• Korean Journal of Heritage: History & Science
• /
• v.56 no.2
• /
• pp.172-203
• /
• 2023

<Cheongdamdo>(true-view landscape painting) was identified in this study to be a folding screen painting painted by Jeong Seon(a.k.a. Gyeomjae, 1676~1759) in the 32nd year of King Yeongjo(1756) while exploring the Cheongdam area located in Mt. Bukhansan near Seoul. Cheongdam Byeol-eop(Korean villa), consisting of Waunru Pavilion and Nongwolru Pavilion, was a cultural and artistic base at that time, where Nakron(Confucian political party) education took place and the Baegak Poetry Society met. <Cheongdamdo> is a painting that recalls a period of autumn rainfall in 1756 when Jeong Seon arrived in the Cheongdam valley with his disciple Kim Hee-sung(a.k.a. Bulyeomjae, 1723~1769) and met Hong Sang-han(1701~1769). It focuses on the valley flowing from Insubong peak to the village entrance. The title has a dual meaning, emphasizing "Cheongdam", a landscape feature that originated from the name of the area, while also referring to the whole scenery of the Cheongdam area. The technique of drastically brushing down(刷擦) wet pimajoon(hanging linen), the expression of soft horizontal points(米點), and the use of fine brush strokes reveal Jeong Seon's mature age. In particular, considering the contrast between the rock peak and the earthy mountain and symmetry of the numbers, the attempt to harmonize yin and yang sees it regarded as a unique Jingyeong painting(眞境術) that Jeong Seon, who was proficient in 『The Book of Changes』, presented at the final stage of his excursion. 「Cheongdamdongbugi」(Personal Anthology) of Eo Yu-bong(1673~1744) was referenced when Jeong Seon sought to understand and express the true scenery of Cheongdam and the physical properties of the main landscape features in the villa garden. The characteristics of this garden, which Jeong Seon clearly differentiated from the field, suppressed the view of water with transformed and exaggerated rocks(水口막이), elaborately creating a rain forest to cover the villa(裨補林), and adding new elements to help other landscape objects function. In addition, two trees were tilted to effectively close the garden like a gate, and an artificial mountain belt(造山帶), the boundary between the outer garden and the inner garden, was built solidly like a long fence connecting an interior azure dragon(內靑龍) and interior white tiger(內白虎). This is the Bibo-Yeomseung painting(裨補厭勝術) that Jeong Seon used to turn the poor location of the Cheongdam Byeol-eop into an auspicious site(明堂). It is interpreted as being devised to be a pungsu(feng shui) trick, and considered an iconographic embodiment of ideal traditional landscape architecture that was difficult to achieve in reality but which was possible through painting.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.193-205
• /
• 2023

A large amount of floating debris from land-based sources during heavy rainfall has negative social, economic, and environmental impacts, but there is a lack of monitoring systems for floating debris accumulation areas and amounts. With the recent development of artificial intelligence technology, there is a need to quickly and efficiently study large areas of water systems using drone imagery and deep learning-based object detection models. In this study, we acquired various images as well as drone images and trained with You Only Look Once (YOLO)v5s and the recently developed YOLO7 and YOLOv8s to compare the performance of each model to propose an efficient detection technique for land-based floating debris. The qualitative performance evaluation of each model showed that all three models are good at detecting floating debris under normal circumstances, but the YOLOv8s model missed or duplicated objects when the image was overexposed or the water surface was highly reflective of sunlight. The quantitative performance evaluation showed that YOLOv7 had the best performance with a mean Average Precision (intersection over union, IoU 0.5) of 0.940, which was better than YOLOv5s (0.922) and YOLOv8s (0.922). As a result of generating distortion in the color and high-frequency components to compare the performance of models according to data quality, the performance degradation of the YOLOv8s model was the most obvious, and the YOLOv7 model showed the lowest performance degradation. This study confirms that the YOLOv7 model is more robust than the YOLOv5s and YOLOv8s models in detecting land-based floating debris. The deep learning-based floating debris detection technique proposed in this study can identify the spatial distribution of floating debris by category, which can contribute to the planning of future cleanup work.