• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Signal Processing. Image Communication: A Publication of the the European Association for Signal Processing >DSiamMFT: An RGB-T fusion tracking method via dynamic Siamese networks using multi-layer feature fusion
【24h】

DSiamMFT: An RGB-T fusion tracking method via dynamic Siamese networks using multi-layer feature fusion

机译：DSIAMMFT：使用多层特征融合的动态暹罗网络的RGB-T融合方法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The task of object tracking is very important since its various applications. However, most object tracking methods are based on visible images, which may fail when visible images are unreliable, for example when the illumination conditions are poor. To address this issue, in this paper a fusion tracking method which combines information from RGB and thermal infrared images (RGB-T) is presented based on the fact that infrared images reveal thermal radiation of objects thus providing complementary features. Particularly, a fusion tracking method based on dynamic Siamese networks with multi-layer fusion, termed as DSiamMFT, is proposed. Visible and infrared images are firstly processed by two dynamic Siamese Networks, namely visible and infrared network, respectively. Then, multi-layer feature fusion is performed to adaptively integrate multi-level deep features between visible and infrared networks. Response maps produced from different fused layer features are then combined through an elementwise fusion approach to produce the final response map, based on which the target can be located. Extensive experiments on large datasets with various challenging scenarios have been conducted. The results demonstrate that the proposed method shows very competitive performance against the-state-of-art RGB-T trackers. The proposed approach also improves tracking performance significantly compared to methods based on images of single modality.
机译：自体应用程序以来，对象跟踪的任务非常重要。然而，大多数物体跟踪方法基于可见图像，当可见图像不可靠时可能失效，例如当照明条件差时。为了解决这个问题，在本文中，基于红外图像揭示对象的热辐射的事实，将来自RGB和热红外图像（RGB-T）相结合的融合跟踪方法。从而提供互补特征。特别是，提出了一种基于具有多层融合的动态暹罗网络的融合跟踪方法，称为DSIAMMFT。可见和红外图像首先由两个动态暹罗网络，即可见和红外网络处理。然后，执行多层特征融合以在可见和红外网络之间自适应地集成多级深度特征。然后通过基于该目标可以定位的目标来产生来自不同融合层特征的响应图，以产生最终响应图。已经进行了关于具有各种具有挑战性场景的大型数据集的广泛实验。结果表明，该方法对最先进的RGB-T跟踪器表现出非常竞争力的性能。与基于单个模态图像的方法相比，该方法还提高了跟踪性能。

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