Automated Debris Detection System Based on Computer Vision

Authors

Nur Athirah Zailan
Department of Electrical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, Malaysia
Mohamad Haniff Junos
School of Aerospace Engineering, Universiti Sains Malaysia, Engineering Campus, 14300, Nibong Tebal, Penang, Malaysia
Khairunnisa Hasikin
Department of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, Malaysia
Anis Salwa Binti Mohd Khairuddin
Department of Electrical Engineering, Faculty of Engineering, Universiti Malaya, 50603, Kuala Lumpur, Malaysia
Uswah Khairuddin
Malaysia Japan International Institute of Technology, Universiti Teknologi Malaysia, Kuala Lumpur, Malaysia

Synopsis

Marine litter has been one of the major challenges and a well-known issue across the globe for decades. 6.4 million tonnes of marine debris per year is estimated to enter water environments, with 8 million items entering each day. These statistics are so worrying, and mitigation steps need to be taken for the sake of a sustainable community. The major contributor to marine litter is no other than riverine litter. However, when there is not enough data about the amount of litter being transported, making quantitative data for monitoring impossible. Nowadays, most countries still use visual counting, which limits the feasibility of scaling to long-term monitoring at multiple locations. Therefore, an object detector using one of the deep learning algorithms, You Only Look Once version 4 (YOLOv4), is developed for floating debris of riverine monitoring system to mitigate the problem mentioned earlier. The proposed automated detection method has the capability to detect and categorize riverine litter, which can be improved in terms of detection speed and accuracy using YOLOv4. The detector is trained on five object classes such as styrofoam, plastic bags, plastic bottle, aluminium can and plastic container. Image augmentation technique is implemented into the previous datasets to increase training and validation datasets, which results in the increase of accuracy of the training. Some YOLOv4 and YOLOv4-tiny parameters have also been studied and manipulated to see their effects on the training.

TechPost2022
Published
December 28, 2022
Online ISSN
2582-3922