Search

Wearing gloves during machinery operation in workshops is essential for preventing accidental injuries, such as mechanical damage and burns. Ensuring that workers are wearing gloves is a key strategy for accident prevention. Consequently, this study proposes a glove detection algorithm called YOLOv8-AFPN-M-C2f based on YOLOv8, offering swifter detection speeds, lower computational demands, and enhanced accuracy for workshop scenarios. This research innovates by substituting the head of YOLOv8 with the AFPN-M-C2f network, amplifying the pathways for feature vector propagation, and mitigating semantic discrepancies between non-adjacent feature layers. Additionally, the introduction of a superficial feature layer enriches surface feature information, augmenting the model's sensitivity to smaller objects. To assess the performance of the YOLOv8-AFPN-M-C2f model, this study conducted multiple experiments using a factory glove detection dataset compiled for this study. The results indicate that the enhanced YOLOv8 model surpasses other network models. Compared to the baseline YOLOv8 model, the refined version shows a 2.6% increase in mAP@50%, a 63.8% rise in FPS, and a 13% reduction in the number of parameters. This research contributes an effective solution for the detection of glove adherence. [ABSTRACT FROM AUTHOR]

With the rapid development of urbanization, it is an important goal for urban green space (UGS) to meet the needs of residents' production and life using a supply–demand evaluation method of ecosystem service (ES). However, most studies have considered all functional types of UGS as the supply side, or rely solely on a single supply or demand side to conduct ecosystem service function (ESF) evaluation, resulting in less accurate and targeted research findings. As a result, a novel methodological framework for matching each ESF with corresponding functional types of UGS, and considering both supply and demand sides have been required. Firstly, the object-oriented approach combining support vector machine (SVM) and normalized difference vegetation index (NDVI) was used to automatically identify UGS, and integrated Point of Interest (POI), urban built-up area, road land, parcel, and socio-economic data to classify six functional types of UGS using the near-convex-hull. Next, matching the functional types of UGS with five ESFs, both supply and demand status were evaluated using the carbon sequestration and release analysis, Gaussian two-step floating catchment area, and spatial equilibrium degree methods. This method was demonstrated in Beijing, China. The results show: (1) the ES supply–demand situation provided by each functional type of UGS is different in five ESFs; (2) considering both supply and demand is more intuitive to see whether the city's demand for UGS has been met. Our results provide a new perspective for evaluating the contribution of UGS and have practical implications for UGS planning. [ABSTRACT FROM AUTHOR]