ABSTRACT
Oceans are ultimately a sink of plastic waste. Complex artificial coastlines pose remarkable challenges for coastal plastic waste monitoring. With the development of machine learning methods, high detection accuracy can be achieved; however, many false positives have been noted in various network models used for plastic waste investigation. In this study, extensive surveys of artificial coastlines were conducted using drones along the Dongjiang Port artificial coastline in the Binhai District, Tianjin, China. The deep learning model YOLOv8 was enhanced by integrating the InceptionNeXt and LSK modules into the network to improve its detection accuracy for plastic waste and reduce instances of tourists being misidentified as plastic. In total, 553 high-resolution coastline images with 3488 items of detected plastic waste were compared using the original and improved YOLOv8 models. The improved YOLOv8s-IL model achieved a detection rate of 64.9%, a notable increase of 11.5% compared with that of the original model. The number of false positives in the improved YOLOv8s-IL model was reduced to 32.3%, the multi-class F-score reached 76.5%, and the average detection time per image was only 2.7 s. The findings of this study provide technical support for future large-scale monitoring of plastic waste on artificial coastlines.
ABSTRACT
The ship exhaust sniffing unmanned aerial vehicle (UAV) system can be applied to monitor vessel emissions in emission control areas (ECAs) to improve the efficiency of maritime law enforcement and reduce ship pollution. To solve the problems of large size, heavy weight and high cost of ship exhaust sniffing sensors, in this paper, a unique diffused mini-sniffing sensor was designed, which provides a low-cost, lightweight, and highly adaptable solution for ship exhaust sniffing UAV. To verify the measurement accuracy of the system, a large number of on-site tests were performed based in the mouth of the Yangtze River, and some cases of violation of the fuel sulfur content (FSC) were verified and punished. Maritime law enforcement officers boarded the ship to take oil samples from eight suspected ships and sent them to the laboratory for testing. The results showed that the FSCs of the eight ships in chemical inspection were all greater than the regulatory limit 0.5% (m/m) of the International Maritime Organization (IMO). The system enables authorities to monitor emissions using rotary UAVs equipped with diffused mini-sniffing sensors to measure the FSC of navigating ships, which couple hardware and operational software with a dedicated lab service to produce highly reliable measurement results. The system offers an effective tool for screening vessel compliance.
