Yolov3 Tabanlı Atık Tespit Sistemleri

Year 2023, Volume: 4 Issue: 2, 160 - 176, 24.12.2023

Dilara Karaca , Süleyman Uzun , Sezgin Kaçar

https://doi.org/10.58769/joinssr.1390459

Cited By: 1

Abstract

Günümüzde insan sayısındaki artış, sanayi ve teknolojideki ilerlemeler, üretimin hızlanmasıyla birlikte ortaya çıkan atıkların sayısında da artışa neden olmaktadır. Bu atıkların daha kolay tespit edilmesi ve geri dönüştürülmesi ülkemizin ve dünyanın geleceği için önem arz etmektedir. Atıkların geri dönüşümü sürecinde, atıkların toplanması kadar sınıflandırılması da maliyetli enerji ve insan gücü gerektirmektedir. Atıklar temel olarak kağıt, plastik, cam ve metal olarak ayrıştırılmaktadır. Yapay zeka, derin öğrenme ve görüntü işleme gibi teknolojiler ile bu süreçlerin daha kısa ve kolay bir şekilde tamamlanması için çeşitli çalışmalar yapılmıştır. Bu çalışmada, çevrede yaygın olarak bulunan kağıt, plastik ve yiyecek-içecek atıklarından oluşan bir veri kümesi oluşturulmuştur. Bu veri kümesinde kağıt bardaklar, plastik su şişeleri ve fast food atıkları doğada farklı lokasyonlardan tespit edilerek fotoğraflanmıştır. Bu görüntüler etiketlenerek derin öğrenme algoritmalarında YoloV3 ile eğitilmiş ve test edilmiştir. Ayrıca yeni veri kümesinin performansını karşılaştırmak amacıyla literatürde kullanılan global bir veri kümesi üzerinde çalışmalar yapılmıştır. Çalışmalar sonucunda yeni oluşturulan veri kümesinin ve global veri kümesinin sınıflandırılmasında başarılı olduğu gözlemlenmiştir.

Keywords

YoloV3, Atık Tespiti, Atık Veri Seti

A Yolov3-Based Garbage Detection Systems

Abstract

Today, the increase in the number of people, advances in industry and technology cause an increase in the number of wastes generated with the acceleration of production. It is important for the future of our country and the world that these wastes are more easily identified and recycled. In the process of recycling wastes, the classification of wastes as well as their collection requires costly energy and manpower. Wastes are basically separated into paper, plastic, glass and metal. Various studies have been carried out to complete these processes in a shorter and easier way with technologies such as artificial intelligence, deep learning and image processing. In this study, a dataset of paper, plastic and food and beverage wastes that are common in the environment was created. In this dataset, paper cups, plastic water bottles and fast food wastes were detected from different locations in nature and photographed. These images were labeled and trained and tested with YoloV3 in deep learning algorithms. In addition, in order to compare the performance of the new dataset, studies were conducted on a global dataset used in the literature. As a result of the studies, it was observed that it was successful in classifying the newly created dataset and the global dataset.

Keywords

YoloV3, Garbage detection, Garbage dataset

References

• [1] A. Sağlık, Y. Selim Domaç, Ş. N. Reyhan, F. Avcı, F. Kartal, and D. Şenkuş, “Akademia Doğa ve İnsan Bilimleri Dergisi Academia Journal of Nature and Human Sciences Katı Atık Depolama Alanlarının Islahı ve Analizi Çanakkale Onsekiz Mart Üniversitesi Örneği,” vol. 7, no. 1, pp. 105–125.
• [2] R. Erdoğan and G. Uzun, “Katı Atık Depolama Alanlarının Bı̇tkı̇sel Islahına Bı̇r Örnek: Adana-Sofulu Çöp Depolama Alanı,” Akdeniz Üniversitesi Ziraat Fakültesi Derg., vol. 20, no. 1, pp. 71–82, 2007.
• [3] N. Özgen, “Kent ve çöp,” TBB Mesleki Sağlık ve Güvenlik Derg., vol. 7, no. 8, pp. 10–12, 2006.
• [4] T. Ç. M. Odası, “Dünya çevre günü Türkiye raporu,” TMMOB Çevre Mühendisleri Odası. [Online]. Available: http://www.cmo.org.tr/resimler/ekler/0d4a5b926c005a6_ek.pdf, Erişim Tarihi: 12.10.2021
• [5] P. P. Rao, S. P. Rao, and R. Ranjan, “Deep Learning Based Smart Garbage Monitoring System,” MPCIT 2020 - Proc. IEEE 3rd Int. Conf. "Multimedia Process. Commun. Inf. Technol., pp. 77–81, Dec. 2020, doi: 10.1109/MPCIT51588.2020.9350390.
• [6] A. Datumaya Wahyudi Sumari, R. Andrie Asmara, D. Rossiawan Hendra Putra, and I. Noer Syamsiana, “Prediction Using Knowledge Growing System: A Cognitive Artificial Intelligence Approach,” Proc. - IEIT 2021 1st Int. Conf. Electr. Inf. Technol., pp. 15–20, Sep. 2021, doi: 10.1109/IEIT53149.2021.9587367.
• [7] E. Saygin et al., “Karaciğer Yetmezliği Teşhisinde Özellik Seçimi Kullanarak Makine Öğrenmesi Yöntemlerinin Başarılarının Ölçülmesi,” Fırat Üniversitesi Müh. Bil. Derg. Araştırma Makal., vol. 33, no. 2, pp. 367–377, 2021, doi: 10.35234/fumbd.832264.
• [8] F. Doğan and İ. Türkoğlu, “Derin Öğrenme Modelleri ve Uygulama Alanlarına İlişkin Bir Derleme,” DÜMF Mühendislik Derg., vol. 10, no. 2, pp. 409–445, 2019, doi: 10.24012/dumf.411130.
• [9] G. Liu, “Surface Defect Detection Methods Based on Deep Learning: A Brief Review,” Proc. - 2020 2nd Int. Conf. Inf. Technol. Comput. Appl. ITCA 2020, pp. 200–203, Dec. 2020, doi: 10.1109/ITCA52113.2020.00049.
• [10] A. E. Ba Alawi, A. Y. A. Saeed, F. Almashhor, R. Al-Shathely, and A. N. Hassan, “Solid Waste Classification Using Deep Learning Techniques,” 2021 Int. Congr. Adv. Technol. Eng. ICOTEN 2021, Jul. 2021, doi: 10.1109/ICOTEN52080.2021.9493430.
• [11] N. Ramsurrun, G. Suddul, … S. A.-… zooming innovation in, and undefined 2021, “Recyclable waste classification using computer vision and deep learning,” ieeexplore.ieee.orgN Ramsurrun, G Suddul, S Armoogum, R Foogooa2021 zooming Innov. Consum. Technol. Conf. (ZINC), 2021•ieeexplore.ieee.org, pp. 11–15, May 2021, doi: 10.1109/ZINC52049.2021.9499291.
• [12] A. Assis, A. R. Biju, N. A. Alisha, A. Dhanadas, and N. Kurian, “Garbage Collecting Robot Using YOLOv3 Deep Learning Model,” 10th Int. Conf. Adv. Comput. Commun. ICACC 2021, 2021, doi: 10.1109/ICACC-202152719.2021.9708298.
• [13] S. K. Koganti, G. Purnima, P. Bhavana, Y. V. Raghava, and R. Resmi, “Deep Learning based Automated Waste Segregation System based on degradability,” Proc. 2nd Int. Conf. Electron. Sustain. Commun. Syst. ICESC 2021,A Yolov3-Based Garbage Detection Systems pp. 1953–1956, Aug. 2021, doi: 10.1109/ICESC51422.2021.9532837.
• [14] C. Zhihong, Z. Hebin, W. Yanbo, L. Binyan, and L. Yu, “A vision-based robotic grasping system using deep learning for garbage sorting,” in Chinese Control Conference, CCC, 2017, pp. 11223–11226. doi: 10.23919/ChiCC.2017.8029147.
• [15] A. Khanum, C. Y. Lee, and C. S. Yang, “End-to-end deep learning model for steering angle control of autonomous vehicles,” Proc. - 2020 Int. Symp. Comput. Consum. Control. IS3C 2020, pp. 189–192, Nov. 2020, doi: 10.1109/IS3C50286.2020.00056.
• [16] K. Turgut and B. Kaleci, “Comparison of Deep Learning Techniques for Semantic Classification of Ramps in Search and Rescue Arenas,” Proc. - 2020 Innov. Intell. Syst. Appl. Conf. ASYU 2020, Oct. 2020, doi: 10.1109/ASYU50717.2020.9259851.
• [17] X. Yao et al., “Traffic vehicle detection algorithm based on YOLOv3,” Proc. - 2021 Int. Conf. Intell. Transp. Big Data Smart City, ICITBS 2021, pp. 47–50, Mar. 2021, doi: 10.1109/ICITBS53129.2021.00020.
• [18] S. S. Rajeswari and M. Nair, “A Transfer Learning Approach for Predicting Alzheimer’s Disease,” 2021 Int. Conf. Nascent Technol. Eng. ICNET 2021 - Proc., Jan. 2021, doi: 10.1109/ICNTE51185.2021.9487746.
• [19] V. Ravanan, R. Subasri, M. G. Vimal Kumar, K. T. Dhivya, P. S. Kumar, and K. Roobini, “Next Generation Smart Garbage Level Indication and Monitoring System using IoT,” Proc. - 1st Int. Conf. Smart Technol. Commun. Robot. STCR 2021, Oct. 2021, doi: 10.1109/STCR51658.2021.9588961.
• [20] S. Amitha et al., “Segregated waste collector with robotic vacuum cleaner using internet of things,” Proc. - 2020 IEEE Int. Symp. Sustain. Energy, Signal Process. Cyber Secur. iSSSC 2020, Dec. 2020, doi: 10.1109/ISSSC50941.2020.9358839.
• [21] J. Bai, S. Lian, Z. Liu, K. Wang, and D. Liu, “Deep Learning Based Robot for Automatically Picking Up Garbage on the Grass,” IEEE Trans. Consum. Electron., vol. 64, no. 3, pp. 382–389, Aug. 2018, doi: 10.1109/TCE.2018.2859629.
• [22] F. C. Yuan, H. L. Sun, S. J. Hu, and L. Z. Wang, “Design of cleaning robot for swimming pools,” 2011 Int. Conf. Manag. Sci. Ind. Eng. MSIE 2011, pp. 1175–1178, 2011, doi: 10.1109/MSIE.2011.5707629.
• [23] G. Thung, “Trashnet Dataset.” [Online]. Available: https://github.com/garythung/trashnet/blob/master/data/dataset-resized.zip, Erişim Tarihi: 10.08.2021
• [24] M. Hewitt, “Make Sense,” Victorian Studies. [Online]. Available: https://www.makesense.ai/, Erişim Tarihi: 10.08.2021
• [25] A. Luque, A. Carrasco, A. Martín, and A. de las Heras, “The impact of class imbalance in classification performance metrics based on the binary confusion matrix,” Pattern Recognit., vol. 91, pp. 216–231, Jul. 2019, doi: 10.1016/J.PATCOG.2019.02.023.
• [26] J. Mccarthy, “What Is Artificia Intelligence?,” in What Is Artificia Intelligence?, philpapers.org, 2004.
• [27] J. H. Fetzer, “What is Artificial Intelligence?,” pp. 3–27, 1990, doi: 10.1007/978-94-009-1900-6_1.
• [28] K. Arslan, “Eğitimde Yapay Zekâ ve Uygulamaları,” Batı Anadolu Eğitim Bilim. Derg., vol. 11, no. 1, pp. 71–80, 2020.
• [29] J. G. Carbonell, R. S. Michalski, and T. M. Mitchell, “An Overview of Machine Learning,” Mach. Learn., pp. 3–23, 1983, doi: 10.1007/978-3-662-12405-5_1.
• [30] E. S. Brunette, R. C. Flemmer, and C. L. Flemmer, “A review of artificial intelligence,” ICARA 2009 - Proc. 4th Int. Conf. Auton. Robot. Agents, pp. 385–392, 2009, doi: 10.1109/ICARA.2000.4804025.
• [31] T. Dergisi, A. Altay, S. Yilmaz, K. Tarihi, A. Kelimeler, and Y. Algoritmas, “YOLO Algoritması Kullanılarak T Hücrelerinin Sınıflandırılması Classification Of T Cells Using YOLO Algorithm Abstract,” vol. 3, no. 2, pp. 66–81, 2023.
• [32] J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” arxiv.org, Apr. 2018, Accessed: Apr. 17, 2023. [Online]. Available: https://arxiv.org/abs/1804.02767
• [33] A. Aktaş, B. Doğan, and Ö. Demir, “Tactile paving surface detection with deep learning methods,” J. Fac. Eng. Archit. Gazi Univ., vol. 35, no. 3, pp. 1685–1700, 2020, doi: 10.17341/gazimmfd.652101.
• [34] J. Redmon and A. Farhadi, “YOLO9000: better, faster, stronger,” in IEEE conference on computer vision 2017, Undefined, 2017, pp. 7263–7271.
• [35] S. K. Tai, C. Dewi, R. C. Chen, Y. T. Liu, X. Jiang, and H. Yu, “Deep Learning for Traffic Sign Recognition Based on Spatial Pyramid Pooling with Scale Analysis,” Appl. Sci. 2020, Vol. 10, Page 6997, vol. 10, no. 19, p. 6997, Oct. 2020, doi: 10.3390/APP10196997.
• [36] C. Dewi, R. C. Chen, and S. K. Tai, “Evaluation of Robust Spatial Pyramid Pooling Based on Convolutional Neural Network for Traffic Sign Recognition System,” Electron. 2020, Vol. 9, Page 889, vol. 9, no. 6, p. 889, May 2020, doi: 10.3390/ELECTRONICS9060889.
• [37] C. Dewi, R.-C. C. Chen, X. Jiang, and H. Yu, “Deep convolutional neural network for enhancing traffic sign recognition developed on Yolo V4,” Multimed. Tools Appl., vol. 81, no. 26, pp. 37821–37845, Nov. 2022, doi: 10.1007/s11042-022-12962-5.
• [38] H. Hussein, Y. Zhu, R. F. Hassan, S. Teng, Z. Liu, and X. Li, “Improved YOLOv3-Based Bridge Surface Defect Detection by Combining High- and Low-Resolution Feature Images,” Build. 2022, Vol. 12, Page 1225, vol. 12, no. 8, p. 1225, Aug. 2022, doi: 10.3390/BUILDINGS12081225.
• [39] S. Teng, Z. Liu, G. Chen, and L. Cheng, “Concrete Crack Detection Based on Well-Known Feature Extractor Model and the YOLO_v2 Network,” Appl. Sci. 2021, Vol. 11, Page 813, vol. 11, no. 2, p. 813, Jan. 2021, doi: 10.3390/APP11020813.
• [40] E. Ulutaş, H. Cengİz, and M. C. Yazicioğlu, “Derin öğrenme temelli nesne tespiti algoritmaları kullanılarak kişiye özgü reklam sunulması,” vol. 24, no. 1, pp. 10–28, 2022, doi: 10.25092/baunfbed.878224.
• [41] T. Shi, Y. Niu, M. Liu, Y. Yang, C. Wang, and Y. Huang, “Underwater dense targets detection and classification based on YOLOv3,” IEEE Int. Conf. Robot. Biomimetics, ROBIO 2019, pp. 2595–2600, Dec. 2019, doi: 10.1109/ROBIO49542.2019.8961615.
• [42] A. Karacı, “Detection and classification of shoulder implants from X-ray images: YOLO and pre-trained convolution neural network based approach,” J. Fac. Eng. Archit. Gazi Univ., vol. 37, pp. 283–294, 2022, doi: 10.17341/gazimmfd.888202.
• [43] B. De Carolis, F. Ladogana, and N. Macchiarulo, “YOLO TrashNet: Garbage Detection in Video Streams,” in 2020 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS), IEEE, May 2020, pp. 1–7. doi: 10.1109/EAIS48028.2020.9122693.
• [44] W. Lin, “YOLO-Green: A Real-Time Classification and Object Detection Model Optimized for Waste Management,” in 2021 IEEE International Conference on Big Data (Big Data), IEEE, Dec. 2021, pp. 51–57. doi: 10.1109/BigData52589.2021.9671821.
• [45] W.-L. Mao, W.-C. Chen, H. I. K. Fathurrahman, and Y.-H. Lin, “Deep learning networks for real-time regional domestic waste detection,” J. Clean. Prod., vol. 344, p. 131096, Apr. 2022, doi: 10.1016/j.jclepro.2022.131096.
• [46] Q. Zhang et al., “A multi-label waste detection model based on transfer learning,” Resour. Conserv. Recycl., vol. 181, p. 106235, Jun. 2022, doi: 10.1016/J.RESCONREC.2022.106235.