Abstract
Trash accumulation in beaches affects the ecosystem of coastal lines. Different types of trash can affect beaches in a variety of ways and manual identification of this trash might become laborious. So, it becomes important to devise a method to facilitate the localization of this trash without human intervention. In this paper, we propose a deep learning-based solution for multi-class segmentation of trash objects using Unmanned Aerial Vehicles. But the problem with the aggregated orthoimages is the low foreground-to-background ratio which tends to render very high false positives (FP) during classification. To counter this, we propose a random data generation method to generate synthetic data over real backgrounds. The best performing model among the chosen candidate architectures (U-Net and SegNet) on both the real and synthetic datasets are evaluated and results are compared using various segmentation metrics. Later the segmentation masks are transposed onto a map to facilitate localization.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The distribution of classes is given in numbers and is not to be confused with pixels.
- 2.
Base map: “13°13′ 13.8648ʺ N, 80°19′ 35.4426ʺ E. Ennore Region, Tamil Nadu, India” Google Maps, Google.
References
Abraham, N., & Khan, N. M. (2019). A novel focal tversky loss function with improved attention u-net for lesion segmentation. In 2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019) (pp. 683–687).
Aerial Semantic Segmentation Drone Dataset, https://www.tugraz.at/index.php?id=22387
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), 2481–2495
Bak, S. H., Hwang, D. H., Kim, H. M., & Yoon, H. J. (2019). Detection and monitoring of beach litter using uav image and deep neural network. In ISPRS—International archives of the photogrammetry, remote sensing and spatial information sciences, XLII-3/W8, 55–58
Bao, Z., Sha, J., Li, X., Hanchiso, T., & Shifaw, E. (2018). Monitoring of beach litter by automatic interpretation of unmanned aerial vehicle images using the segmentation threshold method. Marine Pollution Bulletin, 137, 388–398.
Beach Garbage Dataset: GitHub repository, https://github.com/SrihariM1809/beach-garbage-dataset
Chawla, N., Bowyer, K., Hall, L., & Kegelmeyer, W. (2002) SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence and Research (JAIR), 16, 321–357.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 770–778).
He, K., Girshick, R., & Dollar, P. (2019). Rethinking ImageNet pre-training. In IEEE/CVF international conference on computer vision (ICCV) (pp. 4917–4926).
Ho, Y., & Wookey, S. (2020). The Real-world-weight cross-entropy loss function: Modeling the costs of mislabeling. IEEE Access, 8, 4806–4813.
Ichimura, T., & Nakajima, S. v Development of an autonomous beach cleaning robot “Hirottaro”. In IEEE international conference on mechatronics and automation (pp. 868–872).
Image Segmentation Keras: GitHub repository: https://github.com/divamgupta/image-segmentation-keras
Jadon, S. (2020). A survey of loss functions for semantic segmentation. In IEEE conference on computational intelligence in bioinformatics and computational biology (CIBCB) (pp. 1–7).
Jang, S. W., Lee, S. K., Oh, S. Y., Kim, D. H., & Yoon, H. J. (2011). The application of unmanned aerial photography for effective monitoring of marine debris. Journal of the Korean Society of Marine Environment Safety, 17(4), 307–314.
Kako, S. I., Isobe, A., Kataoka, T., & Yufu, K. (2018). Sequential webcam monitoring and modeling of marine debris abundance. Marine Pollution Bulletin, 132, 33–43
Lin, T., Goyal, P., Girshick, R., He, K., & Dollar, P. (2020). Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2), 318–327.
Nakashima, E. (2011). Using aerial photography and in situ measurements to estimate the quantity of macro-litter on beaches, Marine Pollution Bulletin, 62(4), 762–769.
Park, S. S., & Kang, H. Y. (2005). The quantity and characteristics of marine debris collected from the coastline in Jeonnam. Journal of Korea Society of Waste Management, 22(2), 203–212.
Pihur, V., Datta, S., & Datta, S. (2007). Weighted rank aggregation of cluster validation measures, a monte carlo cross-entropy approach. Bioinformatics, 23(13), 1607–1615.
Pinheiro, P., Cardozo, E., Wainer, J., Rohmer, E. (2015). Cleaning task planning for an autonomous robot in indoor places with multiples rooms. International Journal of Machine Learning and Computing, 5(2), 86–90
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. LNCS, 9351, 234–241.
Salehi, S. S. M., Erdogmus, D., & Gholipour, A. (2017). Tversky loss function for image segmentation using 3d fully convolutional deep networks. In International workshop on machine learning in medical imaging (Vol. 10541, pp. 379–387). Springer.
Shelhamer, E., Long, J., & Darrell, T. (2017). Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4), 640–651.
Sudre, C. H., Li, W., Vercauteren, T., Ourselin, S., & Jorge Cardoso, M. (2017). Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In Cardoso, M. et al. (Eds.), Deep learning in medical image analysis and multimodal learning for clinical decision support. DLMIA 2017, ML-CDS 2017. Lecture Notes in Computer Science (Vol. 10553, pp. 240–248). Springer, Cham.
Thiagarajan, S., & Satheesh, K. G. (2019). Machine learning for beach litter detection. Advances in Intelligent Systems and ComputingIn M. Tanveer & R. Pachori (Eds.), Machine intelligence and signal analysis (Vol. 748, pp. 259–266). Springer.
TrashNet: Github repository—https://github.com/garythung/trashnet
Wattanasophon, S., & Ouitrakul, S. (2014) Garbage collection robot on the beach using wireless communications. In 3rd international conference on informatics, environment, energy and applications (Vol. 66, pp. 92–96).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Surya Prakash, S., Vengadesh, V., Vignesh, M., Gopal, S.K. (2022). Multi-class Segmentation of Trash in Coastal Areas Using Encoder-Decoder Architecture. In: Hemanth, D.J. (eds) Machine Learning Techniques for Smart City Applications: Trends and Solutions. Advances in Science, Technology & Innovation. Springer, Cham. https://doi.org/10.1007/978-3-031-08859-9_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-08859-9_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08858-2
Online ISBN: 978-3-031-08859-9
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)