Exploring the Determinants of Urban Green Space Utilization Based on Microblog Check-In Data in Shanghai, China

Urban green space has significant social, ecological, cultural and economic value. This study uses social media data to examine the spatiotemporal utilization of major parks in Shanghai and explore the determinants of their recreational attraction. Methods: Based on microblog check-in data between 2012 and 2018 across 17 parks in Shanghai, we investigated the patterns at different temporal scales (weekly, seasonal and annual) and across workdays and weekends by using log-linear regression models. Results: Our findings indicate that both internal and external factors affect park utilization. In particular, the presence of sports facilities significantly contributes to higher visit frequency. Factors such as the number of subway stations nearby, scenic quality and popularity have a positive impact on check-in numbers, while negative factors affecting park use are number of roads, ticket price and average surrounding housing price. Across different temporal scales, the use patterns of visitors have obvious seasonal and monthly tendencies, and the differences of workday and weekend models lie in external factors’ impacts. Conclusions: In order to achieve the goal of better serving the visitors, renewal of urban green spaces in megacities should consider these influential factors, increase sports facilities, subway stations nearby and improve scenic quality, popularity and water quality. This study on spatiotemporal utilization of urban parks can help enhance comprehensive functions of urban parks and be helpful for urban renewal strategies.

SPDNet: A Real-Time Passenger Detection Method Based on Attention Mechanism in Subway Station Scenes

In order to implement real-time detection of passengers in subway stations, this paper proposes the SPDNet based on YOLOv4. Aiming at the low detection accuracy of passengers in the subway station due to uneven light conditions, we introduce the attention mechanism CBAM to recalibrate the extracted features and improve the robustness of the network. For the crowded areas in the subway station, we use the K-means++ algorithm to generate anchors that are more consistent with the passenger aspect ratio based on the dataset KITTI, which mitigates the missing caused by the incorrect suppression of true positive boxes by the Nonmaximum Suppression algorithm. We train and test our SPDNet on the KITTI dataset and prove the superiority of our method. Then, we carry out transfer learning based on the subway surveillance video dataset collected by ourselves to make it conform to the distorted passenger targets under the angle of the surveillance camera. Finally, we apply our network in a Beijing subway station and achieve satisfactory results.

Research on Subway Pedestrian Detection Algorithm Based on Big Data Cleaning Technology

The pedestrian detection model has a high requirement on the quality of the dataset. Concerning this problem, this paper uses data cleaning technology to improve the quality of the dataset, so as to improve the performance of the pedestrian detection model. The dataset used in this paper is obtained from subway stations in Beijing and Nanjing. The data images’ quality is subject to motion blur, uneven illumination, and other noisy factors. Therefore, data cleaning is very important for this paper. The data cleaning process in this paper is divided into two parts: detection and correction. First, the whole dataset goes through blur detection, and the severely blurred images are filtered as the difficult samples. Then, the image is sent to DeblurGAN for deblur processing. 2D gamma function adaptive illumination correction algorithm is used to correct the subway pedestrian image. Then, the processed data is sent to the pedestrian detection model. Under different data cleaning datasets, through the analysis of the detection results, it is proved that the data cleaning process significantly improves the detection model’s performance.