Abstract
Shadow removal has been proved very helpful in higher-level computer vision applications which involves object detection, object tracking as part of the process. Removal of the shadow has always been a challenge, especially for ensuring higher-quality images after the shadow removal process. In order to unveil the information occluded by shadow, it is essential to remove the shadow. This is a two-step process which involves shadow detection and shadow removal. In this paper, shadow-less image is generated using a modified conditional GAN (cGAN) model and using shadow image and the original image as the inputs. The proposed novel method uses a discriminator that judges the local patches of the images. The model not only use the residual generator to produce high-quality images but also use combined loss, which is the weighted sum of reconstruction loss and GAN loss for training stability. Proposed model evaluated on the benchmark dataset, i.e., ISTD, and achieved significant improvements in the shadow removal task compared to the state of the art models. Structural similarity index (SSIM) metric also used to evaluate the performance of the proposed model from the perspective of Human Visual System.
Supported by Amrita Vishwa Vidyapeetham.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
I.J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial networks, in International Conference on Neural Information Processing Systems, 2014, https://arxiv.org/abs/1406.2661
S. Veni, R. Anand, B. Santosh, Road accident detection and severity determination from CCTV surveillance, in Advances in Distributed Computing and Machine Learning, Singapore, 2021
R. Sujee, S.K. Thangavel, Plant leaf recognition using machine learning techniques, in New Trends in Computational Vision and Bio-inspired Computing: Selected Works Presented at the ICCVBIC 2018, Coimbatore, India (Springer, Cham, 2020), pp. 1433–1444
J. Wang, X. Li, J. Yang, Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal. CVPR 2017. https://doi.org/10.1109/CVPR.2018.00192
L. Zhang, C. Long, X. Zhang, C. Xiao, RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal. AAAI 2020. https://doi.org/10.1609/aaai.v34i07.6979
L. Qu, J. Tian, S. He, Y. Tang, R.W.H. Lau, DeshadowNet: a multi-context embedding deep network for shadow removal, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. https://ieeexplore.ieee.org/document/8099731
O. Sidorov, Conditional GANs for multi-illuminant color constancy: revolution or yet another approach? in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. https://arxiv.org/abs/1811.06604
C. Wang, H. Xu, Z. Zhou, L. Deng, M. Yang, Shadow detection and removal for illumination consistency on the road. IEEE Trans. Intell. Veh. (2020). https://ieeexplore.ieee.org/document/9068460
C. Wang, L. Deng, Z. Zhou, M. Yang, B. Wang, Shadow detection and removal for illumination consistency on the road. https://ieeexplore.ieee.org/document/8304275
H. Yun, K. Kang Jik, J.-C. Chun, Shadow detection and removal from photo-realistic synthetic urban image using deep learning. Comput. Mater. Continua (2019). https://www.techscience.com/cmc/v62n1/38123
X. Cun, C.-M. Pun, C. Shi, Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN. AAAI 2020. https://arxiv.org/abs/1911.08718
M. Mirza, S. Osindero, Conditional Generative Adversarial Nets. In Arxiv 2014. http://arxiv.org/abs/1411.1784
O. Ronneberger, P. Fischer, T. Brox, U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI 2015. https://arxiv.org/abs/1505.04597
K. Sree, G. Jeyakumar, An evolutionary computing approach to solve object identification problem for fall detection in computer vision-based video surveillance applications. J. Comput. Theor. Nanosci. 17(1), 1–18 (2020). https://doi.org/10.1166/jctn.2020.8687
K. Mondal, S. Padmavathi, Wild animal detection and recognition from aerial videos using computer vision technique. Int. J. Emerg. Trends Eng. Res. 7(5), 21–24 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jishnu, P., Rajathilagam, B. (2022). Enhanced Shadow Removal for Surveillance Systems. In: Raj, J.S., Kamel, K., Lafata, P. (eds) Innovative Data Communication Technologies and Application. Lecture Notes on Data Engineering and Communications Technologies, vol 96. Springer, Singapore. https://doi.org/10.1007/978-981-16-7167-8_5
Download citation
DOI: https://doi.org/10.1007/978-981-16-7167-8_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7166-1
Online ISBN: 978-981-16-7167-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)