{"title":"基于多尺度快速rcnn的飞机检测","authors":"Wei Miao, Z. Luo","doi":"10.1109/ICVRV.2018.00026","DOIUrl":null,"url":null,"abstract":"Remote sensing image recognition has been widely used in civil and military fieldsDIn view of plenty of interference factors in remote-sensing aircraftCsuch as shadeCnoiseCthe changing of perspectiveCetc. An improved target recognition algorithm in remote sensing image based on Faster-RCNN is proposed which uses a standard Region Proposal Network (RPN) generation and incorporates feature maps from shallower convolution feature maps. Convolution neural network is adopted to recognize aircraft target in complex environment , enhance the global context and local information to avoid information loss in the process of feature extractionCwhich improves recognition rate. Simulation results show that the feasibility of aircraft target recognition algorithm in remoting sensing image and the scale and posture changes of target can be overcome.MeanwhileCthe proposed algorithm has higher recognition effect and stronger robustness than traditional Faster-RCNN and BP neural network and support vector machine ( SVM) methods.","PeriodicalId":159517,"journal":{"name":"2018 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"50 2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Aircraft Detection Based on Multiple Scale Faster-RCNN\",\"authors\":\"Wei Miao, Z. Luo\",\"doi\":\"10.1109/ICVRV.2018.00026\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Remote sensing image recognition has been widely used in civil and military fieldsDIn view of plenty of interference factors in remote-sensing aircraftCsuch as shadeCnoiseCthe changing of perspectiveCetc. An improved target recognition algorithm in remote sensing image based on Faster-RCNN is proposed which uses a standard Region Proposal Network (RPN) generation and incorporates feature maps from shallower convolution feature maps. Convolution neural network is adopted to recognize aircraft target in complex environment , enhance the global context and local information to avoid information loss in the process of feature extractionCwhich improves recognition rate. Simulation results show that the feasibility of aircraft target recognition algorithm in remoting sensing image and the scale and posture changes of target can be overcome.MeanwhileCthe proposed algorithm has higher recognition effect and stronger robustness than traditional Faster-RCNN and BP neural network and support vector machine ( SVM) methods.\",\"PeriodicalId\":159517,\"journal\":{\"name\":\"2018 International Conference on Virtual Reality and Visualization (ICVRV)\",\"volume\":\"50 2 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 International Conference on Virtual Reality and Visualization (ICVRV)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICVRV.2018.00026\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 International Conference on Virtual Reality and Visualization (ICVRV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICVRV.2018.00026","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Aircraft Detection Based on Multiple Scale Faster-RCNN
Remote sensing image recognition has been widely used in civil and military fieldsDIn view of plenty of interference factors in remote-sensing aircraftCsuch as shadeCnoiseCthe changing of perspectiveCetc. An improved target recognition algorithm in remote sensing image based on Faster-RCNN is proposed which uses a standard Region Proposal Network (RPN) generation and incorporates feature maps from shallower convolution feature maps. Convolution neural network is adopted to recognize aircraft target in complex environment , enhance the global context and local information to avoid information loss in the process of feature extractionCwhich improves recognition rate. Simulation results show that the feasibility of aircraft target recognition algorithm in remoting sensing image and the scale and posture changes of target can be overcome.MeanwhileCthe proposed algorithm has higher recognition effect and stronger robustness than traditional Faster-RCNN and BP neural network and support vector machine ( SVM) methods.