Litter Detection Using YOLO V3
Keywords:
Smart city, street cleanliness.Abstract
Cleanliness of city streets has an important impact on city environment and public health. Conventional street cleaning methods involve street sweepers going to many spots and manually confirming if the street needs to clean. However, this method takes a substantial amount of manual operations for detection and assessment of street’s cleanliness which leads to a high cost for cities. Using pervasive mobile devices and AI technology, it is now possible to develop smart edge-based service system for monitoring and detecting the cleanliness of streets at scale. This paper explores an important aspect of cities - how to automatically analyse street imagery to understand the level of street litter. A vehicle equipped with smart edge station and cameras is used to collect and process street images in real time. A deep learning model is developed to detect, classify and analysis the diverse types of street litters such as tree branches, leaves, bottles and so on. In addition, two case studies are reported to show its strong potential and effectiveness in smart city systems.
References
- Alfarrarjeh, A., Kim, S. H., Agrawal, S., Ashok, M., Kim, S. Y., &Shahabi, C. (2018). Image classification to determine the level of street cleanliness: A case study. In 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM) (pp. 1–5).
- Balchandani, C., Hatwar, R. K., Makkar, P., Shah, Y., Yelure, P., &Eirinaki, M. (2017). A deep learning framework for smart street cleaning. In 2017 IEEE Third International Conference on Big Data Computing Service and Applications (BigDataService) (pp. 112–117).
- Begur, H., Dhawade, M., Gaur, N., Dureja, P., Gao, J., Mahmoud, M., Huang, J., Chen, S., & Ding, X. (2017). An edge-based smart mobile service system for illegal dumping detection and monitoring in san jose. In 2017 IEEE SmartWorld, Ubiquitous Intelligence Computing, Advanced Trusted Computed, Scalable Computing Communications, Cloud Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) (pp. 1–6). doi:10.1109/UIC-ATC.2017.8397575.
- Ladin-Sienne, S. (2017-04-16). Turning dirty streets clean through comprehensive open data mapping. URL: https://datasmart.ash.harvard.edu/news/article/turning-dirty-streets-clean-through-comprehensive-open-data-mapping-1001.
- Sevilla, A., Rodrłguez, M. L., ¢ngelaGarcła-Maraver, &Zamorano, M. (2013). An index to quantify street cleanliness: The case of granada (spain). Waste Management, 33, 1037 – 1046.
- Van Ryzin, G., Immerwahr, S., & Altman, S. (2008). Measuring street cleanliness: A comparison of new york city’s scorecard and results from a citizen survey. Public Administration Review, 68, 295 – 303.
- Smart street litter detection and classification based on Faster R-CNN and edge computing - Scientific Figure on ResearchGate. Available from: https://www.researchgate.net/figure/Clean-Streets-Framework- System-Architecture_fig1_338988152 [accessed 23 Nov, 2020]
- S. M. Imran, Engineering-final-year-project
- Z.-F. Xu, R.-S. Jia, H.-M. Sun, Q.-M. Liu, and Z. Cui, “Light-YOLOv3: fast method for detecting green mangoes in complex scenes using picking robots,” Appl. Intell., vol. 50, no. 12, pp. ss4670–4687, 2020.
- V. Meel, “YOLOv3: Real-Time Object Detection Algorithm (What's New?),” viso.ai, 31-Mar-2021. [Online]. Available: https://viso.ai/deep-learning/yolov3-overview/#:~:text=YOLOv3%20(You%20Only%20Look%20Once%2C%20Version%203)%20is%20a,Joseph%20Redmon%20and%20Ali%20Farhadi. [Accessed: 04-Jun-2021]
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.