Faster R-CNN based oceanic internal wave detection from SAR images in the South China Sea

نویسندگان

چکیده

æµ·æ´‹å† æ³¢å¹¿æ³›å­˜åœ¨äºŽä¸–ç•Œå„å¤§æ´‹å’Œè¾¹ç¼˜æµ·ä¸­ï¼Œåœ¨æµ·æ´‹èƒ½é‡ä¸²çº§ä¸­æ‰®æ¼”ç€é‡è¦è§’è‰²ï¼Œåœ¨æµ·æ´‹èµ„æºå¼€å‘ã€æµ·æ´‹å·¥ç¨‹å»ºè®¾å’Œæµ·æ´‹å†›äº‹æ´»åŠ¨ç­‰æ–¹é¢å‡å ·æœ‰é‡è¦å­¦æœ¯ä»·å€¼ä¸Žå®žé™ æ„ä¹‰ã€‚æµ·æ´‹å† æ³¢åœ¨åˆæˆå­”å¾„é›·è¾¾SAR(Synthetic Aperture Radar)图像上呈现出亮暗相间的条纹状特征。本文利用2001年—2020å¹´å—æµ·æµ·åŸŸåŒ å«ä¸åŒå¾®æ³¢æ³¢æ®µï¼ˆC、L、X)、不同极化方式、不同空间分辨率的631å¹ æ˜Ÿè½½SAR图像,构建了5480个SARå›¾åƒå—æµ·æµ·æ´‹å† æ³¢æ ·æœ¬ï¼Œç»“åˆFaster R-CNNæ¡†æž¶ï¼Œåˆ©ç”¨è¿ç§»å­¦ä¹ çš„æ–¹æ³•ï¼Œå®žçŽ°SARå›¾åƒä¸Šçš„æµ·æ´‹å† æ³¢è‡ªåŠ¨æ£€æµ‹ã€‚æ¨¡åž‹è¯†åˆ«å‡†ç¡®çŽ‡è¾¾åˆ°95.7%,召回率为92.3%,在准确率较高的同时还能保持较低的虚警率。该算法的建立使得基于海量卫星SARæ•°æ®æ£€å‡ºæµ·æ´‹å† æ³¢æˆä¸ºå¯èƒ½ï¼Œä»Žè€Œä¸ºé’ˆå¯¹æ€§åœ°å¼€å±•å† æ³¢åŠ¨åŠ›å‚æ•°åæ¼”å’Œè¿‡ç¨‹ç ”ç©¶æä¾›äº†æŠ€æœ¯å’Œæ•°æ®åŸºç¡€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

Internal Wave Energy Budget Studies in the South China Sea

We are focused on understanding small-scale processes that influence the ocean’s thermodynamic and dynamic properties on the sub-mesoscale (scales less than 10 km). This includes the role of turbulence in modifying the upper ocean temperature and density structure. In the South China Sea, largeamplitude, nonlinear waves force turbulence in the seasonally variable continental shelf region. New o...

متن کامل

Object Detection in Video using Faster R-CNN

Convolutional neural networks (CNN) currently dominate the computer vision landscape. Recently, a CNN based model, Faster R-CNN [1], achieved stateof-the-art performance at object detection on the PASCAL VOC 2007 and 2012 datasets. It combines region proposal generation with object detection on a single frame in less than 200ms. We apply the Faster R-CNN model to video clips from the ImageNet 2...

متن کامل

Symbol detection in online handwritten graphics using Faster R-CNN

Symbol detection techniques in online handwritten graphics (e.g. diagrams and mathematical expressions) consist of methods specifically designed for a single graphic type. In this work, we evaluate the Faster R-CNN object detection algorithm as a general method for detection of symbols in handwritten graphics. We evaluate different configurations of the Faster R-CNN method, and point out issues...

متن کامل

Internal Wave Detection in SAR Image

ABATRACT Bragg scattering process in sea surface represent the meso-scale feature of sea processes in SAR image. SAR image data is used to for large scales area of monitoring on near real time data. In this research, wavelet analysis is applied to monitor internal wave in ERS-2 SAR image. Wavelet transform of SAR image can be used as feature detection and image enhancement. Furthermore, wavelet...

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: 2023

ISSN: ['1007-4619', '2095-9494']

DOI: https://doi.org/10.11834/jrs.20211324