Abstract
Deep learning has achieved state-of-the-art results in various image classification and image segmentation tasks. However, due to the lack of well-labeled datasets, the insufficiency of deep feature extraction, and the complexity of the distribution of shadows on remote sensing images, popular deep neural networks still fall short on satisfactory shadow detection from remote sensing images. Inspired by the brain's mechanism for processing visual signals, this paper proposes a new Dual-stream Shadow Detection Network (DSSDN) that is specifically designed for detecting shadows on remote sensing images. In DSSDN, the pooling stream extracts high-level features by merging multiple atrous pooling feature maps after the encoder, while the residual stream maintains low-level features and carries out the interaction of dual-stream features. This network is also featured with three new sub-modules. We manually labeled 1724 remote sensing images with shadows to form a new dataset for training and testing of DSSDN. In the quantitative contrast experiment on this dataset, DSSDN reaches the lowest Balanced Error Rate (BER) at 6.6% across all compared models and networks. In the qualitative analysis, the detected shadows of DSSDN also show best contours and details in comparison with results from other approaches.
Similar content being viewed by others
References
Mostafa Y, Abdelhafiz A (2017) Accurate shadow detection from high-resolution satellite images. IEEE Geosci Remote Sens Lett 14(4):494–498. https://doi.org/10.1109/LGRS.2017.2650996
Hu J, Song Y, Jin T, Lu B, Zhu G, Zhou Z (2015) Shadow effect mitigation in indication of moving human behind wall via MIMO TWIR. IEEE Geosci Remote Sens Lett 12(3):453–457. https://doi.org/10.1109/LGRS.2014.2345777
Sirmacek B, Unsalan C (2009) Damaged building detection in aerial images using shadow information. In: International conference on recent advances in space technologies (RAST '09)
Dare PM (2005) Shadow analysis in high-resolution satellite imagery of urban areas. Photogramm Eng Remote Sens 71:169–177
Huang J, Zhang X, Xin Q, Sun Y, Zhang P (2019) Automatic building extraction from high-resolution aerial images and LiDAR data using gated residual refinement network. ISPRS J Photogramm Remote Sens 151:91–105
Liasis G, Stavrou S (2016) Satellite images analysis for shadow detection and building height estimation. ISPRS J Photogramm Remote Sens 119:437–450
Tsai VJD (2006) A comparative study on shadow compensation of color aerial images in invariant color models. IEEE Trans Geosci Remote Sens 44(6):1661–1671
Yamazaki F, Liu W, Takasaki M (2010) Characteristics of shadow and removal of its effects for remote sensing imagery. In: IEEE geoscience and remote sensing symposium
Makarau A, Richter R, Muller R et al (2011) Adaptive shadow detection using a blackbody radiator model. IEEE Trans Geosci Remote Sens 49(6):2049–2059
Elbakary MI, Iftekharuddin KM (2014) Shadow detection of man-made buildings in high-resolution panchromatic satellite images. IEEE Trans Geosci Remote Sens 52(9):5374–5386
Liasis G, Stavrou S (2016) Satellite images analysis for shadow detection and building height estimation. ISPRS J Photogramm Remote Sens 119:437–450
Tong X, Lin X, Feng T et al (2013) Use of shadows for detection of earthquake-induced collapsed buildings in high-resolution satellite imagery. ISPRS J Photogramm Remote Sens 79:53–67
Movia A, Beinat A, Crosilla F (2016) Shadow detection and removal in RGB VHR images for land use unsupervised classification. ISPRS J Photogramm Remote Sens 119:485–495
Chai D, Newsam S, Zhang HK, Qiu Y, Huang J (2019) Cloud and cloud shadow detection in Landsat imagery based on deep convolutional neural networks. Remote Sens Environ 225:307–316
Morales G, Arteaga D, Samuel G et al (2018) Shadow detection in high-resolution multispectral satellite imagery using generative adversarial networks. In: IEEE international conference on electronics, electrical engineering and computing
Kussul N, Lavreniuk M, Skakun S, Shelestov A (2017) Deep learning classification of land cover and crop types using remote sensing data. IEEE Geosci Remote Sens Lett 14(5):778–782. https://doi.org/10.1109/LGRS.2017.2681128
Qiu C, Mou L, Schmitt M, Zhu XX (2020) Fusing multiseasonal sentinel-2 imagery for urban land cover classification with multibranch residual convolutional neural networks. IEEE Geosci Remote Sens Lett 17(10):1787–1791. https://doi.org/10.1109/LGRS.2019.2953497
Yan Z et al (2018) Cloud and cloud shadow detection using multilevel feature fused segmentation network. IEEE Geosci Remote Sens Lett 15(10):1600–1604. https://doi.org/10.1109/LGRS.2018.2846802
Wang T, Hu X, Wang Q, Heng P-A, Fu C-W (2020) Instance shadow detection. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 1877–1886, https://doi.org/10.1109/CVPR42600.2020.00195
Hu X, Fu C-W, Zhu L, Qin J, Heng P-A (2020) Direction-aware spatial context features for shadow detection and removal. IEEE Trans Pattern Anal Mach Intell 42(11):2795–2808. https://doi.org/10.1109/TPAMI.2019.2919616
Inoue N, Yamasaki T (2020) Learning from synthetic shadows for shadow detection and removal. IEEE Trans Circ Syst Video Technol 31:4187–4197. https://doi.org/10.1109/TCSVT.2020.3047977
Chen Z, Zhu L, Wan L, Wang S, Feng W, Heng P-A (2020) A multi-task mean teacher for semi-supervised shadow detection. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 5610–5619. https://doi.org/10.1109/CVPR42600.2020.00565
Cun X, Pun CM, Shi C (2020) Towards ghost-free shadow removal via dual hierarchical aggregation network and shadow matting GAN. In: AAAI conference on artificial intelligence, pp 10680–10687
Ding B, Long C, Zhang L, Xiao C (2019) ARGAN: attentive recurrent generative adversarial network for shadow detection and removal. In: 2019 IEEE/CVF international conference on computer vision (ICCV), pp 10212–10221. https://doi.org/10.1109/ICCV.2019.01031
Hou L, Vicente TFY, Hoai M, Samaras D (2021) Large scale shadow annotation and detection using lazy annotation and stacked CNNs. IEEE Trans Pattern Anal Mach Intell 43(4):1337–1351. https://doi.org/10.1109/TPAMI.2019.2948011
Hu X, Jiang Y, Fu C, Heng P (2019) Mask-ShadowGAN: learning to remove shadows from unpaired data. In: 2019 IEEE/CVF international conference on computer vision (ICCV), pp 2472–2481. https://doi.org/10.1109/ICCV.2019.00256
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T et al (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L (2018) MobileNetV2: inverted residuals and linear bottlenecks. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR), Salt Lake City, UT, pp 4510–4520
Howard A, Sandler M, Chu G, Liang CC, Chen B, Tan MX, Wang W, Zhu Y, Pang R, Vasudevan V, Le Q, Adam H (2019) Searching for MobileNetV3. arXiv:1905.02244
Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2014) Semantic image segmentation with deep convolutional nets and fully connected CRFs. Comput Sci 4:357–361
Chen L, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2016) DeepLab: semantic image segmentation with deep convolutional nets, Atrous convolution, and fully connected CRFs. In: IEEE conference on computer vision and pattern recognition (CVPR)
Chen L, Papandreou G, Schroff F, Adam H (2017) Rethinking Atrous convolution for semantic image segmentation. arXiv: 1706.05587
K. He, G. Gkioxari, P. Dollár and R. Girshick, Mask R-CNN, 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 2980–2988.
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR)
Li D, Wang S, Tang X-S, Kong W, Shi G, Chen Y (2020) Double-stream atrous network for shadow detection. Neurocomputing 417:167–175
G-S Xia, Bai X, Ding J et al (2018) DOTA: a large-scale dataset for object DeTection in aerial images. https://captain-whu.github.io/DOTA/index.html
Maggiori E, Tarabalka Y, Charpiat G, Alliez P (2017) Can semantic labeling methods generalize to any city? The Inria aerial image labeling benchmark. In: IEEE international geoscience and remote sensing symposium (IGARSS). 2017.
Isola P, Zhu J, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI, pp 5967–5976. https://doi.org/10.1109/CVPR.2017.632
Pohlen T, Hermans A, Mathias M, Leibe B (2017) Full-resolution residual networks for semantic segmentation in street scenes. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI, pp 3309–3318
Freitas V, Reis B, Tommaselli A (2017) Automatic shadow detection in aerial and terrestrial images. Boletim de Ciências Geodésicas 23:578–590
Silva GF, Carneiro GB, Doth R, Amaral LA, de Azevedo DFG (2018) Near real-time shadow detection and removal in aerial motion imagery application. ISPRS J Photogramm Remote Sens 140:104–121
Funding
This work was supported in part by Shanghai Rising-Star Program under Grant 21QA1400100, National Natural Science Foundation of China under Grant 62176052, Shanghai Natural Science Foundation under Grant 20ZR1400800, the Shanghai Sailing Program under Grant 20YF1401600, and in part by the Fundamental Research Funds for the Central Universities of China under Grant 2232020D-47.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, D., Wang, S., Xiang, S. et al. Dual-stream shadow detection network: biologically inspired shadow detection for remote sensing images. Neural Comput & Applic 34, 10039–10049 (2022). https://doi.org/10.1007/s00521-022-06989-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-06989-w