IMPLEMENTASI METODE CONVOLUTIONAL NEURAL NETWORK UNTUK KLASIFIKASI TANAMAN PADA CITRA RESOLUSI TINGGI

Erlyna Nour Arrofiqoh, Harintaka Harintaka

Abstract


Citra resolusi tinggi dari teknologi UAV (Unmanned Aerial Vehicle) dapat memberikan hasil yang baik dalam ekstraksi informasi sehingga dapat digunakan untuk monitoring dan updating data suatu wilayah. Pengambilan informasi dari citra dengan interpretasi visual sangat bergantung pada interpreter. Kendala utama interpretasi secara manual adalah saat melakukan pengenalan objek secara visual, khususnya pada objek tanaman pertanian. Kesalahan hasil asumsi interpreter dapat terjadi ketika citra yang diekstraksi memiliki objek yang kompleks dan memiliki karakter fisik yang hampir mirip apabila dilihat dari foto udara yang hanya memiliki band RGB (Red, Green, dan Blue). Penelitian ini mencoba mengimplementasikan pendekatan klasifikasi semantik secara otomatis yang dapat membedakan jenis tanaman sebagai alternatif pengenalan objek berdasarkan metode deep learning menggunakan Convolutional Neural Network (CNN). Metode CNN merupakan salah satu metode deep learning yang mampu melakukan proses pembelajaran mandiri untuk pengenalan objek, ekstraksi objek dan klasifikasi serta dapat diterapkan pada citra resolusi tinggi yang memiliki model distribusi nonparametrik. Pada penelitian ini, diterapkan algoritma CNN untuk membedakan jenis tanaman dengan memberikan label semantik dari objek jenis tanaman. Penelitian menggunakan 5 kelas jenis tanaman, yaitu kelas tanaman padi, bawang merah, kelapa, pisang, dan cabai. Proses learning jaringan menghasilkan akurasi 100% terhadap data training. Pengujian terhadap data validasi menghasilkan akurasi 93% dan akurasi terhadap data tes 82%. Hasil penelitian ini menunjukkan bahwa penggunaan metode CNN berpotensi untuk pendekatan pengenalan objek secara otomatis dalam membedakan jenis tanaman sebagai bahan pertimbangan interpreter dalam menentukan objek pada citra.

Keywords


Convolutional neural network, deep learning, citra resolusi tinggi, klasifikasi

Full Text:

PDF

References


Albelwi, S., & Mahmood, A. (2017). A Framework for Designing the Architectures of Deep Convolutional Neural Networks. Entropy, 19, 242.

Bejiga, M. B., Zeggada, A., Nouffidj, A., & Melgani, F. (2017). A convolutional neural network approach for assisting avalanche search and rescue operations with UAV imagery. Remote Sensing, 9(2). https://doi.org/10.3390/rs9020100

Castelluccio, M., Poggi, G, Sansone, C., Verdoliva, L. (2015). Land Use Classification in Remote Sensing Images by Convolutional Neural Networks. Diambil dari https://arxiv.org/pdf/1508.00092.pdf

Deng, L., & Yu, D. (2013). Deep Learning: Methods and Applications. Foundations and Trends® in Signal Processing, 7(3–4), 197–387. https://doi.org/10.1136/bmj.319.7209.0a

Giordan, D., Manconi, A., Remondino, F., & Nex, F. (2017). Use of unmanned aerial vehicles in monitoring application and management of natural hazards. Geomatics, Natural Hazards and Risk, 8(1), 1–4. https://doi.org/10.1080/19475705.2017.1315619

Heaton, J. (2015). Artificial Intelligence for Humans: Deep learning and neural networks of Artificial Intelligence for Humans Series. Createspace Independent Publishing Platform.

Hijazi, S., Kumar, R., & Rowen, C. (2015). Image Recognition Using Convolutional Neural Networks. Cadence Whitepaper, 1–12.

Hu, F., Xia, G. S., Hu, J., & Zhang, L. (2015). Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery. Remote Sensing, 7(11), 14680–14707. https://doi.org/10.3390/rs71114680

Katole, A. L., Yellapragada, K. P., Bedi, A. K., Kalra, S. S., & Siva Chaitanya, M. (2015). Hierarchical Deep Learning Architecture for 10K Objects Classification. Computer Science & Information Technology ( CS & IT ), (September), 77–93. https://doi.org/10.5121/csit.2015.51408

Kim, J., Sangjun, O., Kim, Y., & Lee, M. (2016). Convolutional Neural Network with Biologically Inspired Retinal Structure. Procedia Computer Science, 88, 145–154. https://doi.org/10.1016/j.procs.2016.07.418

Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Proceedings of the Twenty-Sixth Annual Conference on Neural Information Processing Systems. Lake Tahoe, NY, USA, 3–8 December 2012, 1097–1105.

Maggiori, E., Tarabalka, Y., Charpiat, G., & Alliez, P. (2016). Convolutional Neural Networks for LargeScale Remote-Sensing Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 55(2), 645–657. https://doi.org/10.1109/TGRS.2016.2612821

Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15, 1929– 1958. https://doi.org/10.1214/12-AOS1000

Tso, B., & Mather, P. M. (2009). Classification Methods for Remotely Sensed Data, Second Edition. CRC Press Taylor & Francis Group. Boca Raton.

Vedaldi, A., & Lenc, K. (2015). MatConvNet: Convolutional Neural Networks for MATLAB. In Proceedings of the 23rd ACM International Conference on Multimedia (hal. 689–692). New York, NY, USA: ACM. https://doi.org/10.1145/2733373.2807412

Yalcin, H., & Razavi, S. (2016). Plant classification using convolutional neural networks. 2016 Fifth International Conference on Agro-Geoinformatics (Agro-Geoinformatics), 1–5. https://doi.org/10.1109/AgroGeoinformatics.2016.7577698

Zeiler, M. D., & Fergus, R. (2014). Visualizing and Understanding Convolutional Networks. In D. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars (Ed.), Computer Vision -- ECCV 2014 (hal. 818–833). Cham: Springer International Publishing.

Zhang, C., Sargent, I., Pan, X., Gardiner, A., Hare, J., & Atkinson, P. M. (2018). VPRS-Based Regional Decision Fusion of CNN and MRF Classifications for Very Fine Resolution Remotely Sensed Images. IEEE Transactions on Geoscience and Remote Sensing, 1–15. https://doi.org/10.1109/TGRS.2018.2822783

Zhi, T., Duan, L. Y., Wang, Y., & Huang, T. (2016). Twostage pooling of deep convolutional features for image retrieval. In 2016 IEEE International Conference on Image Processing (ICIP) (hal. 2465–2469). https://doi.org/10.1109/ICIP.2016.7532802




DOI: http://dx.doi.org/10.24895/JIG.2018.24-2.810

Refbacks

  • There are currently no refbacks.


Copyright (c) 2018 GEOMATIKA

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Geomatika Indexed by:

 

Copyright of Geomatika