haoliyoupai09 / hssnet Goto Github PK

Hierarchical Spatial-aware Siamese Network for Thermal Infrared Object Tracking (HSSNet)

We propose a thermal infrared (TIR) tracker via a Hierarchical Spatial-aware Siamese convolutional neural network (CNN), named HSSNet. To obtain both spatial and semantic features of the TIR object, we design a Siamese CNN coalescing the multiple hierarchical convolutional layers. Then, we propose a spatial-aware network to enhance the discriminative ability of the coalesced hierarchical feature. Subsequently, we train this network end to end on a large visible video detection dataset to learn the similarity between paired objects before we transfer the network into the TIR domain. Next, this pre-trained Siamese network is used to evaluate the similarity between the target template and target candidates. Finally, we locate the most similar one as the tracked target.

You can run the runAll_vottir.m to test several given videos in the sequences folder.

The results on the benchmark VOT-TIR2016 can be download in here.

If you find the code is useful, please consider citing:

@article{HSSNet,
  title={Hierarchical spatial-aware Siamese network for thermal infrared object tracking},
  author={Li, Xin and Liu, Qiao and Fan, Nana and He, Zhenyu and Wang, Hongzhi},
  journal={Knowledge-Based Systems},
  volume={166},
  pages={71--81},
  year={2019}
}

Feedbacks and comments are welcome! Feel free to contact us via [email protected] or [email protected]