Unveiling Urban River Visual Features Through Immersive Virtual Reality: Analyzing Youth Perceptions with UAV Panoramic Imagery

• Published in: ISPRS international journal of geo-information 2024-11, Vol.13 (11), p.402
• Main Authors: Shou, Yunlei, Lei, Zexin, Li, Jiaying, Luo, Junjie
• Format: Article
• Language: English
• Subjects: Aerial surveying; Aerial surveys; Aesthetics; Artificial satellites in remote sensing; Buildings; Canals; Cluster analysis; Clustering; Color; Computer applications; Computer vision; Data collection; Drone aircraft; Image processing; Image resolution; Image segmentation; Imagery; Immersive virtual reality; Machine vision; Mental task performance; Perceptions; Photography; Quantitative analysis; Remote sensing; Rivers; riverscapes; Semantic segmentation; Semantics; Spatial distribution; Technology assessment; Teenagers; UAV remote sensing; Unmanned aerial vehicles; Urban areas; Virtual environments; Virtual reality; visual perception; Visual system; Youth
• ISSN: 2220-9964; 2220-9964
• DOI: 10.3390/ijgi13110402

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