Semantic Segmentation Intended Satellite Image Enhancement Method Using Deep Auto Encoders
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Satellite imageries are at a greatest importance for land cover examining. Numerous studies have been conducted with satellite imagesand uses semantic segmentation techniques to extract information which has higher altitude viewpoint. The device which is taking theseimages must employee wireless communication links to send them to receiving ground stations. Wireless communications from a satelliteare inevitably affected due to transmission errors. Evidently images which are being transmitted are distorted because of the informationloss. Current semantic segmentation techniques are not made for segmenting distorted images. Traditional image enhancement methodshave their own limitations when they are used for satellite images enhancement. This paper proposes an auto-encoder based imagepre-enhancing method for satellite images. As a distorted satellite images dataset, images received from a real radio transmitter wereused. Training process of the proposed auto-encoder was done by letting it learn to produce a proper approximation of the sourceimage which was sent by the image transmitter. Unlike traditional image enhancing methods, the proposed method was able to providemore applicable image to a segmentation model. Results showed that by using the proposed pre-enhancing technique, segmentation resultshave been greatly improved. Enhancements made to the aerial images are contributed the correct assessment of land resources.
Abstract
Satellite imageries are at a greatest importance for land cover examining. Numerous studies have been conducted with satellite imagesand uses semantic segmentation techniques to extract information which has higher altitude viewpoint. The device which is taking theseimages must employee wireless communication links to send them to receiving ground stations. Wireless communications from a satelliteare inevitably affected due to transmission errors. Evidently images which are being transmitted are distorted because of the informationloss. Current semantic segmentation techniques are not made for segmenting distorted images. Traditional image enhancement methodshave their own limitations when they are used for satellite images enhancement. This paper proposes an auto-encoder based imagepre-enhancing method for satellite images. As a distorted satellite images dataset, images received from a real radio transmitter wereused. Training process of the proposed auto-encoder was done by letting it learn to produce a proper approximation of the sourceimage which was sent by the image transmitter. Unlike traditional image enhancing methods, the proposed method was able to providemore applicable image to a segmentation model. Results showed that by using the proposed pre-enhancing technique, segmentation resultshave been greatly improved. Enhancements made to the aerial images are contributed the correct assessment of land resources.
참고문헌 (31)
- A. Boguszewski, "LandCover. ai : Dataset for automatic mapping of buildings, woodlands, water and roads from aerial imagery", Proceedings of the IEEE, 2021, 1102~
- F. Gerard, "Land cover change in Europe between 1950 and 2000 determined employing aerial photography", Progress in Physical Geography : Earth and Environment, 34(2), pp.183~205 (2010)
- S. M. Azimi, "Towards multi-class object detection in unconstrained remote sensing imagery", Asian Conference on Computer Vision, pp.150~165 (2018), Springer
- W. Zhou, "Does spatial configuration matter? Understanding the effects of land cover pattern on land surface temperature in urban landscapes", Landscape and Urban Planning, 102(1), pp.54~63 (2011)
- Ananya Gupta, "Deep learning-based aerial image segmentation with open data for disaster impact assessment", Neurocomputing, 439, pp.22~33 (2021), Elsevier BV[DOI]
- J. Kim, "Denoising Auto-encoder based image enhancement for high resolution sonar image", 2017 IEEE Underwater Technology (UT)
- Q. Xiang, "Improved Denoising Auto-encoders for image denoising", 2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI 2018) (2018)
- V. Badrinarayanan, "Segnet : A deep convolutional encoder-decoder architecture for image segmentation", ~ (2015)
- O. Ronneberger, "U-Net : Convolutional networks for biomedical image segmentation", Medical Image Computing and Computer-Assisted Intervention – MICCAI, 234~241 (2015)
- Gaurav Sethi, "Segmentation of cancerous regions in liver using an edge-based and phase congruent region enhancement method", Computers & Electrical Engineering, 53, pp.244~262 (2016), Elsevier BV[DOI]
- Kebin Wu, "Robust tongue segmentation by fusing region-based and edge-based approaches", Expert Systems with Applications, 42(21), pp.8027~8038 (2015), Elsevier BV[DOI]
- P. Vijay, "Gray scale image segmentation using OTSU thresholding optimal approach", Journal for Research, 2(5), pp.20~24 (2016)
- Santiago Aja-Fernández, "A local fuzzy thresholding methodology for multiregion image segmentation", Knowledge-Based Systems, 83, pp.1~12 (2015), Elsevier BV[DOI]
- Nida M. Zaitoun, "Survey on Image Segmentation Techniques", Procedia Computer Science, 65, pp.797~806 (2015), Elsevier BV[DOI]
- Sijie Niu, "Robust noise region-based active contour model via local similarity factor for image segmentation", Pattern Recognition, 61, pp.104~119 (2017), Elsevier BV[DOI]
- E. Anjna, "Review of image segmentation technique", International Journal, 8(4), pp.36~39 (2017)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", ~ (2014)
- J. Long, "Fully convolutional networks for semantic segmentation", pp.3431~3440 (2015), CVPR
- A. Krizhevsky, "Imagenet classification with deep convolutional neural networks", Ad-vances in Neural Information Processing Systems, 25, pp.1097~1105 (2012)
- C. Szegedy, "Going deeper with convolutions", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1~9 (2015)
- H. Noh, "Learning deconvolution network for semantic segmentation", Proceedings of the IEEE International Conference on Computer Vision, pp.1520~1528 (2015)
- A. Chaurasia, "LinkNet: Exploiting encoder representations for efficient semantic segmentation" (2017), IEEE Visual Communications and Image Processing (VCIP)
- "ParseNet: Looking wider to see better, computer vision and pattern recognition" (2016)[URL]
- T. -Y. Lin, "Feature pyramid networks for object detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.2117~2125 (2017)
- M. L. L. de Oliveira, "Deep convolutional autoencoder applied for noise reduction in range-doppler maps of FMCW radars", 2020 IEEE International Radar Conference (RADAR)
- S. Park, "Dual autoencoder network for retinex-based low-light image enhancement", IEEE Access, 6 (2018)
- P. Schuch, "De-convolutional auto-encoder for enhancement of fingerprint samples", Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA) (2016)
- "Satellite images of Dubai Dataset"[URL]
- "Deep Learning using Rectified Linear Units (ReLU)" (2019)[URL]
- K. He, "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.770~778 (2016)
- D. P. Kingma, "Adam : A method for stochastic optimization", 3rd International Conference for Learning Representations (2015)