Uma Implementação Baseada em Mask R-CNN para Detecção de Insetos em Imagens Digitais
Resumo
A tarefa manual de contagem e identificação de pequenos insetos, como afídeos e parasitoides, capturados em armadilhas de campo do tipo cor, é uma atividade exaustiva, demorada e não escalável em centros de pesquisa agrícola. Essas atividades envolvem complexidade na triagem dos elementos de interesse e utilização de lupas e microscópios. Recentes avanços em inteligência artificial e computação de alto desempenho têm viabilizado o desenvolvimento de soluções de visão computacional eficientes para monitoramento de pragas e identificação de doenças em plantas. Nesse contexto, esse artigo apresenta uma rotina para contagem e identificação automática de insetos em imagens, geradas pela digitalização de amostras capturadas pelas armadilhas nas estações experimentais da Embrapa Trigo. Para a implementação foi utilizado um pequeno conjunto de imagens, técnicas de processamento de imagens e a abordagem convolucional de dois estágios Mask R-CNN. Os resultados preliminares indicam uma precisão média (mAP) de 60,4%, e mostram alguns pontos que podem incrementar a eficiência da abordagem proposta.Referências
L. C. Wright and W. W. Cone, "Population Dynamics of Brachycorynella asparagi (Homoptera: Aphididae) on Undisturbed Asparagus in Washington State," Environmental Entomology, vol. 17, no. 5, pp. 878– 886, 10 1988.
P. R. V. d. S. Pereira, J. R. Salvadori, and D. Lau, "Identificação de adultos ápteros e alados das principais espécies de afídeos (hemiptera: Aphididae) associadas acereais de inverno no brasil," Embrapa Trigo, Comunicado Técnico online, 258, Tech. Rep., 2009. [Online]. Available: http://www.cnpt.embrapa.br/biblio/co/p co258.htm
E. A. Lins, J. P. M. Rodriguez, S. I. Scoloski, J. Pivato, M. B. Lima, J. M. C. Fernandes, P. R. V. da Silva Pereira, D. Lau, and R. Rieder, "A method for counting and classifying aphids using computer vision," Computers and Electronics in Agriculture, vol. 169, p. 105200, 2020.
A. Picon, A. Alvarez-Gila, M. Seitz, A. Ortiz-Barredo, J. Echazarra, and A. Johannes, "Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild," Computers and Electronics in Agriculture, 2018. [Online]. Available: https: //doi.org/10.1016/j.compag.2018.04.002
L. Liu, R. Wang, C. Xie, P. Yang, F. Wang, S. Sudirman, and W. Liu, "PestNet: An End-to-End Deep Learning Approach for Large-Scale Multi-Class Pest Detection and Classification," IEEE Access, vol. 7, pp. 45 301–45 312, 2019. [Online]. Available: https://doi.org/10.1109/ACCESS.2019.2909522
M. C. Bakkay, S. Chambon, H. A. Rashwan, C. Lubat, and S. Barsotti, "Automatic detection of individual and touching moths from trap images by combining contour-based and region-based segmentation," IET Computer Vision, vol. 12, no. 2, pp. 138–145, 2018. [Online]. Available: https://doi.org/10.1049/iet-cvi.2017.0086.
V. Partel, L. Nunes, P. Stansly, and Y. Ampatzidis, "Automated visionbased system for monitoring Asian citrus psyllid in orchards utilizing artificial intelligence," Computers and Electronics in Agriculture, vol. 162, pp. 328–336, jul 2019.
Y. Sun, X. Liu, M. Yuan, L. Ren, J. Wang, and Z. Chen, "Automatic in-trap pest detection using learning for pheromone-based Dendroctonus valens monitoring," Biosystems Engineering, vol. 176, pp. 140–150, dec 2018.
A. Kamilaris and F. X. Prenafeta-Boldu, "Deep learning in agriculture: A survey," Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018. [Online]. Available: https://doi.org/10.1016/j.compag.2018.02.016.
Y. Zhong, J. Gao, Q. Lei, and Y. Zhou, "A vision-based counting and recognition system for flying insects in intelligent agriculture," Sensors, vol. 18, no. 5, p. 1489, 2018.
W. Li, P. Chen, B. Wang, and C. Xie, "Automatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline," Scientific Reports, vol. 9, no. 1, 2019.
A. Fuentes, S. Yoon, S. C. Kim, and D. S. Park, "A robust deep-learningbased detector for real-time tomato plant diseases and pests recognition," Sensors (Switzerland), vol. 17, no. 9, 2017.
J. Chen, Y. Fan, T. Wang, C. Zhang, Z. Qiu, and Y. He, "Automatic Segmentation and Counting of Aphid Nymphs on Leaves Using Convolutional Neural Networks," Agronomy, vol. 8, no. 8, 2018.
A. Krizhevsky, I. Sutskever, and G. Hinton, "Imagenet classification with deep convolutional neural networks," Neural Information Processing Systems, vol. 25, 01 2012.
S. Ren, K. He, R. Girshick, and J. Sun, "Faster r-cnn: Towards real-time object detection with region proposal networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137– 1149, 2016.
J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3431–3440.
P. Fischer, A. Dosovitskiy, and T. Brox, "Descriptor matching with convolutional neural networks: a comparison to SIFT," CoRR, vol. abs/1405.5769, 2014, withdrawn. [Online]. Available: http: //arxiv.org/abs/1405.5769.
Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436–444, 2015.
J. Dai, Y. Li, K. He, and J. Sun, "R-fcn: Object detection via region-based fully convolutional networks," in Proceedings of the 30th International Conference on Neural Information Processing Systems, ser. NIPS’16. Red Hook, NY, USA: Curran Associates Inc., 2016, p. 379–387. [Online]. Available: https://dl.acm.org/doi/10.5555/3157096. 3157139.
K. He, G. Gkioxari, P. Dollar, and R. Girshick, "Mask r-cnn," in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2980–2988. [Online]. Available: https://doi.org/10.1109/ICCV.2017.322.
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, "SSD: Single Shot MultiBox Detector," in Computer Vision – ECCV 2016, B. Leibe, J. Matas, N. Sebe, and M. Welling, Eds. Cham: Springer International Publishing, 2016, pp. 21–37.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779–788. [Online]. Available: https://doi.org/10.1109/CVPR.2016.91.
T. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, "Focal loss for ´ dense object detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 2, pp. 318–327, 2018. [Online]. Available: https://doi.org/10.1109/TPAMI.2018.2858826.
A. Nazri, N. Mazlan, and F. Muharam, "PENYEK: Automated brown planthopper detection from imperfect sticky pad images using deep convolutional neural network," PLOS ONE, vol. 13, no. 12, p. e0208501, dec 2018. [Online]. Available: http://dx.plos.org/10.1371/ journal.pone.0208501.
W. Abdulla, "Mask r-cnn for object detection and instance segmentation on keras and tensorflow," 2017. [Online]. Available: https://github.com/ matterport/Mask RCNN
P. R. V. d. S. Pereira, J. R. Salvadori, and D. Lau, "Identificação de adultos ápteros e alados das principais espécies de afídeos (hemiptera: Aphididae) associadas acereais de inverno no brasil," Embrapa Trigo, Comunicado Técnico online, 258, Tech. Rep., 2009. [Online]. Available: http://www.cnpt.embrapa.br/biblio/co/p co258.htm
E. A. Lins, J. P. M. Rodriguez, S. I. Scoloski, J. Pivato, M. B. Lima, J. M. C. Fernandes, P. R. V. da Silva Pereira, D. Lau, and R. Rieder, "A method for counting and classifying aphids using computer vision," Computers and Electronics in Agriculture, vol. 169, p. 105200, 2020.
A. Picon, A. Alvarez-Gila, M. Seitz, A. Ortiz-Barredo, J. Echazarra, and A. Johannes, "Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild," Computers and Electronics in Agriculture, 2018. [Online]. Available: https: //doi.org/10.1016/j.compag.2018.04.002
L. Liu, R. Wang, C. Xie, P. Yang, F. Wang, S. Sudirman, and W. Liu, "PestNet: An End-to-End Deep Learning Approach for Large-Scale Multi-Class Pest Detection and Classification," IEEE Access, vol. 7, pp. 45 301–45 312, 2019. [Online]. Available: https://doi.org/10.1109/ACCESS.2019.2909522
M. C. Bakkay, S. Chambon, H. A. Rashwan, C. Lubat, and S. Barsotti, "Automatic detection of individual and touching moths from trap images by combining contour-based and region-based segmentation," IET Computer Vision, vol. 12, no. 2, pp. 138–145, 2018. [Online]. Available: https://doi.org/10.1049/iet-cvi.2017.0086.
V. Partel, L. Nunes, P. Stansly, and Y. Ampatzidis, "Automated visionbased system for monitoring Asian citrus psyllid in orchards utilizing artificial intelligence," Computers and Electronics in Agriculture, vol. 162, pp. 328–336, jul 2019.
Y. Sun, X. Liu, M. Yuan, L. Ren, J. Wang, and Z. Chen, "Automatic in-trap pest detection using learning for pheromone-based Dendroctonus valens monitoring," Biosystems Engineering, vol. 176, pp. 140–150, dec 2018.
A. Kamilaris and F. X. Prenafeta-Boldu, "Deep learning in agriculture: A survey," Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018. [Online]. Available: https://doi.org/10.1016/j.compag.2018.02.016.
Y. Zhong, J. Gao, Q. Lei, and Y. Zhou, "A vision-based counting and recognition system for flying insects in intelligent agriculture," Sensors, vol. 18, no. 5, p. 1489, 2018.
W. Li, P. Chen, B. Wang, and C. Xie, "Automatic Localization and Count of Agricultural Crop Pests Based on an Improved Deep Learning Pipeline," Scientific Reports, vol. 9, no. 1, 2019.
A. Fuentes, S. Yoon, S. C. Kim, and D. S. Park, "A robust deep-learningbased detector for real-time tomato plant diseases and pests recognition," Sensors (Switzerland), vol. 17, no. 9, 2017.
J. Chen, Y. Fan, T. Wang, C. Zhang, Z. Qiu, and Y. He, "Automatic Segmentation and Counting of Aphid Nymphs on Leaves Using Convolutional Neural Networks," Agronomy, vol. 8, no. 8, 2018.
A. Krizhevsky, I. Sutskever, and G. Hinton, "Imagenet classification with deep convolutional neural networks," Neural Information Processing Systems, vol. 25, 01 2012.
S. Ren, K. He, R. Girshick, and J. Sun, "Faster r-cnn: Towards real-time object detection with region proposal networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137– 1149, 2016.
J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3431–3440.
P. Fischer, A. Dosovitskiy, and T. Brox, "Descriptor matching with convolutional neural networks: a comparison to SIFT," CoRR, vol. abs/1405.5769, 2014, withdrawn. [Online]. Available: http: //arxiv.org/abs/1405.5769.
Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436–444, 2015.
J. Dai, Y. Li, K. He, and J. Sun, "R-fcn: Object detection via region-based fully convolutional networks," in Proceedings of the 30th International Conference on Neural Information Processing Systems, ser. NIPS’16. Red Hook, NY, USA: Curran Associates Inc., 2016, p. 379–387. [Online]. Available: https://dl.acm.org/doi/10.5555/3157096. 3157139.
K. He, G. Gkioxari, P. Dollar, and R. Girshick, "Mask r-cnn," in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2980–2988. [Online]. Available: https://doi.org/10.1109/ICCV.2017.322.
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, "SSD: Single Shot MultiBox Detector," in Computer Vision – ECCV 2016, B. Leibe, J. Matas, N. Sebe, and M. Welling, Eds. Cham: Springer International Publishing, 2016, pp. 21–37.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779–788. [Online]. Available: https://doi.org/10.1109/CVPR.2016.91.
T. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, "Focal loss for ´ dense object detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 2, pp. 318–327, 2018. [Online]. Available: https://doi.org/10.1109/TPAMI.2018.2858826.
A. Nazri, N. Mazlan, and F. Muharam, "PENYEK: Automated brown planthopper detection from imperfect sticky pad images using deep convolutional neural network," PLOS ONE, vol. 13, no. 12, p. e0208501, dec 2018. [Online]. Available: http://dx.plos.org/10.1371/ journal.pone.0208501.
W. Abdulla, "Mask r-cnn for object detection and instance segmentation on keras and tensorflow," 2017. [Online]. Available: https://github.com/ matterport/Mask RCNN
Publicado
07/11/2020
Como Citar
DE CESARO JÚNIOR, Telmo; RIEDER, Rafael.
Uma Implementação Baseada em Mask R-CNN para Detecção de Insetos em Imagens Digitais. In: WORKSHOP DE TRABALHOS EM ANDAMENTO - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 33. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 139-142.
DOI: https://doi.org/10.5753/sibgrapi.est.2020.12996.
