Browse > Article
http://dx.doi.org/10.7780/kjrs.2020.36.2.1.8

Semantic Segmentation of Drone Imagery Using Deep Learning for Seagrass Habitat Monitoring  

Jeon, Eui-Ik (R&D Center, Geostory Inc.)
Kim, Seong-Hak (R&D Center, Geostory Inc.)
Kim, Byoung-Sub (Korea Fisheries Resources Agency)
Park, Kyung-Hyun (Korea Fisheries Resources Agency)
Choi, Ock-In (Korea Fisheries Resources Agency)
Publication Information
Korean Journal of Remote Sensing / v.36, no.2_1, 2020 , pp. 199-215 More about this Journal
Abstract
A seagrass that is marine vascular plants plays an important role in the marine ecosystem, so periodic monitoring ofseagrass habitatsis being performed. Recently, the use of dronesthat can easily acquire very high-resolution imagery is increasing to efficiently monitor seagrass habitats. And deep learning based on a convolutional neural network has shown excellent performance in semantic segmentation. So, studies applied to deep learning models have been actively conducted in remote sensing. However, the segmentation accuracy was different due to the hyperparameter, various deep learning models and imagery. And the normalization of the image and the tile and batch size are also not standardized. So,seagrass habitats were segmented from drone-borne imagery using a deep learning that shows excellent performance in this study. And it compared and analyzed the results focused on normalization and tile size. For comparison of the results according to the normalization, tile and batch size, a grayscale image and grayscale imagery converted to Z-score and Min-Max normalization methods were used. And the tile size isincreased at a specific interval while the batch size is allowed the memory size to be used as much as possible. As a result, IoU was 0.26 ~ 0.4 higher than that of Z-score normalized imagery than other imagery. Also, it wasfound that the difference to 0.09 depending on the tile and batch size. The results were different according to the normalization, tile and batch. Therefore, this experiment found that these factors should have a suitable decision process.
Keywords
Seagrass habitat; Drone; Semantic segmentation; Deep learning; Convolutional neural network; U-Net;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Sameen, M.I., B. Pradhan, and O.S. Aziz, 2018. Classification of very high resolution aerial photos using spectral-spatial convolutional neural networks, Journal of Sensors, 1-16.
2 Sun, W. and R. Wang, 2018. Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with DSM, IEEE Geoscience and Remote Sensing Letters, 15(3): 474-478.   DOI
3 Thomas, F.I. and C.D. Cornelisen, 2003. Ammonium uptake by seagrass communities: effects of oscillatory versus unidirectional flow, Marine Ecology Progress Series, 247: 51-57.   DOI
4 Varia, N., A. Dokania, and J. Senthilnath, 2018. DeepExt: A Convolution Neural Network for Road Extraction using RGB images captured by UAV, Proc. of 2018 IEEE Symposium Series on Computational Intelligence, Bangalore, India, Nov. 18-21, pp. 1890-1895.
5 Yi, Y., Z. Zhang, W. Zhang, C. Zhang, W. Li, and T. Zhao, 2019. Semantic Segmentation of urban buildings from vhr remote sensing imagery using a deep convolutional neural network, Remote Sensing, 11(15): 1774.   DOI
6 You, Y., I. Gitman, and B. Ginsburg, 2017. Scaling sgd batch size to 32k for imagenet training, arXiv:1708.03888.
7 Zhang, Z., Q. Liu, and Y. Wang, 2018. Road extraction by deep residual u-net, IEEE Geoscience and Remote Sensing Letters, 15(5): 749-753.   DOI
8 Zhao, H., J. Shi, X. Qi, X. Wang, and J. Jia, 2017. Pyramid scene parsing network, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, Jul. 21-26, pp. 2881-2890.
9 Kim, J.B., J.I. Park, W.J. Choi, J.S. Lee, and K.S. Lee, 2010. Spatial distribution and ecological characteristics of Zostera marina and Zostera japonica in the Seomjin Estuary, Korean Journal of Fisheries and Aquatic Sciences, 43(4): 351-361 (in Korean with English abstract).   DOI
10 Kim, J.B., J.I. Park, C.S. Jung, P.Y. Lee, and K.S. Lee, 2009. Distributional range extension of the seagrass Halophila nipponica into coastal waters off the Korean peninsula, Aquatic Botany, 90(3):269-272.   DOI
11 Kingma, D.P. and J. Ba, 2014. Adam: A method for stochastic optimization, Proc. of 3rd International Conference on Learning Representations, San Diego, CA, USA, May 7-9, pp. 1-15.
12 Krizhevsky, A., I. Sutskever, and G.E. Hinton, 2012. Imagenet classification with deep convolutional neural networks, Proc. of Neural Information Processing Systems Conference, Lake Tahoe, Nevada, USA, Dec. 3-6, pp. 1097-1105.
13 LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner, 1998. Gradient-based learning applied to document recognition, Proceedings of the IEEE, 86(11):2278-2324.   DOI
14 Lee, K.S. and S.Y. Lee, 2003. The seagrasses of the Republic of Korea, In: Short, F.T., Green, E.P. (Ed.), World atlas of seagrasses: present status and future conservation, University of California Press, Berkeley, USA, pp. 193-198.
15 Liu, L., 2019. Semantic Segmentation of Urban Airborne Oblique Images, University of Twente, Enschede, Netherlands.
16 Li, R., W. Liu, L. Yang, S. Sun, W. Hu, F. Zhang, and W. Li, 2018. Deepunet: A deep fully convolutional network for pixel-level sea-land segmentation, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(11):3954-3962.   DOI
17 Li, W., C. He, J. Fang, and H. Fu, 2018. Semantic Segmentation Based Building Extraction Method Using Multi-Source GIS Map Datasets and Satellite Imagery, Proc. of 2018 Computer Vision and Pattern Recognition Workshops, Salt Lake City, Utah, USA, Jun. 18-22, pp. 238-241.
18 Alickovic, E. and A. Subasi, 2019. Normalized neural networks for breast cancer classification, Proc. of International Conference on Medical and Biological Engineering, Banja Luka, Bosnia and Herzegovina, May 16-18, pp. 519-524.
19 Badrinarayanan, V., A. Kendall, and R. Cipolla, 2017. Segnet: A deep convolutional encoder-decoder architecture for image segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12): 2481-2495.   DOI
20 Buscombe, D. and A.C. Ritchie, 2018. Landscape classifi-cation with deep neural networks, Geosciences, 8(7): 244.   DOI
21 Long, J., E. Shelhamer, and T. Darrell, 2015. Fully convolutional networks for semantic segmentation, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA, Jun. 18-22, pp. 3431-3440.
22 Masters, D. and C. Luschi, 2018. Revisiting small batch training for deep neural networks, arXiv:1804.07612.
23 Okatani, T. and M. Saito, 2015. Deep learning, Koudansha, Tokyo, Japan, pp. 101-121.
24 Park, J.I., J.Y. Park, and M.H. Son, 2012. Seagrass Distribution in Jeju and Chuja Islands, Korean Journal of Environmental Biology, 30(4): 339-348 (in Korean with English abstract).   DOI
25 Park, S.W. and Y.W. Lee, 2019. Detection of forest disaster using high-resolution satellite images with semantic segmentation, The Association of Korean Photo-Geographers, 28(4): 87-101 (in Korean with English abstract).   DOI
26 Ruder, S., 2016. An overview of gradient descent optimization algorithms, arXiv preprint, arXiv:1609.04747.
27 Paszke, A., A. Chaurasia, S. Kim, and E. Culurciello, 2016. Enet: A deep neural network architecture for real-time semantic segmentation, arXiv:1606.02147.
28 Peng, B., Y. Li, L. He, K. Fan, and L. Tong, 2018. Road Segmentation of UAV RS Image Using Adversarial Network with Multi-Scale Context Aggregation, Proc. of 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, Jul. 22-27, pp. 6935-6938.
29 Ronneberger, O., P. Fischer, and T. Brox, 2015. U-net:Convolutional networks for biomedical image segmentation, Proc. of International Conference on Medical Image Computing and Computerassisted Intervention, Munich, Germany, Oct. 5-9, pp. 234-241.
30 Chen, L.C., G. Papandreou, I. Kokkinos, K. Murphy, and A.L. Yuille, 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4): 834-848.   DOI
31 Fu, G., C. Liu, R. Zhou, T. Sun, and Q. Zhang, 2017. Classification for high resolution remote sensing imagery using a fully convolutional network, Remote Sensing, 9(5): 498.   DOI
32 Goyal, P., P. Dollear, R. Girshick, P. Noordhuis, L. Wesolowski, A. Kyrola, A. Tulloch, Y. Jia, and K. He, 2017. Accurate, large minibatch sgd:Training imagenet in 1 hour, arXiv:1706.02677.
33 Keskar, N.S., D. Mudigere, J. Nocedal, M. Smelyanskiy, and P.T.P. Tang, 2016. On large-batch training for deep learning: Generalization gap and sharp minima, Proc. of 5th International Conference on Learning Representations, Palais des Congres Neptune, Toulon, France, Apr. 24-26, pp. 1-16.
34 Guo, Z., H. Shengoku, G. Wu, Q. Chen, W. Yuan, X. Shi, X. Shao, Y. Xu, and R. Shibasaki, 2018. Semantic segmentation for urban planning maps based on U-Net, Proc. of 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, Jul. 22-27, pp. 6187-6190.
35 Ioffe, S., 2017. Batch renormalization: Towards reducing minibatch dependence in batch-normalized model, Proc. of 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, Jul. 22-27, pp. 1945-1953.
36 Kampffmeyer, M., A.B. Salberg, and R. Jenssen, 2016. Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Las Vegas, NV, USA, Jun. 26-Jul. 1, pp. 1-9.
37 Khalel, A. and M. El-Saban, 2018. Automatic pixelwise object labeling for aerial imagery using stacked u-nets, arXiv:1803.04953.