Search Results (2)

In the field of remote sensing image segmentation, achieving high accuracy and efficiency in diverse and complex environments remains a challenge. Additionally, there is a notable imbalance between the underlying features and the high-level semantic information embedded within remote sensing images, and both global and local recognition improvements are also limited by the multi-scale remote sensing scenery and imbalanced class distribution. These challenges are further compounded by inaccurate local localization segmentation and the oversight of small-scale features. To achieve balance between visual space and semantic space, to increase both global and local recognition accuracy, and to enhance the flexibility of input scale features while supplementing global contextual information, in this paper, we propose a U-shaped hierarchical structure called ResU-Former. The incorporation of the Swin Residual Transformer block allows for the efficient segmentation of objects of varying sizes against complex backgrounds, a common scenario in remote sensing datasets. With the specially designed Swin Residual Transformer block as its fundamental unit, ResU-Former accomplishes the full utilization and evolution of information, and the maximum optimization of semantic segmentation in complex remote sensing scenarios. The standard experimental results on benchmark datasets such as Vaihingen, Overall Accuracy of 81.5%, etc., show the ResU-Former’s potential to improve segmentation tasks across various remote sensing applications. Full article

In small and medium-sized cities of China, walking plays an important role as a green and healthy way to travel. However, the intensification of motorized travel and poor planning of pedestrian transportation systems have resulted in poor travel experiences for residents. To encourage residents to change their mode of travel from motorized transport to greener modes, it is necessary to consider the characteristics of walking travel, design good walking street environments, and increase the advantages of walking in the downtown areas of small and medium-sized cities. In this study, a spatial environment model of a pedestrian street was constructed based on the walking score. Visual perception elements, street function elements, and walking scale elements were acquired by semantic segmentation of Baidu street view images obtained with the DeepLab model. Points of interest (POI) were obtained based on surveys, measurements, and the space syntax. Considering walking distances for small and medium-sized cities, the attenuation coefficient of a reasonable facility distance was adopted to modify the walking score. Based on the comprehensive score obtained, walking paths were divided into four categories: functionally preferred, visually preferred, scale preferred, and environmentally balanced. This categorization provides theoretical support for the design of pedestrian street space environments. Taking the pedestrian street in the city center of Gaoping in Shanxi Province, China as an example, the feasibility of the method and model was verified. Full article