Analyzing urban public sports facilities for recognition and optimization using intelligent image processing

Abstract

Quality of urban public sports facilities has an implication for increasing sports satisfaction levels in individuals and for developing a better way of life in cities. The current study aims to assess and improve urban public sports services through intelligent image processing techniques for assessing sports facilities. The method incorporates an optimized Residual-Shuffle Network modified by a boosted variant of Spring Search Algorithm (BSSA) for efficient image recognition along with metaheuristics and super-efficiency data envelopment analysis (SE-DEA) model. The images captured systematically using photographic equipment identify such key information as facility usage, viewer demographics, and activity levels by deep learning algorithms. Sports facilities’ effectiveness evaluation for improvement and optimization has been done using metaheuristics and SE-DEA model. The model has been verified with other modern methods, including Faster R-CNN and Convolutional Neural Network (CNN). The results indicate that the SE-DEA model with an accuracy of 94.76% in recognizing sports facilities, outperforming advanced comparative models like Faster R-CNN (74.21%) and CNN (60.54%). The mean execution time of SE-DEA is 5.6 s, which is slower than Faster R-CNN (4.13 s) but faster than CNN (10.98 s). Also, the SE-DEA model provides a significant reduction in costs, with a public service fee of 1200 (compared to 3200 for traditional public services) and a facility maintenance cost of 1000 (compared to 2500 for traditional public services).