Self-driving Vessels: YOLOv5 Approach for Water Surface Object Detection
Resumo
A aplicação de técnicas de Visão Computacional para detecção de objetos em superfície de água tem destacado-se como uma forte tendência no contexto de embarcações autônomas. Este trabalho apresenta uma avaliação de performance do algoritmo YOLOv5 para detecção de objetos localizados em superfície de água. Em seguida, o compara com a performance de outros 17 detectores clássicos. É utilizado um conjunto de imagens anotadas e disponibilizadas em uma base imagens de referência - WSODD, sendo essa caracterizada por ser pública, abrangente (7.467 imagens, 14 categorias e diferentes condições de captura) e especializada em objetos localizados em superfície de água. Finalmente, YOLOv5 obteve um mAP igual à 76.3 %, tendo superado em 11.3 % o mAP obtido pelo detector CRB-Net na mesma base de referência WSODD.
Palavras-chave:
embarcações autônomas, detecção de objetos, detecção de objetos em superfície de água
Referências
Bloisi, D., Iocchi, L., Fiorini, M., and Graziano, G. (2012). Camera based target recognition for maritime awareness. In 2012 15th International Conference on Information Fusion, pages 1982–1987.
Bloisi, D. D., Iocchi, L., Fiorini, M., and Graziano, G. (2011). Automatic maritime surveillance with visual target detection.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255.
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., and Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1):98–136.
Girshick, R. B. (2015). Fast R-CNN. CoRR, abs/1504.08083.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. http://www.deeplearningbook.org.
Gu, Y., Góez, J., Guajardo, M., and Wallace, S. (2019). Autonomous vessels: State of the art and potential opportunities in logistics. SSRN Electronic Journal, (2019/6).
He, K., Gkioxari, G., Dollár, P., and Girshick, R. B. (2017). Mask R-CNN. CoRR, abs/1703.06870.
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (2001). Gradient-based learning applied to document recognition. In Intelligent Signal Processing, pages 306–351. IEEE Press.
Li, X., Tian, M., Kong, S., Wu, L., and Yu, J. (2020). A modified yolov3 detection method for vision-based water surface garbage capture robot. International Journal of Advanced Robotic Systems, 17(3):1729881420932715.
Lin, T., Goyal, P., Girshick, R. B., He, K., and Dollár, P. (2017). Focal loss for dense object detection. CoRR, abs/1708.02002.
Lin, T., Maire, M., Belongie, S. J., Bourdev, L. D., Girshick, R. B., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. (2014). Microsoft COCO: common objects in context. CoRR, abs/1405.0312.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S. E., Fu, C., and Berg, A. C. (2015). SSD: single shot multibox detector. CoRR, abs/1512.02325.
Prasad, D. K., Dong, H., Rajan, D., and Quek, C. (2020). Are object detection assessment criteria ready for maritime computer vision? IEEE Transactions on Intelligent Transportation Systems, 21(12):5295–5304.
Prasad, D. K., Rajan, D., Rachmawati, L., Rajabally, E., and Quek, C. (2017). Video processing from electro-optical sensors for object detection and tracking in a maritime environment: A survey. IEEE Transactions on Intelligent Transportation Systems, 18(8):1993–2016.
Ren, S., He, K., Girshick, R. B., and Sun, J. (2015). Faster R-CNN: towards real-time object detection with region proposal networks. CoRR, abs/1506.01497.
Ribeiro, R., Cruz, G., Matos, J., and Bernardino, A. (2019). A data set for airborne maritime surveillance environments. IEEE Transactions on Circuits and Systems for Video Technology, 29(9):2720–2732.
Wang, W., Shan, T., Leoni, P., Fernández-Gutiérrez, D., Meyers, D., Ratti, C., and Rus, D. (2020). Roboat II: A novel autonomous surface vessel for urban environments. CoRR, abs/2007.10220.
Xu, Q., Yang, Y., Zhang, C., and Zhang, l. (2017). Deep convolutional neural networkbased autonomous marine vehicle maneuver. International Journal of Fuzzy Systems, 20.
Zhao, Z., Zheng, P., Xu, S., and Wu, X. (2018). Object detection with deep learning: A review. CoRR, abs/1807.05511.
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., and Torralba, A. (2018). Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6):1452–1464.
Zhou, Z., Sun, J., Yu, J., Liu, K., Duan, J., Chen, L., and Chen, C. L. P. (2021). An image-based benchmark dataset and a novel object detector for water surface object detection. Frontiers in Neurorobotics, 15.
Bloisi, D. D., Iocchi, L., Fiorini, M., and Graziano, G. (2011). Automatic maritime surveillance with visual target detection.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255.
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., and Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1):98–136.
Girshick, R. B. (2015). Fast R-CNN. CoRR, abs/1504.08083.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. http://www.deeplearningbook.org.
Gu, Y., Góez, J., Guajardo, M., and Wallace, S. (2019). Autonomous vessels: State of the art and potential opportunities in logistics. SSRN Electronic Journal, (2019/6).
He, K., Gkioxari, G., Dollár, P., and Girshick, R. B. (2017). Mask R-CNN. CoRR, abs/1703.06870.
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (2001). Gradient-based learning applied to document recognition. In Intelligent Signal Processing, pages 306–351. IEEE Press.
Li, X., Tian, M., Kong, S., Wu, L., and Yu, J. (2020). A modified yolov3 detection method for vision-based water surface garbage capture robot. International Journal of Advanced Robotic Systems, 17(3):1729881420932715.
Lin, T., Goyal, P., Girshick, R. B., He, K., and Dollár, P. (2017). Focal loss for dense object detection. CoRR, abs/1708.02002.
Lin, T., Maire, M., Belongie, S. J., Bourdev, L. D., Girshick, R. B., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. (2014). Microsoft COCO: common objects in context. CoRR, abs/1405.0312.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S. E., Fu, C., and Berg, A. C. (2015). SSD: single shot multibox detector. CoRR, abs/1512.02325.
Prasad, D. K., Dong, H., Rajan, D., and Quek, C. (2020). Are object detection assessment criteria ready for maritime computer vision? IEEE Transactions on Intelligent Transportation Systems, 21(12):5295–5304.
Prasad, D. K., Rajan, D., Rachmawati, L., Rajabally, E., and Quek, C. (2017). Video processing from electro-optical sensors for object detection and tracking in a maritime environment: A survey. IEEE Transactions on Intelligent Transportation Systems, 18(8):1993–2016.
Ren, S., He, K., Girshick, R. B., and Sun, J. (2015). Faster R-CNN: towards real-time object detection with region proposal networks. CoRR, abs/1506.01497.
Ribeiro, R., Cruz, G., Matos, J., and Bernardino, A. (2019). A data set for airborne maritime surveillance environments. IEEE Transactions on Circuits and Systems for Video Technology, 29(9):2720–2732.
Wang, W., Shan, T., Leoni, P., Fernández-Gutiérrez, D., Meyers, D., Ratti, C., and Rus, D. (2020). Roboat II: A novel autonomous surface vessel for urban environments. CoRR, abs/2007.10220.
Xu, Q., Yang, Y., Zhang, C., and Zhang, l. (2017). Deep convolutional neural networkbased autonomous marine vehicle maneuver. International Journal of Fuzzy Systems, 20.
Zhao, Z., Zheng, P., Xu, S., and Wu, X. (2018). Object detection with deep learning: A review. CoRR, abs/1807.05511.
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., and Torralba, A. (2018). Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6):1452–1464.
Zhou, Z., Sun, J., Yu, J., Liu, K., Duan, J., Chen, L., and Chen, C. L. P. (2021). An image-based benchmark dataset and a novel object detector for water surface object detection. Frontiers in Neurorobotics, 15.
Publicado
31/07/2022
Como Citar
SÁ, T. R. D.; FIGUEIREDO, C. M. S..
Self-driving Vessels: YOLOv5 Approach for Water Surface Object Detection. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO UBÍQUA E PERVASIVA (SBCUP), 14. , 2022, Niterói.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 31-40.
ISSN 2595-6183.
DOI: https://doi.org/10.5753/sbcup.2022.222855.
