电子电气工程与控制

基于自适应深度网络的无人机目标跟踪算法

  • 刘芳 ,
  • 王洪娟 ,
  • 黄光伟 ,
  • 路丽霞 ,
  • 王鑫
展开
  • 北京工业大学 信息学部, 北京 100124

收稿日期: 2018-05-15

  修回日期: 2018-06-11

  网络出版日期: 2018-09-17

基金资助

国家自然科学基金(61171119);北京工业大学研究生科技基金(ykj-2016-00026)

UAV target tracking algorithm based on adaptive depth network

  • LIU Fang ,
  • WANG Hongjuan ,
  • HUANG Guangwei ,
  • LU Lixia ,
  • WANG Xin
Expand
  • College of Information, Beijing University of Technology, Beijing 100124, China

Received date: 2018-05-15

  Revised date: 2018-06-11

  Online published: 2018-09-17

Supported by

National Natural Science Foundation of China (61171119);Beijing University of Technology Graduate Technology Fund (ykj-2016-00026)

摘要

针对无人机(UAV)视频中目标易受到遮挡、形变、复杂背景干扰等问题,提出一种基于自适应深度网络的无人机目标跟踪算法。首先,基于主成分分析(PCA)和卷积神经网络(CNN)算法,设计3阶的自适应深度网络进行目标特征提取,该网络对图像的H、S、I通道分别进行主成分分析学习,将得到的特征向量输入网络进行分层卷积,优化了网络结构,提高了网络的收敛速度和精度。其次,将目标深度特征输入核相关滤波算法进行目标跟踪,通过分析相邻2帧图像的变化率,采用分段自适应调整学习率的算法进行目标模板更新,有效地改善目标遮挡问题。仿真实验结果表明,该算法有效地避免了复杂因素干扰导致的跟踪精度下降,具有较好的鲁棒性,相较于全卷积跟踪(FCNT)算法平均跟踪精度提高了9.62%,平均跟踪成功率提高了11.9%。

本文引用格式

刘芳 , 王洪娟 , 黄光伟 , 路丽霞 , 王鑫 . 基于自适应深度网络的无人机目标跟踪算法[J]. 航空学报, 2019 , 40(3) : 322332 -322332 . DOI: 10.7527/S1000-6893.2018.22332

Abstract

Aiming at the problem that targets are subject to occlusion, deformation, and complex background interference in the drone video, a Unmanned Aerial Vehicle (UAV) target tracking algorithm based on the adaptive depth network is proposed. First, based on the Principal Component Analysis (PCA) and Convolutional Neural Network (CNN), a 3-order adaptive CNN network is designed for target feature extraction. PCA is hierarchically performed on H,S, and I channels, convolving hierarchically by the obtained eigenvectors, which optimizes the network structure and improves the convergence speed and accuracy. Second, the target depth feature is input into KCF algorithm for target tracking. By analyzing the change rate of the two adjacent frames and using the segmented adaptive adjustment of learning rate to update the target template, the target occlusion problem is effectively moderated. The experimental results show that the algorithm effectively avoids the degradation of tracking accuracy caused by complex factors, reaching good robustness. The average accuracy-rate of the algorithm is 9.62% higher than that of fully convolutional network based tracker Fully Convolutional Network Tracking (FCNT), and the average success-rate is increased by 11.9%.

参考文献

[1] LI X, HU W, SHEN C, et al. A survey of appearance models in visual object tracking[J]. Acm Transactions on Intelligent Systems & Technology, 2013, 4(4):16-58.
[2] 高琳, 王俊峰, 范勇, 等. 基于卷积神经网络与一致性预测器的鲁棒视觉跟踪[J]. 激光与光电子学进展, 2017, 37(8):0815003-0815017. GAO L, WANG J F, FAN Y, et al. Robust visual tracking based on convolutional neural network and consistency predictor[J]. Laser & Optoelectronics Progress, 2017, 37(8):0815003-0815017(in Chinese).
[3] HARE S, GOLODETZ S, SAFFARI A, et al. Struck:Structured output tracking with kernels[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(10):2096-2109.
[4] WANG X F, DONG X M, KONG X W, et al. Drogue detection for autonomous aerial refueling based on convolutional neural networks[J]. Chinese Journal of Aeronautics, 2017, 30(1):380-390.
[5] WANG N, YEUNG D Y. International conference on neural information processing systems[J]. Curran Associates Inc, 2013, 34(5):809-817.
[6] HONG S, YOU T, KWAK S, et al. Online tracking by learning discriminative saliency map with convolutional neural network[C]//International Conference on Machine Learning. New York:ACM, 2015:597-606.
[7] NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ:IEEE Press, 2016:4293-4302.
[8] WANG L, OUYANG W, WANG X, et al. Visual tracking with fully convolutional networks[C]//IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE Press, 2016:3119-3127.
[9] 赵洲, 黄攀峰, 陈路. 一种融合卡尔曼滤波的改进时空上下文跟踪算法[J]. 航空学报, 2017, 38(2):269-279. ZHAO Z, HUANG P F, CHEN L. Improved spatial-temporal context tracking algorithm based on fusion Kalman filter[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(2):269-279(in Chinese).
[10] BOLME D S, BEVERIDGE 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. Piscataway, NJ:IEEE Press, 2010.
[11] HENRIQUES J F, RUI C, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]//European Conference on Computer Vision. Berlin, Heidelberg:Springer, 2012:702-715.
[12] HENRIQUES J F, RUI C, MARTINS P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 37(3):583-596.
[13] 崔乃刚, 张龙, 王小刚, 等. 自适应高阶容积卡尔曼滤波在目标跟踪中的应用[J]. 航空学报, 2015, 36(12):3885-3895. CUI N G, ZHANG L, WANG X G, et al. Application of adaptive high-capacity Kalman filter in target tracking[J]. Acta Aeronautica et Astronautica Sinica, 2015, 36(12):3885-3895(in Chinese).
[14] CHAN T H, JIA K, GAO S, et al. PCANet:A simple deep learning baseline for image classification[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2015, 24(12):5017-5032.
[15] HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 37(9):1904-1916.
[16] HUANG S, YANG D, GE Y, et al. Combined supervised information with PCA via discriminative component selection[J]. Information Processing Letters, 2015, 115(11):812-816.
[17] MUELLER M, SMITH N, GHANEM B. A benchmark and simulator for UAV tracking[J]. Far East Journal of Mathematical Sciences, 2016, 2(2):445-461.
[18] BERTINETTO L, VALMADRE J, GOLODETZ S, et al. Staple:Complementary learners for teal-time tracking[C]//Computer Vision & Pattern Recognition, 2016.
[19] DANELLJAN M, HAGER G, KHAN F S, et al. Learning spatially regularized correlation filters for visual tracking[J]. Proceedings of the IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE Press, 2016:4310-4318.
文章导航

/