In the paper,a multi-feature fusion target tracking algorithm based on RBF neural network is proposed.RBF neural network is a simple and efficient three-layer neural network,which can greatly improve tracking efficiency.This paper first uses the three-dimensional color histogram,the Canny operator and the gray-scale image with spatial correlation to construct the input feature vector of the RBF neural network.Then use the triangular kernel function as the activation function of the RBF neural network.Finally,the proposed algorithm is used to track the target.The experiment results show that the target tracking algorithm proposed in this paper can track the target reliably,and has good adaptability to problems such as camera movement,illumination changes,target rotation,and shape deformation.
Key words
target tracking /
RBF neural network /
color histogram /
Canny operator /
the gray-scale image /
generalized pseudo-inverse
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] 尹宏鹏,陈波,柴毅,等. 基于视觉的目标检测与跟踪综述 [J].自动化学报,2016,42(10):1466-1489.
[2] 陈彦明,赵清杰,刘若宇.一种适用于分布式摄像机网络的SCIWCF算法[J].电子学报,2016,44(10):2335-2343.
[3] 顾幸方,茅耀斌,李秋洁.基于Mean Shift的视觉目标跟踪算法综述[J].计算机科学,2012,39(12):16-24.
[4] 赖程程,梁麟.基于轮廓模型和AdaBoost算法的民族地区舞蹈人员跟踪技术研究[J].现代电子技术,2020,43(5):42-45.
[5] 管皓,薛向阳,安志勇.深度学习在视频目标跟踪中的应用进展与展望[J].自动化学报,2016,42(6):834-847.
[6] 单超颖,李权,郭莉莉.RBF神经网络优化后的无线网络室内定位 [J].现代电子技术,2020,43(22):49-52,56.
[7] 王文成,邱胜朋,姚金峰,等.RBF模型预测PID在两级AO污水处理中的改进研究[J].现代电子技术,2020,43(3):104-108.
[8] BABU R V,SURESH S,MAKURA.Online adaptive radial basis function networks for robust object tracking[J].Computer Vision and Image Understanding,2010,114(3):297-310.
[9] 尹钊,贾尚晖.Moore-Penrose广义逆矩阵与线性方程组的解[J]. 数学的实践与认识,2009,39(9):239-244.
[10] 曾欢,王浩.图像边缘检测算法的性能比较与分析[J].现代电子技术,2006(14):53-55,58.
[11] WU Y,LIM J,YANG M H.Online object tracking:A benchmark;proceedings of the 2013 IEEE[C]//Conference on Computer Vision and Pattern Recognition,Portland,OR,USA,2013.
PDF(1323 KB)
