深度残差特征与熵能量优化运动目标跟踪算法

doi:10.6040/j.issn.1672-3961.0.2018.461

摘要/Abstract

摘要：

针对模型更新的运动目标跟踪算法准确率、实时性和鲁棒性较低的问题,提出一种基于深度残差特征与熵能量优化的运动目标跟踪算法。通过深度残差网络从视频序列中提取深度残差特征,计算深度残差特征的熵能量,并通过二维核变换计算深度频率。由微分方程从深度频率中计算出深度平衡,通过极大似然估计出目标位置和速度等状态信息,完成对运动目标的跟踪。为了验证算法的可行性与有效性,在目标跟踪基准数据集(object tracking basis, OTB)上进行算法对比试验,验证各个算法在运动目标跟踪上的准确性和鲁棒性。试验结果表明,该研究提出的算法比当前最佳算法在运动目标跟踪的速度和位置准确性上都有显著的提升,通过深度残差特征的熵能量优化,使运动目标跟踪算法具有更好的灵活性和鲁棒性。

关键词: 深度残差网络, 熵能量, 深度残差特征, 极大似然估计, 运动目标跟踪

Abstract:

To solve the low rate of accuracy, real-time and robustness of object tracking algorithm based on model updating, a new algorithm based on deep residual features and entropy energy optimization was proposed. Deep residual features were first extracted from original video sequence by deep residual network. The entropy energy from deep residual features were calculated, and the deep frequency from entropy energy by two-dimension kernel transformation could be calculated, after that we got the deep balance by deep frequency with differential equation, and then the object state by MLE was estimated, including object position and speed. To validate the feasibility and efficiency of the proposed algorithm, the comparing experiments on the object tracking basis (OTB) dataset for the state-of-the-art algorithms were done, and the comparison results showed that the proposed algorithm had significant improvement on tracking accuracy and robustness. By using entropy energy optimization for deep residual features, the proposed algorithm had more flexibility and robustness for object tracking.

Key words: deep residual network, entropy energy, deep residual features, maximum likelihood estimation, object tracking

中图分类号:

TP391

黄劲潮. 深度残差特征与熵能量优化运动目标跟踪算法[J]. 山东大学学报 (工学版), 2019, 49(4): 14-23.

Jinchao HUANG. Object tracking algorithm based on deep residual features and entropy energy optimization[J]. Journal of Shandong University(Engineering Science), 2019, 49(4): 14-23.

图/表 8

图1

图2

图3

图4

图5

图6

图7

图8

参考文献 26

1	魏全禄, 老松杨, 白亮. 基于相关滤波器的视觉目标跟踪综述[J]. 计算机科学, 2016, 43 (11): 1- 5, 18. doi: 10.11896/j.issn.1002-137X.2016.11.001
	WEI Quanlu , LAO Songyang , BAI Liang . Visual object tracking based on correlation filters: a survey[J]. Journal of Computer Science, 2016, 43 (11): 1- 5, 18. doi: 10.11896/j.issn.1002-137X.2016.11.001
2	包加桐, 宋爱国, 唐鸿儒, 等. 基于视觉目标跟踪的侦察机器人导航方法[J]. 东南大学学报(自然科学版), 2012, 42 (3): 399- 405.
	BAO Jiangtong , SONG Aiguo , TANG Hongru , et al. Navigation method for reconnaissance robot based on vision object tracking[J]. Journal of Southeast University (Natural science edition), 2012, 42 (3): 399- 405.
3	张微, 康宝生. 相关滤波目标跟踪进展综述[J]. 中国图象图形学报, 2017, 22 (8): 1017- 1033.
	ZHANG Wei , KANG Baosheng . Recent advances in correlation filter-based object tracking: a review[J]. Journal of Image and Graphics, 2017, 22 (8): 1017- 1033.
4	COOKE J R H , TER HORST A C , VAN Beers R J , et al. Effect of depth information on multiple-object tracking in three dimensions: a probabilistic perspective[J]. PLoS Computational Biology, 2017, 13 (7): 100- 109.
5	ONATE J M B , CHIPANTASI D J M , ERAZO N R V . Tracking objects using artificial neural networks and wireless connection for robotics[J]. Journal of Telecommunication, Electronic and Computer engineering (JTEC), 2017, 9 (1/2/3): 161- 164.
6	冯桂兰, 田维坚, 黄昌清, 等. 基于序贯蒙特卡罗的多线索目标跟踪算法[J]. 光电工程, 2010, 37 (8): 5- 11. doi: 10.3969/j.issn.1003-501X.2010.08.002
	FENG Guilan , TIAN Weijian , HUANG Changqing , et al. Object tracking algorithm based on multi-cue and sequential Monte Carlo[J]. Opto-Electronic Engineering, 2010, 37 (8): 5- 11. doi: 10.3969/j.issn.1003-501X.2010.08.002
7	梁顺健, 汪俊彬, 邬依林. 基于模糊算法的多移动机器人目标跟踪[J]. 自动化与仪表, 2014, 29 (2): 5- 7, 37. doi: 10.3969/j.issn.1001-9944.2014.02.002
	LIANG Shunjian , WANG Junbin , WU Yilin . Fuzzy algorithm of target tracking control for multiple mobile robots[J]. Automation and Instrumentation, 2014, 29 (2): 5- 7, 37. doi: 10.3969/j.issn.1001-9944.2014.02.002
8	刘文强, 刘志刚, 耿肖, 等. 基于均值漂移和粒子滤波算法的接触网几何参数检测方法研究[J]. 铁道学报, 2015, 37 (11): 30- 36. doi: 10.3969/j.issn.1001-8360.2015.11.005
	LIU Wenqiang , LIU Zhigang , GENG Xiao , et al. Research on detection method for geometrical parameters of catenary system based on mean shift and particle filter algorithm[J]. Journal of the China Railway Society, 2015, 37 (11): 30- 36. doi: 10.3969/j.issn.1001-8360.2015.11.005
9	JIA C, WANG Z, WU X, et al. A tracking-learning-detection (TLD) method with local binary pattern improved[C]//IEEE International Conference on Robotics and Biomimetics (ROBIO). Waterloo, Canada: IEEE, 2015: 1625-1630.
10	YAO R , SHI Q , SHEN C , et al. Part-based robust tracking using online latent structured learning[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27 (6): 1235- 1248. doi: 10.1109/TCSVT.2016.2527358
11	BIN OMRAN S , KOMEV I A , BELLAICHE L . Wang-Landau Monte Carlo formalism applied to ferroelectrics[J]. Physical Review b, 2016, 93 (1): 141- 148.
12	刘磊. 基于改进卷积神经网络的在线视觉目标跟踪方法[J]. 内蒙古师范大学学报(自然科学汉文版), 2017, 46 (6): 878- 883. doi: 10.3969/j.issn.1001-8735.2017.06.026
	LIU Lei . Online visual target tracking method based on improved convolution neural network[J]. Journal of Inner Mongolia Normal University(Natural Science Chinese Edition), 2017, 46 (6): 878- 883. doi: 10.3969/j.issn.1001-8735.2017.06.026
13	LECUN Y , BENGIO Y , HINTON G . Deep learning[J]. Nature, 2015, 521 (53): 436- 438.
14	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. New York: IEEE, 2016: 770-778.
15	张冬妍, 李佳佳, 宋现铭. 基于二维熵和粒子群优化的红外检测与跟踪[J]. 计算机工程与设计, 2017, 38 (5): 1296- 1300.
	ZHANG Dongyan , LI Jiajia , SONG Xianming . Infrared detection and tracking based on two-dimensional entropy and particle swarm optimization[J]. Computer Engineering and Design, 2017, 38 (5): 1296- 1300.
16	郭学卫, 申永军, 杨绍普. 基于样本熵和分数阶傅里叶变换的滚动轴承故障特征提取[J]. 振动与冲击, 2017, 36 (18): 65- 69.
	GUO Xuewei , SHEN Yongjun , YANG Shaopu . Application of sample entropy and Fractional fourier transform in the fault diagnosis of rolling bearings[J]. Journal of Vibration and Shock, 2017, 36 (18): 65- 69.
17	FIGUEROA A , LOPEZ J , CASTANOS O , et al. Entropy energy inequalities for qudit states[J]. Journal of Physics a: Mathematical and Theoretical, 2015, 48 (6): 653- 659.
18	HENRIQUES J F , CASEIRO R , MARTINS P , et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37 (3): 583- 596. doi: 10.1109/TPAMI.2014.2345390
19	DANELLJAN M, HAGER G, KHAN F, et al. Accurate scale estimation for robust visual tracking[C]//British Machine Vision Conference. Nottingham, UK: BMVA Press, 2014: 141-144.
20	DANELLJAN M, HAGER G, SHAHBAZ KHAN F, et al. Learning spatially regularized correlation filters for visual tracking[C]//Proceedings of the IEEE International Conference on Computer Vision. Los Angles: IEEE, 2015: 4310-4318.
21	ZHANG J, MA S, SCLAROFF S. MEEM: robust tracking via multiple experts using entropy minimization[C]//European Conference on Computer Vision. Zurich: Springer, 2014: 188-203.
22	HARE S, SAFFARI A, STRUCK P H S T. Structured output tracking with kernels[C]//IEEE International Conference on Computer Vision. Sydney: IEEE, 2012: 263-270.
23	JIA X, LU H, YANG M H. Visual tracking via adaptive structural local sparse appearance model[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2012: 1822-1829.
24	ZHONG W, LU H, YANG M H. Robust object tracking via sparsity-based collaborative model[C]//2012 IEEE Conference on Computer vision and pattern recognition. San Diego: IEEE, 2012: 1838-1845.
25	BAO C, WU Y, LING H, et al. Real time robust l1 tracker using accelerated proximal gradient approach[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2012: 1830-1837.
26	ZHANG K, ZHANG L, YANG M H. Real-time compressive tracking[C]//European Conference on Computer Vision. Heidelberg: Springer, 2012: 864-877.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

[1]	汪嘉晨,唐向红,陆见光. 轴承故障诊断中特征选取技术[J]. 山东大学学报 (工学版), 2019, 49(2): 80-87, 95.
[2]	张红斌,邱蝶蝶,邬任重,朱涛,滑瑾,姬东鸿. 基于极端梯度提升树算法的图像属性标注[J]. 山东大学学报 (工学版), 2019, 49(2): 8-16.
[3]	侯霄雄,许新征,朱炯,郭燕燕. 基于AlexNet和集成分类器的乳腺癌计算机辅助诊断方法[J]. 山东大学学报 (工学版), 2019, 49(2): 74-79.
[4]	杨煦,陈辉,林游思,屠长河. 飞行蝙蝠标记自动提取与追踪算法[J]. 山东大学学报 (工学版), 2019, 49(2): 67-73.
[5]	向润,陈素芬,曾雪强. 基于多重多元回归的人脸年龄估计[J]. 山东大学学报 (工学版), 2019, 49(2): 54-60.
[6]	胡云,张舒,李慧,佘侃侃,施珺. 基于信任网络重构的推荐算法[J]. 山东大学学报 (工学版), 2019, 49(2): 42-46.
[7]	高明霞,李经纬. 基于word2vec词模型的中文短文本分类方法[J]. 山东大学学报 (工学版), 2019, 49(2): 34-41.
[8]	李童,马然,郑鸿鹤,安平,胡翔宇. 基于视频统计特征的差错敏感度模型[J]. 山东大学学报 (工学版), 2019, 49(2): 116-121.
[9]	秦军,张远鹏,蒋亦樟,杭文龙. 多代表点自约束的模糊迁移聚类[J]. 山东大学学报 (工学版), 2019, 49(2): 107-115.
[10]	李力钊,蔡国永,潘角. 基于C-GRU的微博谣言事件检测方法[J]. 山东大学学报 (工学版), 2019, 49(2): 102-106, 115.
[11]	刘世光,王海荣,刘锦. 快速四点一致性点云粗配准算法[J]. 山东大学学报 (工学版), 2019, 49(2): 1-7.
[12]	钱春琳,张兴芳,孙丽华. 基于在线评论情感分析的改进协同过滤推荐模型[J]. 山东大学学报 (工学版), 2019, 49(1): 47-54.
[13]	周荣翔,贾修一. 中文反语识别特征分析[J]. 山东大学学报 (工学版), 2019, 49(1): 41-46.
[14]	杨思,李思童,张进东,白羽. 高速光通信激光器带宽模型改进与并行计算优化[J]. 山东大学学报 (工学版), 2019, 49(1): 17-22, 29.
[15]	范君,业巧林,业宁. 基于改进的有监督无参局部保持投影算法的人脸识别[J]. 山东大学学报 (工学版), 2019, 49(1): 10-16.