With the growing awareness of public health, urban parks have increasingly become popular venues for physical activities due to their accessibility and pleasant landscapes, among which walking, jogging, and running dominate. This study innovatively integrates exercise trajectory data from the Strava platform and semantic segmentation technology to analyze the interaction mechanisms among park view elements, physical activities, and physiological responses, based on empirical data from three representative parks in Shanghai. This study includes the following: (1) acquiring hotspot exercise paths and physiological data (heart rate and speed) of walking, jogging, and running users through the open Strava platform; (2) conducting semantic segmentation on real-word photos of three case parks to extract 17 types of park elements; (3) applying Spearman’s correlation analysis to reveal the differential impacts of park elements on physiological responses under walking, jogging, and running behaviors, demonstrating that combinations of elements such as trees, water bodies, fences, and sky influence exercise performance; and (4) constructing scene modules for site attraction, training improvement, and restorative relaxation for walking, jogging, and running, and proposing phased landscape scene sequence strategies to provide quantitative guidance for health-oriented park planning and design. This study breaks through the limitations of traditional subjective evaluations by coupling objective physiological data with spatial elements, offering novel insights for optimizing the exercise functionality of urban green spaces.