Search Results (2)

Previous landscape design mostly relies on general standards, failing to fully consider gender differences in landscape visual perception, with relevant research still needing further exploration. This study takes Beijing’s Beihai Park as the research object, using five types of on-site-collected photos (water landscape, plant landscape, architectural landscape, path landscape, and square landscape) as stimuli. Twenty males and twenty females participated in an eye-tracking experiment and a questionnaire survey to analyze gender differences in the visual perception of these five landscapes. The results show the following: (1) females show a “core–radiation” pattern, focusing on mid-short vision and environmental details; males focus on distant views and functional areas. (2) Females have slightly higher APD and fixation counts, with stronger cognitive/emotional fluctuations; males have longer total fixation time and more sustained attention. (3) Males prefer architectural/square landscapes, emphasizing functionality; females favor water/plant landscapes, prioritizing emotional connection with nature. (4) The total fixation time significantly impacts subjective evaluations; the average fixation duration is gender-neutral but uniquely affects evaluations of certain landscape types. This study has guiding significance for enhancing park landscapes’ inclusiveness and attractiveness, promoting different genders’ participation and satisfaction, and boosting space vitality and utilization efficiency. Full article

Pine wilt disease is a highly contagious forest quarantine ailment that spreads rapidly. In this study, we designed a new Pine-YOLO model for pine wilt disease detection by incorporating Dynamic Snake Convolution (DSConv), the Multidimensional Collaborative Attention Mechanism (MCA), and Wise-IoU v3 (WIoUv3) into a YOLOv8 network. Firstly, we collected UAV images from Beihai Forest and Linhai Park in Weihai City to construct a dataset via a sliding window method. Then, we used this dataset to train and test Pine-YOLO. We found that DSConv adaptively focuses on fragile and curved local features and then enhances the perception of delicate tubular structures in discolored pine branches. MCA strengthens the attention to the specific features of pine trees, helps to enhance the representational capability, and improves the generalization to diseased pine tree recognition in variable natural environments. The bounding box loss function has been optimized to WIoUv3, thereby improving the overall recognition accuracy and robustness of the model. The experimental results reveal that our Pine-YOLO model achieved the following values across various evaluation metrics: MAP@0.5 at 90.69%, mAP@0.5:0.95 at 49.72%, precision at 91.31%, recall at 85.72%, and F1-score at 88.43%. These outcomes underscore the high effectiveness of our model. Therefore, our newly designed Pine-YOLO perfectly addresses the disadvantages of the original YOLO network, which helps to maintain the health and stability of the ecological environment. Full article