End-to-End United Video Dehazing and Detection

Proceedings of 32nd AAAI Conference on Artificial Intelligence (AAAI), 2018, Oral 

Abstract：The recent development of CNN-based image dehazing has revealed the effectiveness of end-to-end modeling. However, extending the idea to end-to-end video dehazing has not been explored yet. In this paper, we propose an End-to-End Video Dehazing Network (EVD-Net), to exploit the temporal consistency between consecutive video frames. A thorough study has been conducted over a number of structure options, to identify the best temporal fusion strategy. Furthermore, we build an End-to-End United Video Dehazing and Detection Network (EVDD-Net), which concatenates and jointly trains EVD-Net with a video object detection model. The resulting augmented end-to-end pipeline has demonstrated much more stable and accurate detection results in hazy video.

Paper

[PDF]

Download

[Code]

Note: If you could not download successfully, you could also find this code in github .

Bibtex

@article{li2017end,

  title={End-to-End United Video Dehazing and Detection},

  author={Li, Boyi and Peng, Xiulian and Wang, Zhangyang and Xu, Jizheng and Feng, Dan},

  journal={arXiv preprint arXiv:1709.03919},

  year={2017}

}

Video

Here shows our work on Improving Detection with Dehazing in Videos. Details can be found in our paper.