Giters

XinZhangRadar / View-Angle-Invariant-Object-Monitoring-Without-Image-Registration

Object monitoring can be performed by change detection algorithms. However, for the image pair with a large perspective difference, the change detection performance is usually impacted by inaccurate image registration. To address the above difficulties, a novel object-specific change detection approach is proposed for object monitoring in this paper. In contrast to traditional approaches, the proposed approach is robust to view angle variation and does not require explicit image registration. Experiments demonstrate the effectiveness and advantages of the proposed approach.

Repository from Github https://github.comXinZhangRadar/View-Angle-Invariant-Object-Monitoring-Without-Image-RegistrationRepository from Github https://github.comXinZhangRadar/View-Angle-Invariant-Object-Monitoring-Without-Image-Registration

View-Angle-Invariant-Object-Monitoring-Without-Image-Registration

Object monitoring can be performed by change detection algorithms. However, for the image pair with a large perspective difference, the change detection performance is usually impacted by inaccurate image registration. To address the above difficulties, a novel object-specific change detection approach is proposed for object monitoring in this paper. In contrast to traditional approaches, the proposed approach is robust to view angle variation and does not require explicit image registration. Experiments demonstrate the effectiveness and advantages of the proposed approach.

Citing VAIOM

If you think this paper is useful in your project, please consider citing us.

@INPROCEEDINGS{9054668,
  author={X. {Zhang} and C. {Huo} and C. {Pan}},
  booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={View-Angle Invariant Object Monitoring Without Image Registration}, 
  year={2020},
  volume={},
  number={},
  pages={2283-2287},}

About

Object monitoring can be performed by change detection algorithms. However, for the image pair with a large perspective difference, the change detection performance is usually impacted by inaccurate image registration. To address the above difficulties, a novel object-specific change detection approach is proposed for object monitoring in this paper. In contrast to traditional approaches, the proposed approach is robust to view angle variation and does not require explicit image registration. Experiments demonstrate the effectiveness and advantages of the proposed approach.