itter Detection with Deep Learning: A Comparative Stud

Author(s)

Cordova, Manuel ^[1] ; Pinto, Allan ^[2] ; Hellevik, Christina Carrozzo ^[3] ; Alaliyat, Saleh Abdel-Afou ^[4] ; Hameed, Ibrahim A. ^[4] ; Pedrini, Helio ^[1] ; Torres, Ricardo da S. ^{[4, 5, 6]}

Affiliation

^[1] Univ Estadual Campinas, Inst Comp, Ave Albert Einstein, BR-13083852 Campinas - Brazil

^[2] Brazilian Ctr Res Energy & Mat CNPEM, Brazilian Synchrotron Light Lab LNLS, BR-13083100 Campinas - Brazil

^[3] NTNU Norwegian Univ Sci & Technol, Dept Int Business, Larsgardsvegen 2, N-6009 Alesund - Norway

^[4] NTNU Norwegian Univ Sci & Technol, Dept ICT & Nat Sci, Larsgardsvegen 2, N-6009 Alesund - Norway

^[5] Wageningen Univ & Res, Farm Technol Grp, NL-6708 PB Wageningen - Netherlands

^[6] Wageningen Univ & Res, Wageningen Data Competence Ctr, NL-6708 PB Wageningen - Netherlands

• Document type: Journal article
• Source: ENSOR; v. 22, n. 2 JAN 2022.
• Web of Science Citations: 0

Abstract

Pollution in the form of litter in the natural environment is one of the great challenges of our times. Automated litter detection can help assess waste occurrences in the environment. Different machine learning solutions have been explored to develop litter detection tools, thereby supporting research, citizen science, and volunteer clean-up initiatives. However, to the best of our knowledge, no work has investigated the performance of state-of-the-art deep learning object detection approaches in the context of litter detection. In particular, no studies have focused on the assessment of those methods aiming their use in devices with low processing capabilities, e.g., mobile phones, typically employed in citizen science activities. In this paper, we fill this literature gap. We performed a comparative study involving state-of-the-art CNN architectures (e.g., Faster RCNN, Mask-RCNN, EfficientDet, RetinaNet and YOLO-v5), two litter image datasets and a smartphone. We also introduce a new dataset for litter detection, named PlastOPol, composed of 2418 images and 5300 annotations. The experimental results demonstrate that object detectors based on the YOLO family are promising for the construction of litter detection solutions, with superior performance in terms of detection accuracy, processing time, and memory footprint. (AU)

• FAPESP's process: 15/24494-8 - Communications and processing of big data in cloud and fog computing
• Grantee: Nelson Luis Saldanha da Fonseca
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 19/17729-0 - Data-driven approaches for soccer match analysis: an e-Science perspective
• Grantee: Paulo Roberto Pereira Santiago
• Support Opportunities: Regular Research Grants
• FAPESP's process: 19/16253-1 - Unraveling the secret of Brazilian and Dutch soccer by capturing successful elements of playing style and playing strategies
• Grantee: Allan da Silva Pinto
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• FAPESP's process: 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction?
• Grantee: Alexandre Xavier Falcão
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 16/50250-1 - The secret of playing football: Brazil versus the Netherlands
• Grantee: Sergio Augusto Cunha
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 17/20945-0 - Multi-user equipment approved in great 16/50250-1: local positioning system
• Grantee: Sergio Augusto Cunha
• Support Opportunities: Multi-user Equipment Program
• FAPESP's process: 19/22262-3 - Large volume reconstruction: high precision system for position detection in sports
• Grantee: Paulo Roberto Pereira Santiago
• Support Opportunities: Organization Grants - Scientific Meeting