动态视角下自主目标识别与跟踪
|
摘要
针对动态视角下由于相机高频率晃动导致的常用目标识别及跟踪算法准确率较低的问题,提出了一种基于Canny和GrabCut的自适应窗口式目标跟踪算法。首先使用加速稳健特征(SURF)算法学习图片库并记忆图片特征,设计基于SURF算法的记忆库目标识别算法;然后,对上述目标区域采用GrabCut的自适应优化算法进行感兴趣区域分割,实现目标粗略跟踪;最后,设计基于Canny算法的窗口式算法进行目标精确追踪。实验结果表明,所设计的算法能快速地识别目标、精确地勾勒出其轮廓并且稳定跟踪目标,相比其他算法,算法在实时性和精确性方面有显著提高。
Aiming at the low accuracy of common target recognition and tracking algorithms caused by camera high frequency sloshing under dynamic view, this paper proposes an adaptive window target tracking algorithm based on Canny and GrabCut. Firstly, the speeded up robust features(SURF) algorithm is used to learn the picture library and remember the picture features. The memory target recognition algorithm based on SURF algorithm is designed. Then, GrabCut adaptive optimization algorithm is used to segment the region of interest to achieve rough tracking of the target. Finally, a windowed algorithm based on Canny is achievedtoaccurately track the target. The experimental results show that the algorithm designed in this paper can quickly identify the target and accurately outline its contour. Moreover, the target can be stably tracked. Compared with other algorithms, the algorithm has obvious improvement in computation efficiency and accuracy.
Aiming at the low accuracy of common target recognition and tracking algorithms caused by camera high frequency sloshing under dynamic view, this paper proposes an adaptive window target tracking algorithm based on Canny and GrabCut. Firstly, the speeded up robust features(SURF) algorithm is used to learn the picture library and remember the picture features. The memory target recognition algorithm based on SURF algorithm is designed. Then, GrabCut adaptive optimization algorithm is used to segment the region of interest to achieve rough tracking of the target. Finally, a windowed algorithm based on Canny is achievedtoaccurately track the target. The experimental results show that the algorithm designed in this paper can quickly identify the target and accurately outline its contour. Moreover, the target can be stably tracked. Compared with other algorithms, the algorithm has obvious improvement in computation efficiency and accuracy.
引文
[1] 张慧,王坤峰,王飞跃.深度学习在目标视觉检测中的应用进展与展望[J].自动化学报,2017,43(8):1290-1304.ZHANG H,WANG K F,WANG F Y.Progress and prospect of application of deep learning in target vision detection[J].Acta Automatica Sinica,2017,43(8):1290-1304.
[2] 翟敬梅,刘坤.特征点辅助的时空上下文目标跟踪与定位[J].仪器仪表学报,2017,38(11):2840- 2841.ZHAI J M,LIU K.Feature-aided spatiotemporal context target tracking and location[J].Chinese Journal of Scientific Instrument,2017,38(11):2840- 2841.
[3] 周鑫,钱秋朦,叶永强,等.改进后的Tracking-Learning-Derection视频目标跟踪方法[J].中国图象图形学报,2013,18(9):1115-1120.ZHOU X,QIAN Q M,YE Y Q,et al.Improved tracking-learning-derection video target tracking method[J].Chinese Journal of Image and Graphics,2013,18(9):1115-1120.
[4] 王晶,宋策,杨立保.融合GrabCut的粒子滤波目标跟踪算法[J].仪器仪表学报,2014,35(S2):20- 27.WANG J,SONG C,YANG L B.Particle filter target tracking based on GrabCut[J].Chinese Journal of Scientific Instrument,2014,35(S2):20- 27.
[5] 郝志成.决策主导的多模式融合目标跟踪算法[J].仪器仪表学报,2013,34(3):487- 493.HAO ZH CH.Decision-oriented multi-mode fusion target tracking algorithm[J].Journal of Instruments and Instruments,2013,34(3):487- 493.
[6] NAM H,HAN B.Learning multi-domain convolutional neural networks for visual tracking[C].Conference on Computer Vision and Pattern Recognition,2016.
[7] 陈杏源,郑烈心,裴海龙.基于Camshift和Speeded Up Robust Features的目标跟踪系统[J].计算机工程与设计,2016,37(4):902-906.CHEN X Y,ZHENG L X,PEI H L.Target tracking system based on Camshift and speeded up robust features[J].Computer Engineering and Design,2016,37(4):902-906.
[8] SAM D B,SURYA S,BABU R V.Switching convolutional neural network for crowd counting[C].Conference on Computer Vision and Pattern Recognition,2017.
[9] 石祥滨,张健,代钦,等.采用显著性分割与目标检测的形变目标跟踪方法[J].计算机辅助设计与图形学学报,2016,28(4):644- 652.SHI X B,ZHANG J,DAI Q,et al.Deformation target tracking method using saliency segmentation and target detection [J].Journal of Computer Aided Design and Graphics,2016,28(4):644- 652.
[10] QI Y,ZHANG S,QIN L,et al.Hedged deep tracking[C].Conference on Computer Vision and Pattern Recognition,2016.
[11] 朱奇光,张朋珍,李昊立,等.基于全局和局部特征融合的图像匹配算法研究[J].仪器仪表学报,2016,37(1):171-172.ZHU Q G,ZHANG P ZH,LI H L,et al.Image matching algorithm based on global and local feature fusion [J].Chinese Journal of Scientific Instrument,2016,37(1):171-172.
[12] CHOI J,CHANG H J,JEONG J,et al.Visual tracking using attention-modulated disintegration and integration[C].Conference on Computer Vision and Pattern Recognition,2016.
[13] CHOI J,CHANG H J,YUN S,et al.Attentional correlation filter network for adaptive visual tracking[C].Conference on Computer Vision and Pattern Recognition,2017.
[14] HELD D,THRUN S,SAVARESE S.Learning to track at 100 fps with deep regression networks[C].European Conference on Computer Vision,2016.
[15] DU B,XIONG W,WU J,et al.Stacked convolutional denoising auto-encoders for feature representation[J].IEEE Transactions on Cybernetics,2017,47(4):1017-1027.
[16] AN N C,Lo Y K,LIN Y S.Recognition of novel Cdc7 kinase inhibitors as anti-cancer agents that target the interaction with Dbf4 by the fragment complementation and drug repositioning approach[J].EBiomedicine,2018(36):241- 245.
[17] SELVARAJ G,KALIAMURTHI S.Recognition of target gene and prognostic evaluation for lung adenocarcinoma using gene expression meta-analysis,network analysis and neural network algorithms[J].Journal of Biomedical Informatics,2018(86):120-123.
[18] ZHANG H Q,GE H W,YANG J L.Improved Gaussian mixture probability hypothesis density for tracking closely spaced targets[J].International Journal of Electronics and Telecommunications,2017,63(3):247- 250.
[19] CHATURVEDI A,SETHI N.Automatic license plate recognition system using SURF features and RBF neural network[J].International Journal of Computer Vision 2013,70(27):37- 41.
[20] WU Y,LIM J,YANG M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[21] OSEP A,MEHNER W,MATHIAS M,et al.Combined image-and world-space tracking in traffic scenes[C].IEEE International Conference on Robotics and Automation (ICRA),2017.
[22] HENRIQUES J F,MARTINS P,BATISTA J.Highspeed tracking with kernelized correlation filters[J].IEEE Transaction on PAMI,2015,37(3):583-596.
[23] HARE S,GOLODETZ S,SAFFARI A,et al.Struck:Structured output tracking with kernels[J].Institute of Electrical and Electronics Engineers Transaction on PAMI,2016,38(10):2096-2109.
[24] YUN K,LIM J,JIM Y C.Scene conditional background update for moving object detection in a moving camera[J].Pattern Recognition Letters,2017,88(1):57- 63.
[2] 翟敬梅,刘坤.特征点辅助的时空上下文目标跟踪与定位[J].仪器仪表学报,2017,38(11):2840- 2841.ZHAI J M,LIU K.Feature-aided spatiotemporal context target tracking and location[J].Chinese Journal of Scientific Instrument,2017,38(11):2840- 2841.
[3] 周鑫,钱秋朦,叶永强,等.改进后的Tracking-Learning-Derection视频目标跟踪方法[J].中国图象图形学报,2013,18(9):1115-1120.ZHOU X,QIAN Q M,YE Y Q,et al.Improved tracking-learning-derection video target tracking method[J].Chinese Journal of Image and Graphics,2013,18(9):1115-1120.
[4] 王晶,宋策,杨立保.融合GrabCut的粒子滤波目标跟踪算法[J].仪器仪表学报,2014,35(S2):20- 27.WANG J,SONG C,YANG L B.Particle filter target tracking based on GrabCut[J].Chinese Journal of Scientific Instrument,2014,35(S2):20- 27.
[5] 郝志成.决策主导的多模式融合目标跟踪算法[J].仪器仪表学报,2013,34(3):487- 493.HAO ZH CH.Decision-oriented multi-mode fusion target tracking algorithm[J].Journal of Instruments and Instruments,2013,34(3):487- 493.
[6] NAM H,HAN B.Learning multi-domain convolutional neural networks for visual tracking[C].Conference on Computer Vision and Pattern Recognition,2016.
[7] 陈杏源,郑烈心,裴海龙.基于Camshift和Speeded Up Robust Features的目标跟踪系统[J].计算机工程与设计,2016,37(4):902-906.CHEN X Y,ZHENG L X,PEI H L.Target tracking system based on Camshift and speeded up robust features[J].Computer Engineering and Design,2016,37(4):902-906.
[8] SAM D B,SURYA S,BABU R V.Switching convolutional neural network for crowd counting[C].Conference on Computer Vision and Pattern Recognition,2017.
[9] 石祥滨,张健,代钦,等.采用显著性分割与目标检测的形变目标跟踪方法[J].计算机辅助设计与图形学学报,2016,28(4):644- 652.SHI X B,ZHANG J,DAI Q,et al.Deformation target tracking method using saliency segmentation and target detection [J].Journal of Computer Aided Design and Graphics,2016,28(4):644- 652.
[10] QI Y,ZHANG S,QIN L,et al.Hedged deep tracking[C].Conference on Computer Vision and Pattern Recognition,2016.
[11] 朱奇光,张朋珍,李昊立,等.基于全局和局部特征融合的图像匹配算法研究[J].仪器仪表学报,2016,37(1):171-172.ZHU Q G,ZHANG P ZH,LI H L,et al.Image matching algorithm based on global and local feature fusion [J].Chinese Journal of Scientific Instrument,2016,37(1):171-172.
[12] CHOI J,CHANG H J,JEONG J,et al.Visual tracking using attention-modulated disintegration and integration[C].Conference on Computer Vision and Pattern Recognition,2016.
[13] CHOI J,CHANG H J,YUN S,et al.Attentional correlation filter network for adaptive visual tracking[C].Conference on Computer Vision and Pattern Recognition,2017.
[14] HELD D,THRUN S,SAVARESE S.Learning to track at 100 fps with deep regression networks[C].European Conference on Computer Vision,2016.
[15] DU B,XIONG W,WU J,et al.Stacked convolutional denoising auto-encoders for feature representation[J].IEEE Transactions on Cybernetics,2017,47(4):1017-1027.
[16] AN N C,Lo Y K,LIN Y S.Recognition of novel Cdc7 kinase inhibitors as anti-cancer agents that target the interaction with Dbf4 by the fragment complementation and drug repositioning approach[J].EBiomedicine,2018(36):241- 245.
[17] SELVARAJ G,KALIAMURTHI S.Recognition of target gene and prognostic evaluation for lung adenocarcinoma using gene expression meta-analysis,network analysis and neural network algorithms[J].Journal of Biomedical Informatics,2018(86):120-123.
[18] ZHANG H Q,GE H W,YANG J L.Improved Gaussian mixture probability hypothesis density for tracking closely spaced targets[J].International Journal of Electronics and Telecommunications,2017,63(3):247- 250.
[19] CHATURVEDI A,SETHI N.Automatic license plate recognition system using SURF features and RBF neural network[J].International Journal of Computer Vision 2013,70(27):37- 41.
[20] WU Y,LIM J,YANG M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[21] OSEP A,MEHNER W,MATHIAS M,et al.Combined image-and world-space tracking in traffic scenes[C].IEEE International Conference on Robotics and Automation (ICRA),2017.
[22] HENRIQUES J F,MARTINS P,BATISTA J.Highspeed tracking with kernelized correlation filters[J].IEEE Transaction on PAMI,2015,37(3):583-596.
[23] HARE S,GOLODETZ S,SAFFARI A,et al.Struck:Structured output tracking with kernels[J].Institute of Electrical and Electronics Engineers Transaction on PAMI,2016,38(10):2096-2109.
[24] YUN K,LIM J,JIM Y C.Scene conditional background update for moving object detection in a moving camera[J].Pattern Recognition Letters,2017,88(1):57- 63.