The applied research in remote sensing images has been pushed by convolutional neural network (CNN). Because of the fixed size of the perceptual field, CNN is unable to model global semantic relevance. Modeling global semantic information is possible with the self-attentive Transformer-based model. However, the method of patch computation used by Transformer for self-attentive computation ignores the spatial information inside each patch. To address these issues, we offer the STransFuse model as a new semantic segmentation method for remote sensing images. It is a model that combines the benefits of Transformer with CNN to improve the segmentation quality of various remote sensing images. We employ a staged model to extract coarse-grained and fine-grained feature representations at various semantic scales, unlike earlier techniques based on Transformer model fusion. In order to take full advantage of the features acquired at different stages, we designed an Adaptive Fusion Module (AFM). This module adaptively fuses the semantic information between features at different scales employing a selfattentive mechanism. The OA of our proposed model on the Vaihingen dataset is 1.36% higher than the baseline, and 1.27% improvement in OA over baseline on the Potsdam dataset. When compared to other advanced models, the STransFuse model performs admirably.
BACKGROUND: In 2017 Tuta absoluta was identified as an invasive species in China. Due to its rapid geographic expansion and the severe crop damage it causes, T. absoluta poses a serious threat to China's tomato production industry. To determine its geographic distribution and host range, intensive surveys and routine monitoring were conducted across the Chinese mainland between 2018 and 2019. The population colonization coefficient (PCC; ratio of colonized sites and prefectures) and population occurrence index (POI; ratio of infested host species and PCCs) were calculated.RESULTS: In northwestern China, T. absoluta populations established in Xinjiang exhibited a medium PCC value (∼0.03). In southwestern China, populations in Yunnan and its five neighboring provinces exhibited high (∼0.50 in Yunnan and Guizhou), or low (<0.02 in Guangxi, Sichuan, Hunan, and Chongqing) PCC values. In the Chinese mainland, infestations of four crop plant species (tomato, eggplant, potato, and Chinese lantern) and two wild plant species (black nightshade and Dutch eggplant) were identified; tomatoes were infested in every colonized province. Chinese lantern and Dutch eggplant are potentially novel hosts. Yunnan, Guizhou, and Xinjiang experienced the most serious damage (POI). In southwestern China, observed damage significantly decreased with increased distance from the first discovery site of T. absoluta to the farthest county of an infested province increased. CONCLUSION: T. absoluta populations are well-established and could potentially spread to other regions of China. The present study helps to inform the establishment of better pest management guidelines and strategies in China and tomato-producing regions worldwide.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.