MFOPA Tracker with Dynamic Adaptive Feature Fusion

HUANG He; LI Wen-long; WU Kun; YANG Lan; WANG Hui-feng; WANG Ping

doi:10.12263/DZXB.20220874

您当前的位置：

首页 >

文章列表页 >

MFOPA Tracker with Dynamic Adaptive Feature Fusion

PAPERS | 更新时间：2025-12-08

- MFOPA Tracker with Dynamic Adaptive Feature Fusion
- ACTA ELECTRONICA SINICA Vol. 51, Issue 5, Pages: 1350-1358(2023)
- 作者机构：
  
  1.长安大学电子与控制工程学院,陕西西安 710064
  2.长安大学信息工程学院,陕西西安 710064
  3.西安市智慧高速公路信息融合与控制重点实验室,陕西西安 710064
  4.中山大学智能工程学院,广东深圳 518107
- 作者简介：
- 基金信息：
  
  Foundation Item(s):　National Key Research and Development Program(2021YFB2501200);General Program of the National Natural Science Foundation of China(52172379;52172324);Key Research and Development Program of Shaanxi Province(2021SF-483);Postdoctoral Scientific Research Project of Shaanxi Province(2018BSHYDZZ64);Xi'an Intelligent Highway Information Fusion and Control Key Laboratory (Chang'an University) Open Fund Project(300102321502);Central Universities Basic Research Funding Projects(300102240203)
- DOI：10.12263/DZXB.20220874
  CLC： TP301.6
- Received：22 July 2022，
  
  Revised：2022-10-31，
  
  Published：25 May 2023
- 稿件说明：
移动端阅览
黄鹤,李文龙,吴琨等.动态自适应特征融合的MFOPA跟踪器[J].电子学报,2023,51(05):1350-1358.

HUANG He,LI Wen-long,WU Kun,et al.MFOPA Tracker with Dynamic Adaptive Feature Fusion[J].ACTA ELECTRONICA SINICA,2023,51(05):1350-1358.
黄鹤,李文龙,吴琨等.动态自适应特征融合的MFOPA跟踪器[J].电子学报,2023,51(05):1350-1358. DOI： 10.12263/DZXB.20220874.

HUANG He,LI Wen-long,WU Kun,et al.MFOPA Tracker with Dynamic Adaptive Feature Fusion[J].ACTA ELECTRONICA SINICA,2023,51(05):1350-1358. DOI： 10.12263/DZXB.20220874.

摘要

本文针对无人机航拍跟踪算法实时性差且易发生跟踪漂移的问题，提出了一种动态自适应特征融合的改进飞蛾扑火优化跟踪器.本文设计了一种基于趋光-聚集度飞蛾扑火优化算法的目标跟踪框架，采用高斯分布和趋光-聚集度改进飞蛾扑火算法的初始化和迭代方式，将改进后的飞蛾扑火算法作为搜索策略优化目标跟踪，提升了跟踪效率；同时，在趋光-聚集度飞蛾扑火优化算法跟踪框架的基础上，本文定义了一种自适应多特征融合的模板和选择了一种动态更新的模板策略，充分利用颜色名特征、融合方向梯度直方图特征及灰度特征各自的优势，消除复杂环境中无人机跟踪受到的干扰，并解决在遮挡等情况下学习到无效的背景信息而导致特征模板退化的问题.实验结果表明，本文提出的算法在复杂环境场景下能够适应不同情况下环境的变化，平均跟踪精度达到87%，保持稳定跟踪，跟踪速度为31.6帧/s，满足实时性要求，大幅提升了跟踪器的精度和鲁棒性.

Abstract

Aiming at the problem of poor real-time and tracking drift of unmanned aerial vehicle (UAV) aerial tracking algorithm

this paper proposes an improved moth-flame optimization (MFO) tracker based on dynamic adaptive feature fusion. This paper designs a target tracking framework based on moth-flame optimization with phototaxis-aggregation degree (MFOPA). The initialization and iteration methods of MFO are improved by Gaussian distribution and phototaxis-aggregation degree. The improved moth-flame algorithm is used as a search strategy to optimize target tracking

which improves tracking efficiency. At the same time

based on the tracking framework of MFOPA

this paper defines an adaptive multi-feature fusion template and selects a dynamical update template strategy

which makes full use of the advantages of color name feature

fused histogram of oriented gradient feature and gray feature to eliminate the interference of UAV tracking in complex environment

and solve the problem of feature template degradation caused by learning invalid background information in the case of occlusion. The experimental results show that the algorithm proposed in this paper can adapt to the changes of the environment under different conditions in complex scenarios

the average tracking accuracy reaches 87%

and the tracking speed is 31.6 frame/s

which meets the real-time requirements and greatly improves the accuracy and robustness of the tracker.

关键词

Keywords

references

孟琭 , 杨旭 . 目标跟踪算法综述 [J]. 自动化学报 , 2019 , 45 ( 7 ): 1244 - 1260 .

MENG Lu , YANG Xu . A survey of object tracking algorithms [J]. Acta Automatica Sinica , 2019 , 45 ( 7 ): 1244 - 1260 . (in Chinese)

RISTAN M , MATAS J , LEONARDIS A , et al . A novel performance evaluation methodology for single-target trackers [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2016 , 38 ( 11 ): 2137 - 2155 .

李康 , 李亚敏 , 胡学敏 , 等 . 基于卷积神经网络的鲁棒高精度目标跟踪算法 [J]. 电子学报 , 2018 , 46 ( 9 ): 2087 - 2093 .

LI Kang , LI Ya-min , HU Xue-min , et al . A robust and accurate object tracking algorithm based on convolutional neural network [J]. Acta Electronica Sinica , 2018 , 46 ( 9 ): 2087 - 2093 . (in Chinese)

DANELLJAN M , HAGER G , KHAN F S , et al . Discriminative scale space tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2016 , 39 ( 8 ): 1561 - 1575 .

HENRIQUES J F , CASEIRO R , MARTINS P , et al . Exploiting the circulant structure of tracking-by-detection with kernels [C]// Computer Vision — ECCV 2012 . Heidelberg : Springer , 2012 : 702 - 715 .

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 .

BERTINETTO L , VALMADRE J , HENRIQUES J F , et al . Fully-convolutional Siamese networks for object tracking [C]// Computer Vision — ECCV 2016 Workshops . Cham : Springer , 2016 : 850 - 865 .

孙锐 , 方林凤 , 梁启丽 , 等 . 孪生网络框架下融合显著性和干扰在线学习的航拍目标跟踪算法 [J]. 电子与信息学报 , 2021 , 43 ( 5 ): 1414 - 1423 .

SUN Rui , FANG Lin-feng , LIANG Qi-li , et al . Siamese network combined learning saliency and online leaning Interference for aerial object tracking algorithm [J]. Journal of Electronics & Information Technology , 2021 , 43 ( 5 ): 1414 - 1423 . (in Chinese)

黄鹤 , 李文龙 , 吴琨 , 等 . 基于ALCE-SSA优化的三维无人机低空突防 [J]. 南京大学学报(自然科学) , 2022 , 58 ( 3 ): 448 - 459 .

HUANG He , LI Wen-long , WU Kun , et al . 3D UAV low altitude penetration optimization based on ALCE⁃SSA [J]. Journal of Nanjing University (Natural Science) , 2022 , 58 ( 3 ): 448 - 459 . (in Chinese)

黄鹤 , 李潇磊 , 杨澜 , 等 . 引入改进蝠鲼觅食优化算法的水下无人航行器三维路径规划 [J]. 西安交通大学学报 , 2022 , 56 ( 7 ): 9 - 18 .

HUANG He , LI Xiao-lei , YANG Lan , et al . Three-dimensional path planning of unmanned underwater vehicle based on improved manta ray foraging optimization algorithm [J]. Journal of Xi'an Jiaotong University , 2022 , 56 ( 7 ): 9 - 18 . (in Chinese)

XUE Jian-kai , SHEN Bo . A novel swarm intelligence optimization approach: Sparrow search algorithm [J]. Systems Science & Control Engineering , 2020 , 8 ( 1 ): 22 - 34 .

MIRJALILI S , MIRJALILI S M , LEWIS A . Grey wolf optimizer [J]. Advances in Engineering Software , 2014 , 69 : 46 - 61 .

LI Shi-min , CHEN Hui-ling , WANG Ming-jing , et al . Slime mould algorithm: A new method for stochastic optimization [J]. Future Generation Computer Systems , 2020 , 111 ( 1 ): 300 - 323 .

NGUYEN H T , BHANU B . Real-time pedestrian tracking with bacterial foraging optimization [C]// 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance . Piscataway : IEEE , 2012 : 37 - 42 .

GAO Ming-liang , HE Xiao-hai , LUO Dai-sheng , et al . Object tracking using firefly algorithm [J]. IET Computer Vision , 2013 , 7 ( 4 ): 227 - 237 .

GAO Ming-liang , ZANG Yuan-ru , SHEN Jin , et al . Visual tracking based on flower pollination algorithm [C]// 2016 35th Chinese Control Conference (CCC) . Piscataway : IEEE , 2016 : 3866 - 3868 .

NENAVATH H , JATOTH R K . Hybrid SCA-TLBO: a novel optimization algorithm for global optimization and visual tracking [J]. Neural Computing and Applications , 2019 , 31 ( 9 ): 5497 - 5526 .

MIRJALILI S . Moth-flame optimization algorithm: A novel nature-inspired heuristic paradigm [J]. Knowledge-Based Systems , 2015 , 89 ( 11 ): 228 - 249 .

黄鹤 , 胡凯益 , 宋京 , 等 . 雾霾线求解透射率的二次优化方法 [J]. 西安交通大学学报 , 2021 , 55 ( 8 ): 130 - 138 .

HUANG He , HU Kai-yi , SONG Jin , et al . Quadratic optimization method for solving transmittance of haze line [J]. Journal of Xi'an Jiaotong University , 2021 , 55 ( 8 ): 130 - 138 . (in Chinese)

李维刚 , 甘平 , 谢璐 , 等 . 基于样本对元学习的小样本图像分类方法 [J]. 电子学报 , 2022 , 50 ( 2 ): 295 - 304 .

LI Wei-gang , GAN Ping , XIE Lu , et al . A few-shot image classification method by pairwise-based meta learning [J]. Acta Electronica Sinica , 2022 , 50 ( 2 ): 295 - 304 . (in Chinese)

MUELLER M , SMITH N , GHANEM B . A benchmark and simulator for UAV tracking [C]// Computer Vision—ECCV 2016 . Cham : Springer , 2016 : 445 - 461 .

DANELLJAN M , KHAN F S , FELSBERG M , et al . Adaptive color attributes for real-time visual tracking [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2014 : 1090 - 1097 .

ZHU Peng-fei , SUN Yi-ming , WEN Long-yin , et al . Drone based RGBT vehicle detection and counting: A challenge [EB/OL].[ 2020-03-05 ]. https://arxiv.org/abs/2003.02437v1 https://arxiv.org/abs/2003.02437v1 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Variable Horizon Multi-Directional Scanning Method for Time Series Anomaly Detection

Low-Light Small Target Detection Method Combining Feature Fusion Enhancement and Detail Features

Object Detection Based on EIMYOLO for High-Resolution Remote Sensing Images

Research on Improved Localization Based on Real-Time Semantic Chain List Systems

Related Author

HUANG Yu-zhe

GUAN Yong-yuan

WEI Song-jie

JIANG Ze-tao

CHENG Liu-ming

YANG Jian-chen

CAO Feng

ZENG Ke-wen

Related Institution

School of Computer Science and Engineering, School of Cyber Science and Engineering, Nanjing University of Science and Technology

Guangxi Key Laboratory of Image and Graphics Processing and Intelligent Processing, Guilin University of Electronic Technology

School of Information and Technology, Shanxi University

School of Computer Science and Technology, Soochow University

School of Electronics and Information Engineering, Suzhou University of Science and Technology

⁰