{"title":"增强现实和机器学习的内容增强","authors":"J. Freeman","doi":"10.1071/ES19046","DOIUrl":null,"url":null,"abstract":"\nContent enhancement of real-world environments is demonstrated through the combination of machine learning methods with augmented reality displays. Advances in machine learning methods and neural network architectures have facilitated fast and accurate object and image detection, recognition and classification, as well as providing machine translation, natural language processing and neural network approaches for environmental forecasting and prediction. These methods equip computers with a means of interpreting the natural environment. Augmented reality is the embedding of computer-generated assets within the real-world environment. Here I demonstrate, through the development of four sample mobile applications, how machine learning and augmented reality may be combined to create localised, context aware and user-centric environmental information delivery channels. The sample mobile applications demonstrate augmented reality content enhancement of static real-world objects to deliver additional environmental and contextual information, language translation to facilitate accessibility of forecast information and a location aware rain event augmented reality notification application that leverages a nowcasting neural network.\n","PeriodicalId":55419,"journal":{"name":"Journal of Southern Hemisphere Earth Systems Science","volume":null,"pages":null},"PeriodicalIF":3.6000,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Content enhancement with augmented reality and machine learning\",\"authors\":\"J. Freeman\",\"doi\":\"10.1071/ES19046\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\nContent enhancement of real-world environments is demonstrated through the combination of machine learning methods with augmented reality displays. Advances in machine learning methods and neural network architectures have facilitated fast and accurate object and image detection, recognition and classification, as well as providing machine translation, natural language processing and neural network approaches for environmental forecasting and prediction. These methods equip computers with a means of interpreting the natural environment. Augmented reality is the embedding of computer-generated assets within the real-world environment. Here I demonstrate, through the development of four sample mobile applications, how machine learning and augmented reality may be combined to create localised, context aware and user-centric environmental information delivery channels. The sample mobile applications demonstrate augmented reality content enhancement of static real-world objects to deliver additional environmental and contextual information, language translation to facilitate accessibility of forecast information and a location aware rain event augmented reality notification application that leverages a nowcasting neural network.\\n\",\"PeriodicalId\":55419,\"journal\":{\"name\":\"Journal of Southern Hemisphere Earth Systems Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2020-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Southern Hemisphere Earth Systems Science\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1071/ES19046\",\"RegionNum\":4,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Earth and Planetary Sciences\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Southern Hemisphere Earth Systems Science","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1071/ES19046","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Earth and Planetary Sciences","Score":null,"Total":0}
Content enhancement with augmented reality and machine learning
Content enhancement of real-world environments is demonstrated through the combination of machine learning methods with augmented reality displays. Advances in machine learning methods and neural network architectures have facilitated fast and accurate object and image detection, recognition and classification, as well as providing machine translation, natural language processing and neural network approaches for environmental forecasting and prediction. These methods equip computers with a means of interpreting the natural environment. Augmented reality is the embedding of computer-generated assets within the real-world environment. Here I demonstrate, through the development of four sample mobile applications, how machine learning and augmented reality may be combined to create localised, context aware and user-centric environmental information delivery channels. The sample mobile applications demonstrate augmented reality content enhancement of static real-world objects to deliver additional environmental and contextual information, language translation to facilitate accessibility of forecast information and a location aware rain event augmented reality notification application that leverages a nowcasting neural network.
期刊介绍:
The Journal of Southern Hemisphere Earth Systems Science (JSHESS) publishes broad areas of research with a distinct emphasis on the Southern Hemisphere. The scope of the Journal encompasses the study of the mean state, variability and change of the atmosphere, oceans, and land surface, including the cryosphere, from hemispheric to regional scales.
general circulation of the atmosphere and oceans,
climate change and variability ,
climate impacts,
climate modelling ,
past change in the climate system including palaeoclimate variability,
atmospheric dynamics,
synoptic meteorology,
mesoscale meteorology and severe weather,
tropical meteorology,
observation systems,
remote sensing of atmospheric, oceanic and land surface processes,
weather, climate and ocean prediction,
atmospheric and oceanic composition and chemistry,
physical oceanography,
air‐sea interactions,
coastal zone processes,
hydrology,
cryosphere‐atmosphere interactions,
land surface‐atmosphere interactions,
space weather, including impacts and mitigation on technology,
ionospheric, magnetospheric, auroral and space physics,
data assimilation applied to the above subject areas .
Authors are encouraged to contact the Editor for specific advice on whether the subject matter of a proposed submission is appropriate for the Journal of Southern Hemisphere Earth Systems Science.