Semantic understanding of geo-objects’ relationship in high resolution remote sensing image driven by dual LSTM

نویسندگان

چکیده

é«˜åˆ†è¾¨çŽ‡é¥æ„Ÿå½±åƒä¸­çš„åœ°ç‰©ç›®æ ‡å ·æœ‰æ¸ æ™°çš„ç±»åˆ«å±žæ€§ä¸Žç©ºé—´å ³ç³»è¯­ä¹‰ã€‚åœ¨äººå·¥æ™ºèƒ½æŠ€æœ¯æ”¯æ’‘ä¸‹ï¼Œç”¨è®¡ç®—æœºè‡ªåŠ¨è®¤çŸ¥å ¶ç©ºé—´å ³ç³»å ·å¤‡äº†å¯è¡Œæ€§ã€‚ç›®å‰ï¼Œé¥æ„Ÿå½±åƒåœºæ™¯çš„è¯­ä¹‰ç†è§£ä¸»è¦ä¾æ‰˜å›¾åƒæè¿°ä»»åŠ¡ï¼ˆimage captionï¼‰ï¼ŒåŸºäºŽå½±åƒçš„å ¨å±€ç‰¹å¾ç”Ÿæˆæè¿°è¯­å¥ã€‚ä½†æ˜¯ï¼Œè¿™ç§ç²—ç²’åº¦ç‰¹å¾å®¹æ˜“å¯¼è‡´åœ°ç‰©ç›®æ ‡çš„ç±»åˆ«å±žæ€§åœ¨æè¿°è¯­å¥ç”Ÿæˆè¿‡ç¨‹ä¸­è¢«é”™è¯¯é¢„æµ‹ã€‚äº‹å®žä¸Šï¼Œä»¥åœ°ç‰©ç›®æ ‡ä½œä¸ºç©ºé—´å ³ç³»è¯­ä¹‰ç†è§£çš„åŸºæœ¬å•å ƒï¼Œæ›´ç¬¦åˆäººä»¬è®¤çŸ¥åœ°ç†ç©ºé—´çš„ä¹ æƒ¯ã€‚ä¸ºå¾—åˆ°æ›´å‡†ç¡®çš„æè¿°è¯­å¥ï¼Œæœ¬æ–‡æž„å»ºäº†åŸºäºŽåœ°ç‰©ç›®æ ‡çš„é¥æ„Ÿå½±åƒè¯­ä¹‰ç†è§£æ•°æ®é›†ï¼Œå¹¶æå‡ºåŒLSTMé©±åŠ¨çš„åœ°ç‰©ç›®æ ‡ç©ºé—´å ³ç³»è¯­ä¹‰ç†è§£æ–¹æ³•ã€‚è¯¥æ–¹æ³•ç”¨ç›®æ ‡æ£€æµ‹æ¨¡åž‹è¯†åˆ«å½±åƒä¸­çš„æ˜¾è‘—ç›®æ ‡ï¼Œå°†è¿™äº›ç›®æ ‡ç‰¹å¾è¾“å ¥åˆ°è¯­è¨€æ¨¡åž‹ï¼Œä»¥ç¼“è§£æè¿°è¯­å¥ä¸­ç±»åˆ«è¢«é”™è¯¯é¢„æµ‹çš„é—®é¢˜ã€‚è¿›è€Œï¼Œä¸ºåˆ©ç”¨é¥æ„Ÿå½±åƒåœºæ™¯ä¿¡æ¯ï¼Œå°†å½±åƒå ¨å±€ç‰¹å¾ä¸Žç›®æ ‡åŒºåŸŸç‰¹å¾è¿›è¡Œèžåˆï¼Œå¹¶ç”¨åŒLSTMé¢„æµ‹ç›®æ ‡çš„æ³¨æ„åŠ›åˆ†å¸ƒï¼Œæé«˜æè¿°è¯­å¥ç”Ÿæˆè´¨é‡ã€‚å¯¹æ¯”å®žéªŒç»“æžœè¡¨æ˜Žï¼Œè¯¥æ–¹æ³•èƒ½ç”Ÿæˆæ›´å‡†ç¡®çš„å›¾åƒæè¿°ã€‚

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Classification of high resolution remote sensing image based on Geo- ontology and Conditional Random Fields

The availability of high spatial resolution remote sensing data provides new opportunities for urban land-cover classification. More geometric details can be observed in the high resolution remote sensing image, Also Ground objects in the high resolution remote sensing image have displayed rich texture, structure, shape and hierarchical semantic characters. More landscape elements are represent...

متن کامل

Remote sensing minefield area reduction: Semantic knowledge-based image understanding

This study addresses the design issues of an intelligent system for image understanding applied to remote sensing minefield area reduction. We propose a system using a combination of image processing techniques and a knowledge-based intelligent scheme that interactively cooperate together to produce a danger map of the surveyed area. This contribution suggests a semantic knowledge-based scene i...

متن کامل

Enhancing a eucalypt crown condition indicator driven by high spatial and spectral resolution remote sensing imagery

Individual crown condition of Eucalyptus gomphocephala was assessed using two classification models to understand changes in forest health through space and time. Using high resolution (0.5 m) digital multispectral imagery, predictor variables were derived from textural and spectral variance of all pixels inside the crown area. The results estimate crown condition as a surrogate for tree health...

متن کامل

The Image Registration Technique for High Resolution Remote Sensing Image in Hilly Area

Image registration is one of the important image processing procedures in remote sensing; it has been studied and developed for a long time. However, until now, it is still rare to find an accurate, robust, and automatic image registration method, and most existing image registration methods are designed for particular application. At present, high resolution remote sensing images have made it ...

متن کامل

Exterior Orientation for Remote Sensing Image with High Resolution by Linear Feature

An automatic approach to the exterior orientation by using linear primitives such as rivers and roads, which are extracted from the image and match to the existing vector data, is presented in this paper. Because the automatic identifying line features is much easier than point features, so that the observations are increased significantly and the exterior orientation can be improved. Proposed ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Journal of remote sensing

سال: 2021

ISSN: ['1007-4619', '2095-9494']

DOI: https://doi.org/10.11834/jrs.20210340