Corpus ID: 39526802

Hierarchical Siamese Network for Thermal Infrared Object Tracking

@article{Liu2017HierarchicalSN,
  title={Hierarchical Siamese Network for Thermal Infrared Object Tracking},
  author={Q. Liu and Zhenyu He and Hongzhi Wang and Xin Li},
  journal={ArXiv},
  year={2017},
  volume={abs/1711.09539}
}

Q. Liu, Zhenyu He, +1 author Xin Li

Published 2017

Geography, Computer Science

ArXiv

Most thermal infrared (TIR) tracking methods are discriminative, which treat the tracking problem as a classification task. [...] Key Method We propose a TIR tracker via a hierarchical Siamese convolutional neural network (CNN), named HSNet. To obtain both spatial and semantic features of the TIR object, we design a Siamese CNN coalescing the multiple hierarchical convolutional layers.Expand Abstract

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed