This research explores the environmental safety challenges faced by pocket parks in the context of urban aging within Chinese cities. It systematically analyzes visual elements that influence the elderly’s perception of environmental safety by applying interpretable machine learning techniques. By integrating panoramic image semantic segmentation and explainable AI models (e.g., SHAP and PDP), the study transforms subjective environmental perception into measurable indicators and constructs an environmental safety perception model using the LightGBM algorithm. Results indicate that sufficient pedestrian areas and moderate crowd activities significantly enhance safety perception among the elderly. Conversely, the presence of cars emerges as the most substantial adverse factor. Natural elements, such as vegetation and grass, exhibit nonlinear effects on safety perception, with an optimal threshold range identified. The research further elucidates the intricate synergies and constraints among visual elements, underscoring that the highest perceived safety arises from the synergistic combination of positive factors. This study deepens the understanding of environmental perception among the elderly and offers a data-driven framework and practical guidelines for urban planners and designers. It holds significant theoretical and practical implications for advancing the refined and human-centered renewal of urban public spaces.

As global population aging intensifies, pocket parks in high-density urban areas have emerged as vital venues for older adults' daily activities. However, existing research predominantly relies on roadway-captured street view imagery (SVI), which inadequately captures the internal spatial heterogeneity and micro-scale visual features of these parks. To address this, we evaluated the age-friendly spatial visual quality (SVQ) of 29 pocket parks on Xiamen Island from an internal panoramic perspective. We developed the Older-Adult Friendly Visual Quality Index (OAVQ-I) utilizing panoramic imagery and deep learning-based semantic segmentation to quantify six indicators: Green View Ratio (GVR), Natural Elements Richness (NER), Sky Openness (SO), Enclosure (Encl), Rest Facilities Visibility (RFV), and Walkable Space Ratio (WSR). Coefficient of variation (CV) objective weighting revealed that RFV, Encl, and SO exhibit the highest relative dispersion among the indicators, collectively comprising 87% of the total weight. Notably, a high GVR does not guarantee high quality; excessively dense vegetation can create an "ecological trap" by obstructing facilities and limiting light penetration. Comparative case analysis identified three distinct spatial patterns: high-quality friendly, moderately friendly, and low-quality (requiring improvement). This study advances urban green space evaluation from macroscopic statistical assessment to microscopic functional diagnosis. The findings suggest that urban renewal should transition from blindly increasing greenery to optimizing spatial quality—specifically by pruning mid-level vegetation to enhance facility visibility and illumination—thereby creating safer, more supportive environments for older adults.