[1]黄 鹤,陈永安,张少帅,等.融入运动信息和模型自适应的相关滤波跟踪[J].机械与电子,2021,(01):3-07.
　HUANG He,CHEN Yongan,ZHANG Shaoshuai,et al.Correlation Filter Tracking Incorporating Motion Information and Model Adaptive[J].Machinery & Electronics,2021,(01):3-07.
点击复制

融入运动信息和模型自适应的相关滤波跟踪()
分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2021年01期
页码:
3-07
栏目:
设计与研究
出版日期:
2021-01-20

文章信息/Info

Title:
Correlation Filter Tracking Incorporating Motion Information and Model Adaptive
文章编号:
1001-2257(2021)01-0003-05
作者:
黄 鹤1; 陈永安1; 张少帅1; 茹 锋1; 王会峰1; 郭 璐2
1.长安大学电子与控制工程学院,陕西 西安 710064;
2.无人机系统国家工程研究中心,陕西 西安 710072
Author(s):
HUANG He1;  CHEN Yong’an1;  ZHANG Shaoshuai1;  RU Feng1;  WANG Huifeng1; GUO Lu2
1.School of electronics and control engineering, Chang’an University, Xi’an 710064, China;
2. UAV System National Engineering Research Center, Xi’an  710072,China
关键词:
余弦窗; 遮挡; 相关滤波; 目标跟踪; 卡尔曼滤波
Keywords:
cosine window;  occlusion;  correlation filtering;  target tracking;  Kalman filtering
分类号:
TP391.41
文献标志码:
A
摘要:
为解决余弦窗的影响和复杂场景中的目标遮挡问题，提出了一种融入运动信息和模型自适应的相关滤波跟踪算法。采用HOG特征和颜色直方图特征互补结合的框架，引入卡尔曼滤波和上下文感知滤波器，可以解决余弦窗的影响；引入一种高置信度检测方法和一种新的模型自适应更新方法，可以解决目标遮挡的问题。将提出的算法在OTB-2015测试集与其他6种相关滤波类算法进行比较，实验结果表明，该算法精确度和成功率分别为0.821和0.615。相对于Staple-CA算法，精确度提升了1.3%，成功率提升了2.8%，同时，算法速度为54.34 帧/s，满足实际工程实时性要求。
Abstract:
In order to solve the problem of cosine window influence and target occlusion in complex scenes, a correlation filtering tracking algorithm incorporating motion information and model adaptation is proposed. Adopting the framework of complementary combination of HOG features and color histogram features, introducing Kalman filter and context-aware filter, can solve the influence of cosine window; introducing a high-confidence detection method and a new model adaptive update method, Solve the problem of target occlusion. The proposed algorithm is compared with other 6 related filtering algorithms in the OTB-2015 test set. Experimental results show that the accuracy and success rate of the algorithm are 0.821 and 0.615, respectively. Compared with the Staple-CA algorithm, the accuracy has increased by 1.3%, the success rate has increased by 2.8%, At the same time, the algorithm speed is 54.34 frames/s, which meets the real-time requirements of actual engineering.

参考文献/References:

[1] 孟琭, 杨旭. 目标跟踪算法综述[J]. 自动化学报, 2019, 45(7): 1244-1260.
[2] 刘波, 许廷发, 李相民, 等. 自适应上下文感知相关滤波跟踪[J]. 中国光学, 2019, 12(2): 265-273.
[3] 江山, 张锐, 韩广良, 等. 复杂背景灰度图像下的多特征融合运动目标跟踪[J]. 中国光学, 2016, 9(3): 320-328.
[4] WU Y, LIM J, YANG M-H, et al.: Online object tracking: a benchmark[C]//Proceedings of the  2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013: 2411-2418.
[5] DANELLJIAN M, HAGER G, KHAN F, et al. Accurate scale estimation for robust visual tracking[C]//Proceedimgs of the British Machine Vision Conference, 2014: 1551-1562.
[6] BOLME D S, BEVEERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[C]// 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010: 2544-2550.
[7] HENRIQUES J F, CASEIRO R, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]// European Conference on Computer Vision, 2012: 702-715.

[8] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on pattern analysis and machine intelligence, 2009, 32(9): 1627-1645.

[9] 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, 2014, 37(3): 583-596.

[10] DANELLJAN M, HÄGER G, KHAN F S, et al. Discriminative scale space tracking[J]. IEEE Transactions on pattern analysis and machine intelligence, 2016, 39(8): 1561-1575.

[11] DANELLJAN M, HAGER G, KHAN F S, et al.: Learning spatially regularized correlation filters for  visual tracking[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 4310-4318.

[12] BERTINETTO L, VALMADRE J, GOLODETZ S, et al. Staple: complementary learners for real-time tracking[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 1401-1409.

[13] POSSEGGER H, MAUTHNER T, BISCHOF H, et al.: In Defense of Color-based Model-free Tracking[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 2113-2120.

[14] MUELLER M, SMITH N, GHANEM B. Context-aware correlation filter tracking[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1396-1404.

[15] WANG M, LIU Y, HUANG Z. Large margin object tracking with circulant feature maps[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4021-4029.

[16] LI Y, ZHU J. A scale adaptive kernel correlation filter tracker with feature integration[C]// European Conference on Computer Vision, 2014: 254-265.

[17] WU Y, LIM J, YANG M H. Object tracking benchmark[J]. IEEE Transactions on pattern analysis and machine intelligence, 2015, 37(9): 1834-1848

备注/Memo

备注/Memo:
 收稿日期：2020-07-22
基金项目：国家重点研发计划项目(No.2018YFB1600600)；中央高校基本科研业务费专项项目(300102329501)资助项目
作者简介：黄 鹤 (1979—)，男，河南南阳人，博士，副教授，研究方向为控制科学与工程；陈永安 (1994—)，男，河南平顶山人，硕士研究生，研究方向为图像处理、目标跟踪等。
更新日期/Last Update: 2020-12-25