ABSTRACT
We assessed several state-of-the-art deep learning algorithms and computer vision techniques for estimating the particle size of mixed commercial waste from images. In waste management, the first step is often coarse shredding, using the particle size to set up the shredder machine. The difficulty is separating the waste particles in an image, which can not be performed well. This work focused on estimating size by using the texture from the input image, captured at a fixed height from the camera lens to the ground. We found that EfficientNet achieved the best performance of 0.72 on F1-Score and 75.89% on accuracy.
- Gavin C. Cawley and Nicola L.C. Talbot. 2010. On Over-Fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation. The Journal of Machine Learning Research 11 (Aug. 2010), 2079–2107.Google Scholar
- Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Fei-Fei Li. 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20-25 June 2009, Miami, Florida, USA. IEEE Computer Society, 248–255. https://doi.org/10.1109/CVPR.2009.5206848Google ScholarCross Ref
- Terrance Devries and Graham W. Taylor. 2017. Improved Regularization of Convolutional Neural Networks with Cutout. CoRR abs/1708.04552(2017). arxiv:1708.04552http://arxiv.org/abs/1708.04552Google Scholar
- Francesco Di Maria, Francesco Bianconi, Caterina Micale, Stefano Baglioni, and Moreno Marionni. 2016. Quality assessment for recycling aggregates from construction and demolition waste: An image-based approach for particle size estimation. Waste Management 48 (Feb. 2016), 344–352. https://doi.org/10.1016/j.wasman.2015.12.005Google ScholarCross Ref
- Gregory Dunnu, Thomas Hilber, and Uwe Schnell. 2006. Advanced Size Measurements and Aerodynamic Classification of Solid Recovered Fuel Particles. Energy Fuels 20, 4 (July 2006), 1685–1690. https://doi.org/10.1021/ef0600457Google ScholarCross Ref
- Shin Fujieda, Kohei Takayama, and Toshiya Hachisuka. 2017. Wavelet Convolutional Neural Networks for Texture Classification. arXiv abs/1707.07394 (July 2017). arxiv:1707.07394 [cs.CV] https://arxiv.org/abs/1707.07394v1Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Los Alamitos, CA, USA, 770–778. https://doi.org/10.1109/CVPR.2016.90Google ScholarCross Ref
- L. Kandlbauer, K. Khodier, D. Ninevski, and R. Sarc. 2021. Sensor-based Particle Size Determination of Shredded Mixed Commercial Waste based on two-dimensional Images. Waste Management 120(2021), 784–794. https://doi.org/10.1016/j.wasman.2020.11.003Google ScholarCross Ref
- Silpa Kaza, Lisa C. Yao, Perinaz Bhada-Tata, and Frank Van Woerden. 2018. What a Waste 2.0. Washington, DC: World Bank, Washington, DC, USA. https://doi.org/10.1596/978-1-4648-1329-0Google ScholarCross Ref
- Karim Khodier, Sandra Antonia Viczek, Alexander Curtis, Alexia Aldrian, Paul O’Leary, Markus Lehner, and Renato Sarc. 2020. Sampling and analysis of coarsely shredded mixed commercial waste. Part I: procedure, particle size and sorting analysis. International Journal of Environmental Science and Technology 17, 2 (Feb. 2020), 959–972. https://doi.org/10.1007/s13762-019-02526-wGoogle ScholarCross Ref
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2017. ImageNet Classification with Deep Convolutional Neural Networks. Commun. ACM 60, 6 (May 2017), 84–90. https://doi.org/10.1145/3065386Google ScholarDigital Library
- Microsoft Research. 2016. Image Composite Editor. https://www.microsoft.com/en-us/research/product/computational-photography-applications/image-composite-editor [Online; accessed 16. Mar. 2021].Google Scholar
- Lin Mar Oo and Nay Zar Aung. 2018. A simple and efficient method for automatic strawberry shape and size estimation and classification. Biosystems Engineering 170 (June 2018), 96–107. https://doi.org/10.1016/j.biosystemseng.2018.04.004Google ScholarCross Ref
- Juan Manuel Ponce, Arturo Aquino, Borja Millán, and José Manuel Andújar. 2018. Olive-Fruit Mass and Size Estimation Using Image Analysis and Feature Modeling. Sensors 18, 9 (Sept. 2018), 2930. https://doi.org/10.3390/s18092930Google ScholarCross Ref
- Sebastian Raschka. 2018. Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning. CoRR abs/1811.12808(2018). arxiv:1811.12808http://arxiv.org/abs/1811.12808Google Scholar
- Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018 (18-23 June 2018). IEEE, Salt Lake City, UT, USA, 4510–4520. https://doi.org/10.1109/CVPR.2018.00474Google ScholarCross Ref
- Renato Sarc. 2021. The “ReWaste4.0” Project–A Review. Processes 9, 5 (Apr 2021), 764. https://doi.org/10.3390/pr9050764Google ScholarCross Ref
- Renato Sarc, Alexander Curtis, Lisa Kandlbauer, Karim Khodier, KE Lorber, and Roland Pomberger. 2019. Digitalisation and intelligent robotics in value chain of circular economy oriented waste management – A review. Waste Management 95 (July 2019), 476–492. https://doi.org/10.1016/j.wasman.2019.06.035Google ScholarCross Ref
- Renato Sarc, KE Lorber, Roland Pomberger, Melanie Rogetzer, and Ernst-Michael Sipple. 2014. Design, quality, and quality assurance of solid recovered fuels for the substitution of fossil feedstock in the cement industry. Waste Management & Research 32, 7 (June 2014), 565–585. https://doi.org/10.1177/0734242X14536462Google ScholarCross Ref
- Renato Sarc, KE Lorber, Roland Pomberger, Melanie Rogetzer, and Ernst-Michael Sipple. 2019. Design, quality and quality assurance of solid recovered fuels for the substitution of fossil feedstock in the cement industry – Update 2019. Waste Management & Research 37, 9 (July 2019), 885–897. https://doi.org/10.1177/0734242X19862600Google ScholarCross Ref
- Renato Sarc and Karl E Lorber. 2013. Production, quality and quality assurance of Refuse Derived Fuels (RDFs). Waste Management 33, 9 (Sept. 2013), 1825–1834. https://doi.org/10.1016/j.wasman.2013.05.004Google ScholarCross Ref
- Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http://arxiv.org/abs/1409.1556Google Scholar
- Ilya Sutskever, James Martens, George E. Dahl, and Geoffrey E. Hinton. 2013. On the Importance of Initialization and Momentum in Deep Learning. In Proceedings of the 30th International Conference on Machine Learning, ICML 2013 (Atlanta, GA, USA) (JMLR Workshop and Conference Proceedings, Vol. 28). JMLR.org, 1139–1147. https://doi.org/10.5555/3042817.3043064Google ScholarDigital Library
- Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of the Machine Learning Research, Vol. 97). PMLR, 6105–6114. http://proceedings.mlr.press/v97/tan19a.htmlGoogle Scholar
- Michael De Villiers. 1994. The Role and Function of a Hierarchical Classification of Quadrilaterals. For the Learning of Mathematics 14, 1 (1994), 11–18. http://www.jstor.org/stable/40248098Google Scholar
- Zelin Zhang, Jian guo Yang, X. Su, and Li hua Ding. 2013. Analysis of large particle sizes using a machine vision system. Physicochemical Problems of Mineral Processing Volume 49, issue 2 (2013). http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.baztech-410d7c2e-ccaf-4c7d-8d35-73c3f5528f96Google Scholar
Index Terms
- Particle Size Estimation in Mixed Commercial Waste Images Using Deep Learning
Recommendations
Classification of Waste Materials using CNN Based on Transfer Learning
FIRE '22: Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval EvaluationWaste Management is important for humans as well as nature for healthy life and a clean environment. The major step for effective waste management is the segregation of waste according to its types. The advancement of technology such as hardware and ...
Cognitive cloud framework for waste dumping analysis using deep learning vision computing in healthy environment
AbstractIncreased population and usage of more unnatural particles create dangerous waste in society. Environmental Sustainability is ensured based on proper waste management solutions. There is a need for real-time monitoring of waste dumping in the ...
A Vision Based Approach to Localize Waste Objects and Geometric Features Exaction for Robotic Manipulation
AbstractThe quantity of waste generated is increasing daily, demanding an intelligent waste management system for effective and timely solutions. Pollution induced by garbage has been one of the major problems globally for a long time. The unawareness ...
Comments