Research on visual quality assessment and landscape elements influence mechanism of rural greenways

•A quantitative evaluation model based on the subjective and objective influence of visual landscape components.•The composition of landscape elements in rural greenways and the ranking of their impact intensity.•The interrelationships among landscape elements constitute the landscape characteristics and influence visual quality.•The eye movement model and the evaluation model (SBE) have consistency. Rural landscapes have significant ecological, historical, and cultural value including numerous green spaces and forest spaces that should be protected and utilized. With the growing demand for green tourism in rural areas in recent years, rural greenways have become increasingly crucial for promoting urban–rural development by connecting linear spatial corridors such as landscape patches, scenic pathways, and strip woodlands. The accuracy and universality of landscape visual quality assessment affect the construction and enhancement of linear landscapes. The previous studies predominantly focused on individual perceptions of greenway landscapes, neglecting the comprehensive visual characteristics of both internal composition and visible surroundings.The evaluation model usually are purely subjective and overall evaluations, lacking the exploration of prediction mechanisms and specific analyses of constituent elements. This study correlates the percentage of elements obtained from image segmentation with subjective evaluation, aims to derive the influence ranking of constituent elements and the visual quality prediction model of visual space, and compares it with the results of objective experiments to further improve the objectivity of the conclusions. Based on visual quality assessment, this study utilize deep learning, eye movement analysis, and visual elements assessment to obtain objective results for visual quality assessment of rural greenways, analyze their influencing factors. A quantitative evaluation model based on the subjective and objective influence of visual landscape components was constructed by combining deep learning and eye movement information processing with human–machine–environment synchronous quantitative analysis technology. This model reveals then relationship between visual influence elements and the influence strength of rural greenway landscapes. The attractiveness strength of spatial visual elements of rural greenway landscapes is consistent with human aesthetic preferences, visual perception, and physiological responses. This s