ABSTRACT
Deterioration of image due to haze is one of the factors that degrade the performance of computer vision algorithm. The haze component absorbs and reflects the reflected light from the object, distorting the original irradiance. The more the distance from the camera is, the more deteriorated it tends to be. Therefore, studies have been conducted to remove haze by estimating the distribution of haze along the distance. In this paper, we use convolution neural network to simultaneously perform depth estimation and haze removal based on stereo image, and depth information to help improve performance of haze removal. We propose a multitasking network in which the encoder learns depth information and dehazing features simultaneously by performing depth estimation and dehazing using two decoders.
The learning of the network is based on a stereo image, and a large amount of left and right hazy images are required. However, existing hazy image data sets are inferior in reality because they are added to fog components in indoor images. Therefore, a data set composed of a haze component corresponding to the distance information was constructed and used in the KITTI road data set composed of a large amount of stereo outdoor driving images. Experimental results show that the proposed network has robust dehazing performance compared to existing methods for various levels of hazy images and improves the visibility by strengthening the contrast of boundaries in faint areas due to haze.
- R. Fattal. Single image dehazing. In ACM SIGGRAPH 2008 Papers, pages 72:1--72:9, 2008. Google ScholarDigital Library
- S. K. Nayar and S. G. Narasimhan. Vision in bad weather. In Proceedings of the Seventh IEEE International Conference on Computer Vision, volume 2, pages 820--827 vol.2, 1999. Google ScholarDigital Library
- Y. Y. Schechner, S. G. Narasimhan, and S. K. Nayar. Polarization-based vision through haze. Appl. Opt., 2003.Google ScholarCross Ref
- D. Berman, T. Treibitz, and S. Avidan. Non-local image dehazing. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1674--1682, 2016.Google ScholarCross Ref
- K. He, J. Sun, and X. Tang. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12):2341--2353, 2011. Google ScholarDigital Library
- C. Ancuti, C. O. Ancuti, and C. D. Vleeschouwer. D-hazy: A dataset to evaluate quantitatively dehazing algorithms. In 2016 IEEE International Conference on Image Processing (ICIP), pages 2226--2230, 2016.Google ScholarCross Ref
- J.-P. Tarel, N. Hautière, A. Cord, D. Gruyer, and H. Halmaoui. Improved visibility of road scene images under heterogeneous fog. In Proceedings of IEEE Intelligent Vehicle Symposium (IV'2010), pages 478--485, 2010.Google ScholarCross Ref
- W. Ren, S. Liu, H. Zhang, J. Pan, X. Cao, and M.-H. Yang. Single image dehazing via multi-scale convolutional neural networks. In European Conference on Computer Vision, 2016.Google ScholarCross Ref
- H. Zhang, V. Sindagi, and V. M. Patel. Joint transmission map estimation and dehazing using deep networks. CoRR, abs/1708.00581, 2017.Google Scholar
- B. Li, X. Peng, Z. Wang, J.-Z. Xu, and D. Feng. Aod-net: All-in-one dehazing network. In Proceedings of the IEEE International Conference on Computer Vision, 2017.Google ScholarCross Ref
- Z. Ling, G. Fan, Y. Wang, and X. Lu. Learning deep transmission network for single image dehazing. In 2016 IEEE International Conference on Image Processing (ICIP), pages 2296--2300, 2016.Google ScholarCross Ref
- P. K. Nathan Silberman, Derek Hoiem and R. Fergus. Indoor segmentation and support inference from rgbd images. In European Conference on Computer Vision, 2012. Google ScholarDigital Library
- D. Scharstein, H. Hirschmüller, Y. Kitajima, G. Krathwohl, N. Nesic, X. Wang, and P. Westling. High-resolution stereo datasets with subpixel-accurate ground truth. In GCPR, volume 8753, pages 31--42, 2014.Google ScholarCross Ref
- A. Geiger, P. Lenz, and R. Urtasun. Are we ready for autonomous driving? The kitti vision benchmark suite. In Conference on Computer Vision and Pattern Recognition (CVPR), 2012. Google ScholarDigital Library
- C. Godard, O. Mac Aodha, and G. J. Brostow. Unsupervised monocular depth estimation with left-right consistency. In CVPR, 2017.Google ScholarCross Ref
Index Terms
- Stereo Vision aided Image Dehazing using Deep Neural Network
Recommendations
Image Dehazing Via Cycle Generative Adversarial Network
AISS '21: Proceedings of the 3rd International Conference on Advanced Information Science and SystemRecovering a clear image from single hazy image has been widely investigated in recent researches. Due to the lack of the real hazed image dataset, most studies use artificially synthesized dataset to train the models. Nonetheless, the real word foggy ...
Haze transfer and feature aggregation network for real-world single image dehazing
AbstractThe absence of ground truth for hazy images in real scenes results in most dehazing models being trained only by synthesized datasets, which is not feasible for real hazy images due to the domain shift. To address this problem, a haze ...
Highlights- We propose a haze transfer model for haze information from a real hazy image to a clear image.
A new approach for training a physics-based dehazing network using synthetic images
Highlights- We present a novel method of using synthetic images, captured from a 3D urban virtual environment, for a physics-based dehazing task.
AbstractIn this study, we propose a new approach for training a physics-based dehazing network, using RGB images and depth maps gathered from a 3D urban virtual environment, with simulated global illumination and physically-based shaded ...
Comments