• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.5
• /
• pp.539-544
• /
• 2016

The aim of this study is identifying characteristics of spatial distribution using submerged debris data on the bottom of sea ground. Marine debris is classified into floating and submerged debris. These are polluting marine environment, ecology and habitat by floating and submerged. Also it takes a lot of money when it is to process the waste flowing into the ocean. In this study, it is used data of submerged debris by side scan sonar on the bottom of sea ground in Pohang port. Submerged distribution map is made to identify spatial classified characteristics of SMD(submerged marine debris) using by position and weight per area of SMD.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.2
• /
• pp.295-307
• /
• 2021

The Korean Peninsula is surrounded on three sides by the East Sea, West Sea and South Sea which are connected to many rivers and streams, thereby facilitating easy inflow of debris from land. Furthermore, excessive debris inflow to the sea because of active fishing and various recreational activities. Debris entering the sea are weighted over time and settle in the seabed, thus, making direct monitoring of debris impossible and its collection difficult. Uncollected submerged marine debris affects the seabed ecosystem and water quality and can cause ghost fishing and ship accidents, especially due to waste net ropes and waste fishing gears. Therefore, understanding the debris distribution characteristics is necessary to assist quick collection of these debris (waste net ropes and waste fishing gears). Thus, this study conducted a survey of debris deposited in the seas of 39 ports. Furthermore, distribution characteristics and compositions of submerged marine debris were identified by a map prepared through GIS-based spatial analysis of the East Sea. Consequently, 58% of waste tires in the East Sea were concentrated in breakwaters and ship berthing facilities. Moreover, 26 % of waste plastics were distributed outside the port. Identifying the distinct distribution characteristics of submerged marine debris was difficult; however, compared with others, the distribution of waste plastics was possible outside the port. The findings of this study can serve as baseline data to assist the collection of submerged marine debris using the distribution characteristics.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1329-1341
• /
• 2022

Destroying the marine environment and marine ecosystem and causing marine accidents, marine debris is generated every year, and among them, submerged marine debris is difficult to identify and collect because it is on the seabed. Therefore, deep-learning-based semantic segmentation was experimented on waste fish nets and waste ropes using underwater images to identify efficient collection and distribution. For segmentation, a high-resolution network (HRNet), a state-of-the-art deep learning technique, was used, and the performance of each optimizer was compared. In the segmentation result fish net, F1 score=(86.46%, 86.20%, 85.29%), IoU=(76.15%, 75.74%, 74.36%), For the rope F1 score=(80.49%, 80.48%, 77.86%), IoU=(67.35%, 67.33%, 63.75%) in the order of adaptive moment estimation (Adam), Momentum, and stochastic gradient descent (SGD). Adam's results were the highest in both fish net and rope. Through the research results, the evaluation of segmentation performance for each optimizer and the possibility of segmentation of marine debris in the latest deep learning technique were confirmed. Accordingly, it is judged that by applying the latest deep learning technique to the identification of submerged marine debris through underwater images, it will be helpful in estimating the distribution of marine sedimentation debris through more accurate and efficient identification than identification through the naked eye.