End-to-End United Video Dehazing and Detection

Authors

  • Boyi Li Huazhong University of Science and Technology
  • Xiulian Peng Microsoft Research
  • Zhangyang Wang Texas A&M University
  • Jizheng Xu Microsoft Research
  • Dan Feng Huazhong University of Science and Technology

Keywords:

Vision, Machine Learning Applications

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.

Downloads

Published

2018-04-27

How to Cite

Li, B., Peng, X., Wang, Z., Xu, J., & Feng, D. (2018). End-to-End United Video Dehazing and Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12287