Mangrove species classification with UAV-based remote sensing data and XGBoost

نویسندگان

چکیده

æ— äººæœºé¥æ„Ÿæ•°æ®ä¼šè¡ç”Ÿå¤§é‡çš„å ‰è°±ã€çº¹ç†ä¸Žç»“æž„ç‰¹å¾ï¼Œå¦‚ä½•æå–ä¼˜åŠ¿ç‰¹å¾æ˜¯æé«˜çº¢æ ‘æž—ç‰©ç§åˆ†ç±»æ•ˆçŽ‡å’Œç²¾åº¦çš„å ³é”®é—®é¢˜ã€‚é’ˆå¯¹æ·±åœ³ç¦ç”°çº¢æ ‘æž—è‡ªç„¶ä¿æŠ¤åŒºç¼“å†²åŒºèŽ·å–çš„æ— äººæœºé«˜å ‰è°±å½±åƒå’ŒLiDARç‚¹äº‘æ•°æ®ï¼Œæœ¬ç ”ç©¶æ—¨åœ¨åˆ©ç”¨æžç«¯æ¢¯åº¦æå‡ç®—æ³•ï¼ˆXGBoostï¼‰çš„â€œç‰¹å¾é‡è¦æ€§â€å±žæ€§ç­›é€‰å‡ºé€‚åˆçº¢æ ‘æž—ç‰©ç§åˆ†ç±»çš„8ç±»ä¼˜åŠ¿ç‰¹å¾ï¼šåŸºäºŽæ— ‰è°±å½±åƒçš„å•ä¸€ç‰¹å¾ï¼ˆå ‰è°±æ³¢æ®µã€æ¤è¢«æŒ‡æ•°å’Œçº¹ç†ç‰¹å¾ï¼šF1—F3ï¼‰åŠå ¶èžåˆç‰¹å¾ï¼ˆF4)、基于LiDAR点云的单一特征(高度和强度特征:F5和F6ï¼‰åŠå ¶èžåˆç‰¹å¾ï¼ˆF7ï¼‰ã€é«˜å ‰è°±å½±åƒä¸ŽLiDAR点云的融合特征(F8);基于以上优势特征构建8个XGBooståˆ†ç±»æ¨¡åž‹ã€‚ç»“æžœè¡¨æ˜Žï¼šç»¼åˆç‰©ç§åˆ†ç±»ç²¾åº¦åŠå ¶åˆ¶å›¾ç»“æžœï¼ŒåŸºäºŽF8特征的模型分类性能最佳(总体精度为96.41%ï¼ŒèŽ«å °æŒ‡æ•°ä¸º0.5520);基于单一数据源融合特征(总体精度,F4:96.74%;F7:90.64%)的分类性能优于基于单一特征(总体精度,F1—F3:90.31%、92.20%和91.96%;F5和F6:87.66%和81.99%);基于融合特征(F4、F7和F8)和纹理特征(F3ï¼‰åˆ†ç±»å›¾çš„èŽ«å °æŒ‡æ•°æ¯”åŸºäºŽå•ä¸€ç‰¹å¾ï¼ˆF1、F2、F5和F6ï¼‰çš„æ›´å¤§ã€‚æœ¬æ–‡è®ºè¯äº†æ— äººæœºé¥æ„Ÿæ•°æ®å’ŒXGBoostæ–¹æ³•åœ¨åŸºäºŽåƒå ƒçš„çº¢æ ‘æž—ç‰©ç§ç²¾å‡†åˆ†ç±»ä¸Šå ·å¤‡å¯è¡Œæ€§ï¼Œå¯ä¸ºçº¢æ ‘æž—ç”Ÿæ€ç³»ç»Ÿå¥åº·ã€ä¿æŠ¤ä¸Žæ¢å¤çš„ç«‹ä½“ç›‘æµ‹æä¾›ç§‘å­¦ä¾æ®å’ŒæŠ€æœ¯æ”¯æ’‘ã€‚

برای دانلود رایگان 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

Low Cost UAV-based Remote Sensing for Autonomous Wildlife Monitoring

In recent years, developments in unmanned aerial vehicles, lightweight on-board computers, and low-cost thermal imaging sensors offer a new opportunity for wildlife monitoring. In contrast with traditional methods now surveying endangered species to obtain population and location has become more cost-effective and least time-consuming. In this paper, a low-cost UAV-based remote sensing platform...

متن کامل

Object-based classification of remote sensing data for change detection

In this paper, a change detection approach based on an object-based classification of remote sensing data is introduced. The approach classifies not single pixels but groups of pixels that represent already existing objects in a GIS database. The approach is based on a supervised maximum likelihood classification. The multispectral bands grouped by objects and very different measures that can b...

متن کامل

Remote Sensing in Mapping Mangrove Ecosystems - An Object-Based Approach

Over the past few decades, clearing for shrimp farming has caused severe losses of mangroves in the Mekong Delta (MD) of Vietnam. Although the increasing importance of shrimp aquaculture in Vietnam has brought significant financial benefits to the local communities, the rapid and largely uncontrolled increase in aquacultural area has contributed to a considerable loss of mangrove forests and to...

متن کامل

Spherical Classification of Remote Sensing Data

Real data are often characterized by high dimensional feature vectors. However, such data contain redundant information that may not be beneficial for analysis algorithms. As such, feature transformation arises in related fields of study, including geoscientific applications, as a means to capture the few characteristics that are useful for pattern analysis algorithms. In this study, we investi...

متن کامل

Remote Sensing Techniques for mangrove mapping

Mangroves, important components of the world’s coastal ecosystems, are threatened by the expansion of human settlements, the boom in commercial aquaculture, the impact of tidal waves and storm surges, etc. Such threats are leading to the increasing demand for detailed mangrove maps for the purpose of measuring the extent of the decline of mangrove ecosystems. Detailed mangrove maps at the commu...

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.20210281