|
|
基于LOG算子和多特征融合的改进型KCF目标追踪算法研究
|
Abstract:
针对在跟踪目标受到严重遮挡或者尺度变化显著等复杂场景下原始核相关滤波算法(Kernel Correlati-on Filter, KCF)追踪目标失败的问题，本文提出了一种将边缘检测算子(Edge Detection Operator, EDO)、多特征融合、尺度自适应相结合的改进型KCF目标追踪算法。首先，通过引进高斯拉普拉斯算子(Laplacian of Gaussian, LOG)，对初始帧图像进行处理以获取更多边缘信息。其次，将颜色特征(Color Naming, CN)与方向梯度直方图(Histogram of Gradient, HOG)进行线性融合，可以在处理目标被遮挡时获取更多目标图像的多特征信息。然后，通过使用尺度池自适应方法解决跟踪目标时尺度变化问题。最后，使用OTB-100数据集进行算法仿真和效果评估，证明了使用本文提出的改进型KCF目标追踪算法在复杂背景下依然具有较好的准确性和鲁棒性。
In this paper, an enhanced KCF target tracking algorithm is proposed to address the limitations of the original Kernel Correlation Filter (KCF) in tracking targets under complex scenarios with significant scale changes or severe occlusion. The proposed algorithm integrates Edge Detection Operator (EDO), multi-feature fusion, and scale adaptation. Firstly, Laplacian of Gaussian (LOG) is introduced to process the initial frame image for obtaining more edge information. Secondly, a linear fusion of Color Naming (CN) and Histogram of Gradient (HOG) enhances multi-feature information extraction when the target is obstructed. Furthermore, the scale change issue is addressed using a scale pool adaptive method. Finally, simulation and evaluation on OTB-100 dataset demonstrate that the improved KCF target tracking algorithm maintains high accuracy and robustness in complex backgrounds.
| [1] | 闫虓堃, 刘天波. 尺度自适应与抗遮挡的KCF方法研究[J]. 数据挖掘, 2023, 13(2): 135-142. |
| [2] | 王鑫瑞. 目标跟踪算法研究综述[J]. 信息通信, 2020(4): 42-43+46. |
| [3] | 孟晓燕, 段建民. 基于相关滤波的目标跟踪算法研究综述[J]. 北京工业大学学报, 2020, 46(12): 1393-1416. |
| [4] | 汤一明, 刘玉菲, 黄鸿. 视觉单目标跟踪算法综述[J]. 测控技术, 2020, 39(8): 21-34. |
| [5] | 谢郭蓉, 曲毅, 蒋镕圻. 基于抗遮挡目标模型的跟踪算法综述[J]. 激光与光电子学进展, 2022, 59(8): 325-338. |
| [6] | 孟琭, 杨旭. 目标跟踪算法综述[J]. 自动化学报, 2019, 45(7): 1244-1260. |
| [7] | 卢湖川, 李佩霞, 王栋. 目标跟踪算法综述[J]. 模式识别与人工智能, 2018, 31(1): 61-76. |
| [8] | 戴广军, 张乐, 李亚霖, 等. 滤波算法在图像跟踪中的应用综述[J]. 电脑知识与技术, 2016, 12(23): 151-152. |
| [9] | Henriques, J.F., Caseiro, R., Martins, P. and Batista, J. (2015) High-Speed Tracking with Kernelized Correlation Filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 583-596. https://doi.org/10.1109/tpami.2014.2345390 |
| [10] | Dalal, N. and Triggs, B. (2005) Histograms of Oriented Gradients for Human Detection. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, 20-26 June 2005, 886-893. https://doi.org/10.1109/cvpr.2005.177 |
| [11] | Cai, C., Liang, X., Wang, B., Cui, Y. and Yan, Y. (2018) A Target Tracking Method Based on KCF for Omnidirectional Vision. 2018 37th Chinese Control Conference (CCC), Wuhan, 25-27 July 2018, 962-967. https://doi.org/10.23919/chicc.2018.8483083 |
| [12] | Ong, L., Lau, S. and Koo, V. (2017) Performance of Invariant Feature Descriptors with Adaptive Prediction in Occlusion Handling. 2017 3rd International Conference on Control, Automation and Robotics (ICCAR), Nagoya, 22-24 April 2017, 385-388. https://doi.org/10.1109/iccar.2017.7942723 |
| [13] | Mirunalini, P., Jaisakthi, S.M. and Sujana, R. (2017) Tracking of Object in Occluded and Non-Occluded Environment Using SIFT and Kalman Filter. TENCON 2017-2017 IEEE Region 10 Conference, Penang, 5-8 November 2017, 1290-1295. https://doi.org/10.1109/tencon.2017.8228056 |
| [14] | 刘建芳, 李成建. 基于YOLO和KCF的目标跟踪算法研究[J]. 计算机科学与应用, 2020, 10(6): 1113-1121. |
| [15] | 孙静, 刘凌, 亢春燕, 等. 基于尺度自适应和遮挡重定位机制的KCF改进算法[J]. 机械设计与制造工程, 2023, 52(5): 107-111. |
| [16] | 王玲, 马胜楠, 王鹏. 自适应多策略融合快速KCF跟踪算法[J]. 计算机应用与软件, 2023, 40(5): 207-213. |
| [17] | 陈志旺, 刘旺. 特征融合和自校正的多尺度改进KCF目标跟踪算法研究[J]. 高技术通讯, 2022, 32(4): 337-350. |
| [18] | 郭勇, 赖广. 基于遮挡判断的自适应更新相关滤波跟踪算法[J]. 电光与控制, 2021, 28(12): 57-60. |
| [19] | Li, P., Shi, T., Lu, A. and Wang, B. (2020) Quantum Implementation of Classical Marr-Hildreth Edge Detection. Quantum Information Processing, 19, Article No. 64. https://doi.org/10.1007/s11128-019-2559-0 |
| [20] | Li, Y. and Zhu, J. (2015) A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration. Computer Vision—ECCV 2014, Zurich, 6-7 and 12 September 2014, 254-265. https://doi.org/10.1007/978-3-319-16181-5_18 |
| [21] | Shi, H., Hou, J., Li, H., Yi, J., Hu, J. and Tian, Y. (2021) Target Tracking Algorithm Based on Improved Kernel Correlation Filtering. 2021 China Automation Congress (CAC), Beijing, 22-24 October 2021, 516-521. https://doi.org/10.1109/cac53003.2021.9728622 |
| [22] | 肖扬, 周军. 图像边缘检测综述[J]. 计算机工程与应用, 2023, 59(5): 40-54. |
| [23] | 吴琼, 马雷. 一种基于LOG算子的量子图像边缘检测算法[J]. 量子电子学报, 2022, 39(5): 720-727. |
| [24] | Danelljan, M., Khan, F.S., Felsberg, M. and Van De Weijer, J. (2014) Adaptive Color Attributes for Real-Time Visual Tracking. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 1090-1097. https://doi.org/10.1109/cvpr.2014.143 |
