DNN-PolSAR: Urban Image Segmentation and Classification using Polarimetric SAR based on DNNs
Article Sidebar
Main Article Content
Abstract
Synthetic Aperture Radar (SAR) image segmentation and classification is a popular technique for learn- ing and detection of objects such as buildings, trees, monuments, crops water-bodies, hills, etc. SAR technique is being used for urban development and city-planning, building control of municipal objects, searching best locations, detection of changes in the existing systems, etc. using polarimetry based on Deep Neural Networks. In this paper, weproposed a technique for Urban Image Segmentation and Classification using Polarimetric SAR based on Deep NeuralNetworks (DNN-PolSAR). In our proposed DNN-PolSAR technique, we useMask-RCNN, LinkNet, FPN, and PSP- Net as model architectures, whereas ResNet50, ResNet101, ResNet152, and VGG-19 are used as backbone networks.We first apply polarimetric decomposition on airborne Uninhabited Aerial Vehicle Synthetic Aperture (UAVSAR) im- ages of urban areas and then the decomposed images are fed to DNNs for segmentation and classification. We then simulate DNN-PolSAR considering different hyper-parameters and compare the obtained scores of hyper-parametersagainst used model architectures and backbone networks. In comparison, it is found that DNN-PolSAR based on FPNmodel with ResNet152 performed the best for segmentation and classification. The mean Average Precision (mAP) score of the DNN-PolSAR based on FPN with a pixel accuracy of 90.9% is 0.823, which outperforms other Deep Learning models.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
Z. Niu, G. Hua, X. Gao, et al., “Context aware topic model for scene recognition,” in 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2743–2750, IEEE (2012).
S. A. Taghanaki, K. Abhishek, J. P. Cohen, et al., “Deep semantic segmentation of natural and medical images: a review,” Artificial Intelligence Review 54(1), 137–178 (2021). https://doi.org/10.1007/s10462-020-09854-1
T. Zhou, Z. Li, and J. Pan, “Multi-feature classification of multi-sensor satellite imagery based on dual-polarimetric sentinel-1a, landsat-8 oli, and hyperion images for urban land- cover classification,” Sensors 18(2), 373 (2018). https://doi.org/10.3390/s18020373
S.-W. Chen and C.-S. Tao, “Polsar image classification using polarimetric-feature-driven deep convolutional neural network,” IEEE Geoscience and Remote Sensing Letters 15(4), 627–631 (2018). https://doi.org/10.1109/LGRS.2018.2799877
Y. Zhang, J. Zhang, X. Zhang, et al., “Land cover classification from polarimetric sar data based on image segmentation and decision trees,” Canadian Journal of Remote Sensing 41(1), 40–50 (2015). https://doi.org/10.1080/07038992.2015.1032901
S. De, L. Bruzzone, A. Bhattacharya, et al., “A novel technique based on deep learning and a synthetic target database for classification of urban areas in polsar data,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 11(1), 154–170 (2017). https://doi.org/10.1109/JSTARS.2017.2752282
S. De, L. Bruzzone, A. Bhattacharya, et al., “A novel technique based on deep learning and a synthetic target database for classification of urban areas in polsar data,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 11(1), 154–170 (2018). https://doi.org/10.1109/JSTARS.2017.2752282
Z. Cui, Q. Li, Z. Cao, et al., “Dense attention pyramid networks for multi-scale ship detection in sar images,” IEEE Transactions on Geoscience and Remote Sensing 57(11), 8983–8997 (2019). https://doi.org/10.1109/TGRS.2019.2923988
S. Ren, K. He, R. Girshick, et al., “Faster r-cnn: Towards real-time object detection with region proposal networks,” Advances in neural information processing systems 28, 91–99 (2015).
S. P. Mohanty, J. Czakon, K. A. Kaczmarek, et al., “Deep learning for understanding satellite imagery: An experimental survey,” Frontiers in Artificial Intelligence 3, 85 (2020). https://doi.org/10.3389/frai.2020.534696
X. Wang, L. Zhang, B. Zou, et al., “Polarimetric sar image classification based on kernel sparse representation,” in Compressive Sensing VII: From Diverse Modalities to Big Data Analytics, 10658, 106580L, International Society for Optics and Photonics (2018).
A. Femin and K. Biju, “Accurate detection of buildings from satellite images using cnn,” in 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), 1–5, IEEE (2020). https://doi.org/10.1109/ICECCE49384.2020.9179232
X. Wang, Z. Cao, Z. Cui, et al., “Polsar image classification based on deep polarimetric feature and contextual information,” Journal of Applied Remote Sensing 13, 1 (2019). https://doi.org/10.1117/1.JRS.13.034529
L. Ding, K. Zheng, D. Lin, et al., “Mp-resnet: Multipath residual network for the seman- tic segmentation of high-resolution polsar images,” IEEE Geoscience and Remote Sensing Letters , 1–5 (2021). https://doi.org/10.1109/LGRS.2021.3079925
L. Zhao and E. Chen, “Segmentation and classification of polsar data using spectral graph partitioning,” in MIPPR 2013: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 8921, 89210E, International Society for Optics and Pho- tonics (2013). https://doi.org/10.1117/12.2031128
A. Ouahabi and A. Taleb-Ahmed, “Deep learning for real-time semantic segmentation: Ap- plication in ultrasound imaging,” Pattern Recognition Letters 144, 27–34 (2021). https://doi.org/10.1016/j.patrec.2021.01.010
Y. Chen, X. He, J. Wang, et al., “The influence of polarimetric parameters and an object-based approach on land cover classification in coastal wetlands,” Remote Sensing 6(12), 12575– 12592 (2014). https://doi.org/10.3390/rs61212575
K. He, X. Zhang, S. Ren, et al., “Deep residual learning for image recognition,” in Proceed- ings of the IEEE conference on computer vision and pattern recognition, 770–778 (2016).
S. Xie, R. Girshick, P. Dolla´r, et al., “Aggregated residual transformations for deep neural networks,” arXiv preprint arXiv:1611.05431 (2016). https://doi.org/10.1109/CVPR.2017.634
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556 (2014).
P. Burlina, “Mrcnn: A stateful fast r-cnn,” in 2016 23rd International Conference on Pattern Recognition (ICPR), 3518–3523 (2016). https://doi.org/10.1109/ICPR.2016.7900179
T.-Y. Lin, P. Dolla´r, R. Girshick, et al., “Feature pyramid networks for object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2117–2125 (2017).
A. Chaurasia and E. Culurciello, “Linknet: Exploiting encoder representations for effi- cient semantic segmentation,” in 2017 IEEE Visual Communications and Image Processing (VCIP), 1–4, IEEE (2017). https://doi.org/10.1109/VCIP.2017.8305148
H. Zhao, J. Shi, X. Qi, et al., “Pyramid scene parsing network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2881–2890 (2017). https://doi.org/10.1109/CVPR.2017.660
S. Cloude and E. Pottier, “A review of target decomposition theorems in radar polarimetry,”IEEE Transactions on Geoscience and Remote Sensing 34(2), 498–518 (1996). https://doi.org/10.1109/36.485127
E. Pottier and J.-S. Lee, “Application of the h/a/alpha polarimetric decomposition theorem for unsupervised classification of fully polarimetric sar data based on the wishart distribution,” in SAR workshop: CEOS Committee on Earth Observation Satellites, 450, 335 (2000).
M. Neumann, L. Ferro-Famil, and E. Pottier, “A general model-based polarimetric decom- position scheme for vegetated areas,” in Proceedings of the 4th International Workshop on Science and Applications of SAR Polarimetry and Polarimetric Interferometry (ESRIN), Fras- cati, Italy, 26–30, Citeseer (2009).
A. Freeman, “Fitting a two-component scattering model to polarimetric sar data from forests,”IEEE Transactions on Geoscience and Remote Sensing 45(8), 2583–2592 (2007). https://doi.org/10.1109/TGRS.2007.897929
A. Freeman and S. Durden, “A three-component scattering model for polarimetric sar data,”IEEE Transactions on Geoscience and Remote Sensing 36(3), 963–973 (1998). https://doi.org/10.1109/36.673687
J. R. Huynen, “Stokes matrix parameters and their interpretation in terms of physical target properties,” in Polarimetry: Radar, infrared, visible, ultraviolet, and X-ray, 1317, 195–207, International Society for Optics and Photonics (1990). https://doi.org/10.1117/12.22083
A. Bhattacharya, A. Muhuri, S. De, et al., “Modifying the yamaguchi four-component de- composition scattering powers using a stochastic distance,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 8(7), 3497–3506 (2015). https://doi.org/10.1109/JSTARS.2015.2420683
G. Singh and Y. Yamaguchi, “Model-based six-component scattering matrix power decom- position,” IEEE Transactions on Geoscience and Remote Sensing 56(10), 5687–5704 (2018). https://doi.org/10.1109/TGRS.2018.2824322
R. Barnes, “Roll-invariant decompositions for the polarization covariance matrix,” in Pro- ceedings of the Polarimetry Technology Workshop, Redstone Arsenal, AL, USA, 1618 (1988).
W. A. Holm and R. M. Barnes, “On radar polarization mixed target state decomposition techniques,” in Proceedings of the 1988 IEEE National Radar Conference, 249–254, IEEE (1988).
M. Arii, J. J. van Zyl, and Y. Kim, “Adaptive model-based decomposition of polarimetric sar covariance matrices,” IEEE Transactions on Geoscience and Remote Sensing 49(3), 1104– 1113 (2011). https://doi.org/10.1109/TGRS.2010.2076285
W. An, Y. Cui, and J. Yang, “Three-component model-based decomposition for polarimetric sar data,” IEEE Transactions on Geoscience and Remote Sensing 48(6), 2732–2739 (2010). https://doi.org/10.1109/TGRS.2010.2041242
W. An, C. Xie, X. Yuan, et al., “Four-component decomposition of polarimetric sar images with deorientation,” IEEE Geoscience and Remote Sensing Letters 8(6), 1090–1094 (2011). https://doi.org/10.1109/LGRS.2011.2157078
Y. Yamaguchi, G. Singh, C. Yi, et al., “Comparison of model-based four-component scatter- ing power decompositions,” in Conference Proceedings of 2013 Asia-Pacific Conference on Synthetic Aperture Radar (APSAR), 92–95, IEEE (2013).
Y. Yamaguchi, T. Moriyama, M. Ishido, et al., “Four-component scattering model for po- larimetric sar image decomposition,” IEEE Transactions on Geoscience and Remote Sensing 43(8), 1699–1706 (2005). https://doi.org/10.1109/TGRS.2005.852084
E. Pottier, F. Sarti, M. Fitrzyk, et al., “Polsarpro-biomass edition: The new esa polarimetric sar data processing and educational toolbox for the future esa & third party fully polarimetric sar missions,” in ESA Living Planet Symposium 2019, (2019).
B, Mr. K., Balasaran, M., Vishwanath, K. G., SK, R., & Samuel, B. J. (2020). A Dynamic Multi Label Image Classification based on Recurrent Neural Networks. In International Journal of Recent Technology and Engineering (IJRTE) (Vol. 8, Issue 6, pp. 5093–5096). https://doi.org/10.35940/ijrte.f9817.038620
Crop Detection and Classification using Remote Sensing Images. (2019). In International Journal of Innovative Technology and Exploring Engineering (Vol. 8, Issue 12S, pp. 1165–1173). https://doi.org/10.35940/ijitee.k1318.10812s19
Kumar, P., & Rawat, S. (2019). Implementing Convolutional Neural Networks for Simple Image Classification. In International Journal of Engineering and Advanced Technology (Vol. 9, Issue 2, pp. 3616–3619). https://doi.org/10.35940/ijeat.b3279.129219