extract a series of initial filter banks; in the tracking process, the background information of the target and the candidate target for the foreground were convoluted; then the simple and abstract features of the target were extracted; finally, all the convolutions of a simple layer were superposed to form a deep-level feature representation. The Gaussian kernel function was used to speed-up the convolution operations; also, the local structural feature information of the target was used to update the filters in every stage of the network; in addition, the tracking was realized by combining the particle filter tracking framework. The experimental results on the CVPR2013 tracking datasets show that the method used in this paper can help avoid the typically cumbersome operational environment of deep learning, overcome local object occlusion and deformation at low resolution, and improve tracking efficiency under a complex background.
引文
[1]杨戈,刘宏.视觉跟踪算法综述[J].智能系统学报,2010,5(2):95–105.YANG Ge,LIU Hong.Survey of visual tracking algorithms[J].CAAI transactions on intelligent systems,2010,5(2):95–105.
[2]黄凯奇,陈晓棠,康运锋,等.智能视频监控技术综述[J].计算机学报,2015,38(6):1093–1118.HUANG Kaiqi,CHEN Xiaotang,KANG Yunfeng,et al.Intelligent visual surveillance:a review[J].Chinese journal of computers,2015,38(6):1093–1118.
[3]WU Yi,LIM J,YANG M H.Online object tracking:a benchmark[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.Portland,OR,USA,2013:2411-2418.
[4]BABENKO B,YANG M H,BELONGIE S.Robust object tracking with online multiple instance learning[J].IEEE transactions on pattern analysis and machine intelligence,2011,33(8):1619–1632.
[5]陈真,王钊.元认知粒子滤波目标跟踪算法[J].智能系统学报,2015,10(3):387–392.CHEN Zhen,WANG Zhao.Object tracking algorithm with metacognitive model-based particle filters[J].CAAI transactions on intelligent systems,2015,10(3):387–392.
[6]MEI Xue,LING Haibin.Robust visual tracking using?1minimization[C]//Proceedings of the 12th IEEE International Conference on Computer Vision.Kyoto,Japan,2009:1436-1443.
[7]ZHANG Kaihua,ZHANG Lei,YANG M H.Real-time compressive tracking[C]//Proceedings of the 12th European Conference on Computer Vision.Berlin,Germany,2012:864-877.
[8]韩华,丁永生,郝矿荣.综合颜色和小波纹理特征的免疫粒子滤波视觉跟踪[J].智能系统学报,2011,6(4):289–294.HAN Hua,DING Yongsheng,HAO Kuangrong.An immune particle filter video tracking method based on color and wavelet texture[J].CAAI transactions on intelligent systems,2011,6(4):289–294.
[9]RABINER L R.A tutorial on hidden Markov models and selected applications in speech recognition[J].Proceedings of the IEEE,1989,77(2):257–286.
[10]BAR-SHALOM Y,FORTMANN T E,CABLE P G.Tracking and data association[J].The journal of the acoustical society of America,1990,87(2):918–919.
[11]COMANICIU D,RAMESH V,MEER P.Real-time tracking of non-rigid objects using mean shift[C]//Proceedings of 2000 IEEE Conference on Computer Vision and Pattern Recognition.Hilton Head Island,SC,USA,2000:142-149.
[12]ISARD M,BLAKE A.CONDENSATION-conditional density propagation for visual tracking[J].International journal of computer vision,1998,29(1):5–28.
[13]BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition.San Francisco,CA,USA,2010:2544-2550.
[14]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Exploiting the circulant structure of tracking-by-detection with kernels[C]//Proceedings of the 12th European Conference on Computer Vision.Berlin,Germany,2012:702-715.
[15]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Highspeed tracking with kernelized correlation filters[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(3):583–596.
[16]余凯,贾磊,陈雨强,等.深度学习的昨天、今天和明天[J].计算机研究与发展,2013,50(9):1799–1804.YU Kai,JIA Lei,CHEN Yuqiang,et al.Deep learning:yesterday,today,and tomorrow[J].Journal of computer research and development,2013,50(9):1799–1804.
[17]WANG Naiyan,YEUNG D Y.Learning a deep compact image representation for visual tracking[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems.Lake Tahoe,USA,2013:809-817.
[18]ZHANG Kaihua,LIU Qingshan,WU Yi,et al.Robust visual tracking via convolutional networks without training[J].IEEE transactions on image processing,2016,25(4):1779–1792.
[19]NAM H,HAN B.Learning multi-domain convolutional neural networks for visual tracking[C]//Proceedings of2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,CA,USA,2016:4293-4302.
[20]ROSS D A,LIM J,LIN R S,et al.Incremental learning for robust visual tracking[J].International journal of computer vision,2008,77(1/2/3):125–141.
[21]WU Yi,LIM J,YANG M H.Object tracking benchmark[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(9):1834–1848.
[2]黄凯奇,陈晓棠,康运锋,等.智能视频监控技术综述[J].计算机学报,2015,38(6):1093–1118.HUANG Kaiqi,CHEN Xiaotang,KANG Yunfeng,et al.Intelligent visual surveillance:a review[J].Chinese journal of computers,2015,38(6):1093–1118.
[3]WU Yi,LIM J,YANG M H.Online object tracking:a benchmark[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.Portland,OR,USA,2013:2411-2418.
[4]BABENKO B,YANG M H,BELONGIE S.Robust object tracking with online multiple instance learning[J].IEEE transactions on pattern analysis and machine intelligence,2011,33(8):1619–1632.
[5]陈真,王钊.元认知粒子滤波目标跟踪算法[J].智能系统学报,2015,10(3):387–392.CHEN Zhen,WANG Zhao.Object tracking algorithm with metacognitive model-based particle filters[J].CAAI transactions on intelligent systems,2015,10(3):387–392.
[6]MEI Xue,LING Haibin.Robust visual tracking using?1minimization[C]//Proceedings of the 12th IEEE International Conference on Computer Vision.Kyoto,Japan,2009:1436-1443.
[7]ZHANG Kaihua,ZHANG Lei,YANG M H.Real-time compressive tracking[C]//Proceedings of the 12th European Conference on Computer Vision.Berlin,Germany,2012:864-877.
[8]韩华,丁永生,郝矿荣.综合颜色和小波纹理特征的免疫粒子滤波视觉跟踪[J].智能系统学报,2011,6(4):289–294.HAN Hua,DING Yongsheng,HAO Kuangrong.An immune particle filter video tracking method based on color and wavelet texture[J].CAAI transactions on intelligent systems,2011,6(4):289–294.
[9]RABINER L R.A tutorial on hidden Markov models and selected applications in speech recognition[J].Proceedings of the IEEE,1989,77(2):257–286.
[10]BAR-SHALOM Y,FORTMANN T E,CABLE P G.Tracking and data association[J].The journal of the acoustical society of America,1990,87(2):918–919.
[11]COMANICIU D,RAMESH V,MEER P.Real-time tracking of non-rigid objects using mean shift[C]//Proceedings of 2000 IEEE Conference on Computer Vision and Pattern Recognition.Hilton Head Island,SC,USA,2000:142-149.
[12]ISARD M,BLAKE A.CONDENSATION-conditional density propagation for visual tracking[J].International journal of computer vision,1998,29(1):5–28.
[13]BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition.San Francisco,CA,USA,2010:2544-2550.
[14]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Exploiting the circulant structure of tracking-by-detection with kernels[C]//Proceedings of the 12th European Conference on Computer Vision.Berlin,Germany,2012:702-715.
[15]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Highspeed tracking with kernelized correlation filters[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(3):583–596.
[16]余凯,贾磊,陈雨强,等.深度学习的昨天、今天和明天[J].计算机研究与发展,2013,50(9):1799–1804.YU Kai,JIA Lei,CHEN Yuqiang,et al.Deep learning:yesterday,today,and tomorrow[J].Journal of computer research and development,2013,50(9):1799–1804.
[17]WANG Naiyan,YEUNG D Y.Learning a deep compact image representation for visual tracking[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems.Lake Tahoe,USA,2013:809-817.
[18]ZHANG Kaihua,LIU Qingshan,WU Yi,et al.Robust visual tracking via convolutional networks without training[J].IEEE transactions on image processing,2016,25(4):1779–1792.
[19]NAM H,HAN B.Learning multi-domain convolutional neural networks for visual tracking[C]//Proceedings of2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,CA,USA,2016:4293-4302.
[20]ROSS D A,LIM J,LIN R S,et al.Incremental learning for robust visual tracking[J].International journal of computer vision,2008,77(1/2/3):125–141.
[21]WU Yi,LIM J,YANG M H.Object tracking benchmark[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(9):1834–1848.