An experimental study on marine debris location and recognition using object detection

Sánchez-Ferrer, Alejandro; Valero-Mas, Jose J.; Gallego, Antonio‐Javier; Calvo-Zaragoza, Jorge

doi:10.1016/j.patrec.2022.12.019

Cited by 10 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alejandro Sánchez-Ferrer conducted "An Experimental Study on Marine Debris Location and Recognition" [1]. The study employed the RCNN model for object detection to locate and recognize marine debris.…”

Section: Related Workmentioning

confidence: 99%

“…By concurrently addressing precision and recall and accounting for different IoU thresholds, our evaluation framework ensures a thorough assessment of the model's performance within the context of underwater waste detection. [1]. The assessment of the YoloV8 model has produced a range of significant metrics shedding light on its performance.…”

Section: Evaluation Of Yolov8 Modelmentioning

confidence: 99%

See 1 more Smart Citation

Waste Detection and Water Quality Assessment in Aquatic Environments: A Comprehensive Study Using YoloV8 and XGBoost

Parasar,

Vadalia,

Chavan

et al. 2024

Preprint

View full text Add to dashboard Cite

This research paper presents a structured approach to address the critical concerns associated with water quality assessment and underwater waste detection, employing advanced machine learning techniques. It commences with an exposition on the significance of water pollution's impact on aquatic ecosystems. Subsequently, the methodology employed in this study encompasses the utilization of the YOLOv8 model for the identification of underwater waste, a rule-based classifier for the evaluation of water quality, and the application of the XGBoost algorithm for predicting water potability. The ensuing sections delve into the practical implementation of these components, offering in-depth insights into their technical intricacies and seamless integration. A thorough evaluation follows, substantiating the system's effectiveness and reliability in three key dimensions: underwater waste detection, water quality assessment, and water potability prediction. As indicated by the lower map50-95 score, the Yolov8 model showed impressive precision and recall in recognising positive cases; however, improvements are required for complex object detection scenarios. Analysing the confusion matrix revealed particular categories that needed to be improved. On the other hand, the XGBoost classifier produced encouraging outcomes, demonstrating excellent accuracy, f1 score, precision, and recall in a variety of categories, underscoring its efficacy in precise sample class prediction. The research paper concludes by underscoring the transformative potential of this multifaceted approach in bolstering environmental conservation and safeguarding aquatic ecosystems against the pernicious effects of water pollution.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Evaluation Of Yolov8 Modelmentioning

confidence: 99%