International Journal of Applied Science and Engineering
Published by Chaoyang University of Technology

Novian Adi Prasetyoa, Pranowob and Albertus Joko Santosob*

aDepartement of Informatics Engineering, Institut Teknologi Telkom Purwokerto, Jalan D.I. Panjaitan, Indonesia
bMagister Teknik Informatika, Universitas Atma Jaya Yogyakarta, Jalan Babarsari, Yogyakarta, Indonesia


 

Download Citation: |
Download PDF


ABSTRACT


Indonesia is the largest industry of crude palm oil (CPO) center in the world after Malaysia and Thailand [1]. Based on data from the Ministry of Agriculture 2018 [2], Indonesia produced 27.78 million tons CPO in 2013 and increased to 37.81 million tons in 2017, with an average growth of 2.13% per year in the period 2013-2017. In 2013, the value of Indonesia's CPO exports to the world amounted to USD 17.67 million or 59.97% of Indonesia's total plantation commodity exports and increased to USD 21.25 million or 66.81% in 2017 with an average growth of 26.41% per year. CPO is a source of non-oil foreign exchange for Indonesia, so the enhancement of CPO production in Indonesia is expected to improve the welfare of the nation.

During 2013-2017, the growth of the area of oil palm plantations in Indonesia decreased -0.52% [2], the decline is expected not to affect the amount of CPO production. One of the things that affect CPO production is the primary raw material availability of palm fresh fruit bunches (FFB). The raw material availability of FFB can be predicted by several methods such as Fuzzy Rule-Based Time Series Method [3] and linear regression [4]. Both forecasting methods only calculate the needs of raw material and cannot predict the availability of real raw material. Farmers can do calculations from close range and long distance. The close range calculation of the uneven and large FFB has been done manually and it is quite difficult and spends a lot of time to do. Long distance calculations certainly have a higher level of difficulty. In addition to limited vision, loss of concentration also increases the difficulty of distance calculation.


Keywords: Palm oil fresh fruit bunches (FFB); Faster R-CNN; computer vision; object detection.


Share this article with your colleagues

 


REFERENCES


  1. [1] Palm Oil Production by Country in 1000 MT. 2019. [Website Link]

  2. [2] Kariyasa, K., Susanti, A. A. and Waryanto, B. 2018. Center for Agricultural Data and Information System Ministry of Agriculture Republic of Indonesia. Agricultulral Statistics

  3. [3] Rahim, N. F., Othman, M., Sokkalingam, R. and Abdul Kadir, E. 2018. Forecasting Crude Palm Oil Prices Using Fuzzy Rule-Based Time Series Method. IEEE Access, 6: 32216–32224.  [Publisher Site]

  4. [4] Oettli, P., Behera, S. K. and Yamagata, T. 2018. Climate Based Predictability of Oil Palm Tree Yield in Malaysia. Rep, 8, 1: 1–13.  [Publisher Site]

  5. [5] Ciocca, G., Napoletano, P. and Schettini, R. 2018. CNN-based features for retrieval and classification of food images, Comput. Image Underst, 176: 70–77.  [Publisher Site]

  6. [6] Anwar, I. and Islam, N. U. 2017. Learned features are better for ethnicity classification. Inf. Technol, 17, 3: 152–164.  [Publisher Site]

  7. [7] Cho, S. W., Baek, N. R., Kim, M. C., Koo, J. H., Kim, J. H. and Park, K. R. 2018. Face detection in nighttime images using visible-light camera sensors with two-step faster region-based convolutional neural network. Sensors (Switzerland), 18, 9.  [Publisher Site]

  8. [8] Liu, T. and Stathaki, T. 2018. Faster R-CNn for robust pedestrian detection using semantic segmentation network. Neurorobot, 12: 1–10.  [Publisher Site]

  9. [9] Cao et al, X. 2018. Region based CNN for foreign object debris detection on airfield pavement. Sensors (Switzerland), 18, 3: 1–14.  [Publisher Site]

  10. [10] Rahnemoonfar, M. and Sheppard, C. 2017. Deep count: Fruit counting based on deep simulated learning. Sensors (Switzerland), 17, 4: 1–12.  [Publisher Site]

  11. [11] Liu, G., Mao, S. and Kim, J. H. 2019. A Mature-Tomato Detection Algorithm Using Machine Learning and Color Analysis. Sensors, 19, 9: 2023. [Publisher Site]

  12. [12] Muhammad, U. R., Svanera, M., Leonardi, R. and Benini, S. 2018. Hair detection, segmentation, and hairstyle classification in the wild. Image Vis. Comput, 71: 25–37.  [Publisher Site]

  13. [13] Bargoti, S. and Underwood, J. P. 2017. Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards. F. Robot, 34, 6: 1039–1060.  [Publisher Site]

  14. [14] Zhang, C., Yue, P., Di, L. and Wu, Z. 2018. Automatic Identification of Center Pivot Irrigation Systems from Landsat Images Using Convolutional Neural Networks. Agriculture, 8, 10:  [Publisher Site]

  15. [15] Maldonado, W. and Barbosa, J. C. 2016. Automatic green fruit counting in orange trees using digital images. Electron. Agric, 127: 572–581.  [Publisher Site]

  16. [16] Bargoti, S. and Underwood, J. 2017. Deep fruit detection in orchards. - IEEE Int. Conf. Robot. Autom, 3626–3633.  [Publisher Site]

  17. [17] Koirala, A., Walsh, K. B., Wang, Z. and McCarthy, C. 2019. Deep learning – Method overview and review of use for fruit detection and yield estimation. Electron. Agric, 162: 219–234.  [Publisher Site]

  18. [18] Kestur, R., Meduri, A. and Narasipura, O. 2019. MangoNet: A deep semantic segmentation architecture for a method to detect and count mangoes in an open orchard. Appl. Artif. Intell, 77: 59–69.  [Publisher Site]

  19. [19] Habaragamuwa, H., Ogawa, Y., Suzuki, T., Shiigi ,T., Ono, M. and Kondo, N. 2018. Detecting greenhouse strawberries (mature and immature), using deep convolutional neural network. Agric. Environ. Food, 11, 3: 127–138.  [Publisher Site]

  20. [20] Kamilaris, A. and Prenafeta-Boldú, F. X. 2018. Deep learning in agriculture: A survey. Electron. Agric, 147: 70–90.  [Publisher Site]

  21. [21] Brooks, Justin. 2019. COCO Annotator. (June 11, 2019).  [Website Link]

  22. [22] Lin et al, T. Y. 2014. Microsoft COCO: Common objects in context. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), 8693 LNCS, 5: 740–755.

  23. [23] Xiang, X., Lv, N., Guo, X., Wang, S. and El Saddik, A. 2018. Engineering vehicles detection based on modified faster R-CNN for power grid surveillance. Sensors (Switzerland), 18, 7.  [Publisher Site]

  24. [24] Girshick, R., Donahue, J., Member, S. and Darrell, T. 2015. Region-based Convolutional Networks for Accurate Object Detection and Segmentation, 8828: 1–16.  [Publisher Site]

  25. [25] Uijlings, J. R. R., Van, K. E. A. de Sande, T. Gevers and Smeulders, A. W. M. 2013. Selective search for object recognition. J. Comput. Vis.  [Publisher Site]

  26. [26] Girshick, R. 2015. Fast R-CNN. IEEE Int. Conf. Comput. Vis, 1440–1448.  [Publisher Site]

  27. [27] Ren, S., He, K., Girshick, R. and Sun, J. 2017. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell, 39, 6: 1137–1149.  [Publisher Site]

  28. [28] Huang et al, J. 2017. Speed/accuracy trade-offs for modern convolutional object detectors. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR, 2017-Janua, 3296–3305.  [Publisher Site]

  29. [29] Szegedy, C. et al. 2015. Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–12. [Publisher Site]

  30. [30] Ioffe, S. and Szegedy, C. 2015. Batch Normalization : Accelerating Deep Network Training by Reducing Internal Covariate Shift. Learn

  31. [31] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. and Wojna, Z. 2016. Rethinking the Inception Architecture for Computer Vision. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit, 2016-Decem, 2818–2826.  [Publisher Site]

  32. [32] Szegedy, C., Ioffe, S., Vanhoucke, V. and Alemi, A. 2016. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. Vis. Pattern Recognit

  33. [33] Schillaci, G., Pennisi, A., Franco, F. and Longo, D. 2012. Detecting tomato crops in greenhouses using a vision based method. Conf. Saf.Heal. Welf. Agric. Agro-food Syst, 1: 20–26.

  34. [34] He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 770–778, 2016. [Publisher Site]

  35. [35] Girshick, R., Donahue, J., Darrell, T. and Malik, J. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit, 580–587. [Publisher Site]


ARTICLE INFORMATION


Received: 2019-12-05
Revised: 2020-02-29
Accepted: 2020-03-15
Publication Date: 2020-06-01


Cite this article:

Prasetyoa, N.A., Pranowob, Santosob, A.J. 2020. Automatic detection and calculation of palm oil fresh fruit bunches using faster R-CNN. International Journal of Applied Science and Engineering, 17, 121–134. https://doi.org/10.6703/IJASE.202005_17(2).121


We use cookies on this website to improve your user experience. By using this site you agree to its use of cookies.