Abstract
Finding shadows in images is useful for many applications, such as white balance, shadow removal, or obstacle detection for autonomous vehicles. Shadow segmentation has been investigated both by classical computer vision and machine learning methods. In this paper, we propose a simple Convolutional-Neural-Net (CNN) running on a PC-GPU to semantically segment shadowed regions in an image. To this end, we generated a synthetic set of shadow objects, which we projected onto hundreds of shadow-less images in order to create a labeled training set. Furthermore, we suggest a novel loss function that can be tuned to balance runtime and accuracy. We argue that the combination of a synthetic training set, a simple CNN model, and loss function designed for semantic segmentation, are sufficient for semantic segmentation of shadows, especially in outdoor scenes.
This research was supported by the Israel Science Foundation and by the Israel Ministry of Science and Technology.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Guo, R., Dai, Q., Hoiem, D.: Single-image shadow detection and removal using paired regions. In: CVPR 2011 (2011)
Kovacs, B., Bell, S., Snavely, N., Bala, K.: Shading Annotations in the Wild. arXiv:1705.01156 (2017)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Optimizing IoU Semantic Segmentation. http://angusg.com/writing/2016/12/28/optimizing-iou-semantic-segmentation.html/
Rahman, M.A., Wang, Y.: Optimizing intersection-over-union in deep neural networks for image segmentation. In: Bebis, G., et al. (eds.) ISVC 2016. LNCS, vol. 10072, pp. 234–244. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-50835-1_22
Blajovici, C., Kiss, P.J., Bonus, Z., Varga, L.: Shadow detection and removal from a single image. In: SSIP 2011 (2011)
Nguyen, V., Vicente, T.F.Y., Zhao, M., Hoai, M., Samaras, D.: Shadow detection with conditional generative adversarial networks. In: ICCV 2017 (2017)
Russell, M., Zou, J.J., Fang, G.: An evaluation of moving shadow detection techniques. Comput. Vis. Med. 2(3), 195–217 (2016)
Vicente, T.F.Y., Hou, L., Yu, C.-P., Hoai, M., Samaras, D.: Large-scale training of shadow detectors with noisily-annotated shadow examples. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 816–832. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_49
Zhu, J., Samuel, K.G., Masood, S.Z., Tappen, M.F.: Learning to recognize shadows in monochromatic natural images. In: CVPR 2010 (2010)
Khan, S.H., Bennamoun, M., Sohel, F., Togneri, R.: Automatic shadow detection and removal from a single image. In: PAMI 2016 (2016)
Lalonde, J.-F., Efros, A.A., Narasimhan, S.G.: Detecting ground shadows in outdoor consumer photographs. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6312, pp. 322–335. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15552-9_24
Dataset and Source Code. http://www.cs.huji.ac.il/~werman//
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Kaminsky, E., Werman, M. (2018). ShadowNet. In: Campilho, A., Karray, F., ter Haar Romeny, B. (eds) Image Analysis and Recognition. ICIAR 2018. Lecture Notes in Computer Science(), vol 10882. Springer, Cham. https://doi.org/10.1007/978-3-319-93000-8_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-93000-8_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92999-6
Online ISBN: 978-3-319-93000-8
eBook Packages: Computer ScienceComputer Science (R0)