首页> 外文会议>IEEE International Conference on Computer and Communications >An Improved Visual Tracking Algorithm Based on Efficient Convolution Operators
【24h】

An Improved Visual Tracking Algorithm Based on Efficient Convolution Operators

机译:一种基于高效卷积运算符的改进的视觉跟踪算法

获取原文

摘要

Effcient Convolution Operators (ECO) is one of the most outstanding visual tracking algorithms in recent years, it combines two methods of Deep Learning and Discriminative Correlation Filter (DCF), and has excellent performance in VOT2016, UAV123, OTB-2015 and TempleColor. The paper propose integrating ECO and Fully Convolutional Networks (FCN) to achieve state-of-the-art segmentation for ECO. In our experiments, the original CNN model of ECO is replaced by the FCN model. Compared with the traditional Convolutional Neural Networks (CNN), the FCN has higher accuracy of segmentation and can input any size of image. We perform comprehensive experiments which obtained 0.653 area under curve (AUC) and 0.861 precision plot (DP) on OTB-2013 dataset.
机译:效率卷积运营商(ECO)是近年来最出色的视觉跟踪算法之一,它结合了两种深度学习和鉴别相关滤波器(DCF),在VOT2016,UAV123,OTB-2015和TempleColor中具有出色的性能。本文建议将生态和全卷积网络(FCN)集成,以实现ECO的最先进的细分。在我们的实验中,ECO的原始CNN模型由FCN模型代替。与传统的卷积神经网络(CNN)相比,FCN具有更高的分割精度,并且可以输入任何大小的图像。我们在OTB-2013 DataSet上执行曲线(AUC)和0.861精密图(DP)下的0.653面积的全面实验。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号