Comparison of Classical Computer Vision vs. Convolutional Neural Networks for Weed Mapping in Aerial Images

Paulo César Pereira Júnior, Alexandre Monteiro, Rafael da Luz Ribeiro, Antonio Carlos Sobieranski, Aldo von Wangenheim

Abstract


In this paper, we present a comparison between convolutional neural networks and classical
computer vision approaches, for the specific precision agriculture problem of weed mapping on sugarcane fields aerial images. A systematic literature review was conducted to find which computer vision methods are being used on this specific problem. The most cited methods were implemented, as well as four models of convolutional neural networks. All implemented approaches were tested using the same dataset, and their results were quantitatively and qualitatively analyzed. The obtained results were compared to a human expert made ground truth, for validation. The results indicate that the convolutional neural networks present better precision and generalize better than the classical models

Keywords


Convolutional Neural Networks; Deep Learning; Digital Image Processing; Precision Agriculture; Semantic Segmentation; Unmanned Aerial Vehicles

Full Text:

PDF

References


MCBRATNEY, A. et al. Future directions of precision agriculture. Precision agriculture, Springer, v. 6, n. 1, p. 7–23, 2005.

REYNS, P. et al. A review of combine sensors for precision farming. Precision Agriculture, Springer, v. 3, n. 2, p. 169–182, 2002.

VIDOVIĆ, I.; CUPEC, R.; HOCENSKI, Ž. Crop row detection by global energy minimization. Pattern Recognition, Elsevier, v. 55, p. 68–86, 2016.

LOUARGANT, M. et al. Unsupervised classification algorithm for early weed detection in row-crops by combining spatial and spectral information. Remote Sensing, Multidisciplinary Digital Publishing Institute, v. 10, n. 5, p. 761, 2018.

EVERINGHAM, M. et al. The pascal visual object classes (voc) challenge. International journal of computer vision, Springer, v. 88, n. 2, p. 303–338, 2010.

ZHOU, B. et al. Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision, Springer, v. 127, n. 3, p. 302–321, 2019.

JÚNIOR, P. C. P.; WANGENHEIM, A. V.; MONTEIRO, A. Weed Mapping on Aerial Images - A Systematic Literature Review. [S.l.], 2019. Doi: 10.13140/RG.2.2.34979.71204. Disponı́vel em: hhttp://www.incod.ufsc.br/wp-content/uploads/2019/05/INCoD.LAPIX .01.2019.E.SLR .Weed.Mapping.Aerial.Images.pdf.

KITCHENHAM, B. Procedures for performing systematic reviews. Keele University, Joint Technical Report TR/SE-0401, v. 33, n. 2004, p. 1–26, 2004.

CASTILLEJO-GONZÁLEZ, I. L. et al. Evaluation of pixel-and object-based approaches for mapping wild oat (avena sterilis) weed patches in wheat fields using quickbird imagery for site-specific management. European Journal of Agronomy, Elsevier, v. 59, p. 57–66, 2014.

PÉREZ-ORTIZ, M. et al. A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method. Applied Soft Computing, Elsevier, v. 37, p. 533–544, 2015.

PÉREZ-ORTIZ, M. et al. Machine learning paradigms for weed mapping via unmanned aerial vehicles. In: IEEE. Computational Intelligence (SSCI), 2016 IEEE Symposium Series on. [S.l.], 2016. p. 1–8.

DAVID, L. C. G.; BALLADO, A. H. Vegetation indices and textures in object-based weed detection from uav imagery. In: IEEE. Control System, Computing and Engineering (ICCSCE), 2016 6th IEEE International Conference on. [S.l.], 2016. p. 273–278.

FERREIRA, A. dos S. et al. Weed detection in soybean crops using convnets. Computers and Electronics in Agriculture, Elsevier, v. 143, p. 314–324, 2017.

ISHIDA, T. et al. A novel approach for vegetation classification using uav-based hyperspectral imaging. Computers and

electronics in agriculture, Elsevier, v. 144, p. 80–85, 2018.

LOTTES, P. et al. Uav-based crop and weed classification for smart farming. In: IEEE. Robotics and Automation (ICRA), 2017 IEEE International Conference on. [S.l.], 2017. p. 3024–3031.

GAO, J. et al. Fusion of pixel and object-based features for weed mapping using unmanned aerial vehicle imagery. International Journal of Applied Earth Observation and Geoinformation, Elsevier, v. 67, p. 43–53, 2018.

PÉREZ-ORTIZ, M. et al. Selecting patterns and features for between-and within-crop-row weed mapping using uav imagery. Expert Systems with Applications, Elsevier, v. 47, p. 85–94, 2016.

BAH, M. D.; HAFIANE, A.; CANALS, R. Weeds detection in uav imagery using slic and the hough transform. In: IEEE. Image Processing Theory, Tools and Applications (IPTA), 2017 Seventh International Conference on. [S.l.], 2017. p. 1–6.

SA, I. et al. weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming. IEEE Robotics and Automation Letters, IEEE, v. 3, n. 1, p. 588–595, 2018.

BAH, M. D. et al. Deep learning based classification system for identifying weeds using high-resolution uav imagery. In: SPRINGER. Science and Information Conference. [S.l.], 2018. p. 176–187.

GRUDIC, G.; MULLIGAN, J. Outdoor path labeling using polynomial mahalanobis distance. In: Robotics: Science and Systems. [S.l.: s.n.], 2006.

LOPES, M. D. et al. A web-based tool for semi-automated segmentation of histopathological images using nonlinear color classifiers. In: 2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS). [S.l.: s.n.], 2016. p. 247–252.

CARVALHO, L. E. et al. Improving graph-based image segmentation using nonlinear color similarity metrics. International Journal of Image and Graphics, v. 15, n. 04, p. 1550018, 2015.

CARVALHO, L. E. et al. Hybrid color segmentation method using a customized nonlinear similarity function. International Journal of Image and Graphics, v. 14, n. 01n02, p. 1450005, 2014.

SOBIERANSKI, A. C. et al. Color skin segmentation based on non-linear distance metrics. In: BAYRO-CORROCHANO, E.; HANCOCK, E. (Ed.). Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Cham: Springer International Publishing, p. 143–150, 2014.

SOBIERANSKI, A. C.; COMUNELLO, E.; WANGENHEIM, A. von. Learning a nonlinear distance metric for supervised region-merging image segmentation. Computer Vision and Image Understanding, v. 115, n. 2, p. 127 - 139, 2011.

SOBIERANSKI, A. C. et al. Learning a color distance metric for region-based image segmentation. Pattern Recognition Letters, v. 30, n. 16, p. 1496 – 1506, 2009.

SOBIERANSKI, A. C. et al. Learning a nonlinear color distance metric for the identification of skin immunohistochemical staining. In: 2009 22nd IEEE International Symposium on Computer-Based Medical Systems. [S.l.: s.n.], .p. 1–7, 2009.

JAKKULA, V. Tutorial on support vector machine (svm). School of EECS, Washington State University, v. 37, 2006.

BREIMAN, L. Random forests. Machine learning, Springer, v. 45, n. 1, p. 5–32, 2001.

WANG, A.; ZHANG, W.; WEI, X. A review on weed detection using ground-based machine vision and image processing techniques. Computers and Electronics in Agriculture, Elsevier, v. 158, p. 226–240, 2019.

GABOR, D. Theory of communication. part 1: The analysis of information. Journal of the Institution of Electrical Engineers-Part III: Radio and Communication Engineering, IET, v. 93, n. 26, p. 429–441, 1946.

ILEA, D. E.; WHELAN, P. F. Image segmentation based on the integration of colour–texture descriptors—a review. Pattern Recognition, Elsevier, v. 44, n. 10-11, p. 2479–2501, 2011.

SOBIERANSKI, A. C. et al. A fast gabor filter approach for multi-channel texture feature discrimination. In: BAYRO-CORROCHANO, E.; HANCOCK, E. (Ed.). Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Cham: Springer International Publishing, p. 135–142, 2014.

JAIN, A.; FARROKHNIA, F. Unsupervised texture segmentation using gabor filters. PR, v. 24, n. 12, p. 1167 – 1186, 1991.

HARALICK, R.; SHANMUGAM, K.; DINSTEIN, I. Textural features for image classification. IEEE Trans Syst. Man. Cybern., SMC-3, p. 610–621, 01 1973.

LECUN, Y. et al. Gradient-based learning applied to document recognition. Proceedings of the IEEE, IEEE, v. 86, n. 11, p. 2278–2324, 1998.

KRIZHEVSKY, A.; SUTSKEVER, I.; HINTON, G. E. Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems. [S.l.: s.n.], p. 1097–1105, 2012.

SIMONYAN, K.; ZISSERMAN, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.

SZEGEDY, C. et al. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. [S.l.: s.n.], 2015. p. 1–9.

GIRSHICK, R. Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision. [S.l.: s.n.], p. 1440–1448, 2015.

SERMANET, P. et al. Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229, 2013.

SZEGEDY, C. et al. Scalable, high-quality object detection. arXiv preprint arXiv:1412.1441, 2014.

LIN, T.-Y. et al. Feature pyramid networks for object detection. In: CVPR. [S.l.: s.n.], 2017. v. 1, n. 2, p. 4.

GIDARIS, S.; KOMODAKIS, N. Object detection via a multi-region and semantic segmentation-aware cnn model. In: Proceedings of the IEEE International Conference on Computer Vision. [S.l.: s.n.], p. 1134–1142, 2015.

DAI, J.; HE, K.; SUN, J. Instance-aware semantic segmentation via multi-task network cascades. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S.l.: s.n.], p. 3150–3158, 2016.

HARIHARAN, B. et al. Hypercolumns for object segmentation and fine-grained localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition. [S.l.: s.n.], p. 447–456, 2015.

SHELHAMER, E.; LONG, J.; DARRELL, T. Fully convolutional networks for semantic segmentation. arXiv preprint arXiv:1605.06211, 2016.

THOMA, M. A survey of semantic segmentation. arXiv preprint arXiv:1602.06541, 2016.

BADRINARAYANAN, V.; KENDALL, A.; CIPOLLA, R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint arXiv:1511.00561, 2015.

RONNEBERGER, O.; FISCHER, P.; BROX, T. U-net: Convolutional networks for biomedical image segmentation. In: SPRINGER. International Conference on Medical image computing and computer-assisted intervention. [S.l.], p. 234–241, 2015.

ZHAO, H. et al. Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition. [S.l.: s.n.], p. 2881–2890, 2017.

POHLEN, T. et al. Full resolution residual networks for semantic segmentation in street scenes. arXiv preprint, 2017.

HE, K. et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. [S.l.: s.n.], p. 770–778, 2016.

RAHMAN, M. A.; WANG, Y. Optimizing intersection-over-union in deep neural networks for image segmentation. In: SPRINGER. International symposium on visual computing. [S.l.], p. 234–244, 2016.

RIJSBERGEN, C. J. V. Information Retrieval. 2nd. ed. Newton, MA, USA: Butterworth-Heinemann, 1979.

KINGMA, D. P.; BA, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.




DOI: https://doi.org/10.22456/2175-2745.97835

Copyright (c) 2020 Paulo César Pereira Júnior, Alexandre Monteiro, Rafael da Luz Ribeiro, Antonio Carlos Sobieranski, Aldo von Wangenheim

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

Indexing databases:
        

Acknowledgments: