ISPRS International Journal of Geo-Information, Год журнала: 2024, Номер 13(11), С. 402 - 402

Опубликована: Ноя. 7, 2024

The visual evaluation and characteristic analysis of urban rivers are pivotal for advancing our understanding waterscapes their surrounding environments. Unmanned aerial vehicles (UAVs) offer significant advantages over traditional satellite remote sensing, including flexible surveying, diverse perspectives, high-resolution imagery. This study centers on the Haihe River, South Canal, North Canal in Tianjin China, employing UAVs to capture continuous panoramic image data. Through immersive virtual reality (VR) technology, evaluations these images were obtained from a cohort young participants. These encompassed assessments scenic beauty, color richness, vitality, historical sense. Subsequently, computer vision techniques utilized quantitatively analyze proportions various landscape elements (e.g., trees, grass, buildings) within images. Clustering results semantic segmentation outcomes different points facilitated effective identification grouping river features. findings reveal differences vitality among whereas Canals exhibited limited sense history. Six elements—water bodies, buildings, etc.—comprised 90% images, forming primary characteristics three rivers. Nonetheless, uneven spatial distribution resulted notable variations features demonstrates that feature method based UAV can achieve quantitative multi-scene 3D landscapes, thereby providing robust scientific foundation optimization

Язык: Английский