改进Mask R-CNN模型的海洋锋检测  

Ocean front detection method based on improved Mask R-CNN

作　　者：徐慧芳[1,2] 黄冬梅 贺琪[1] 杜艳玲 覃学标[1] Xu Huifang;Huang Dongmei;He Qi;Du Yanling;Qin Xuebiao(College of Information Technology,Shanghai Ocean University,Shanghai 201306,China;College of Information Technology,Shanghai Jian Qiao University,Shanghai 201306,China;Shanghai University of Electric Power,Shanghai 201306,China)

机构地区：[1]上海海洋大学信息学院,上海201306 [2]上海建桥学院信息技术学院,上海201306 [3]上海电力大学,上海201306

出　　处：《中国图象图形学报》2021年第12期2981-2990,共10页Journal of Image and Graphics

基　　金：国家自然科学基金项目(41671431,41906179);上海市教育发展基金项目(AASH2004);国家海洋局数字海洋科学技术重点实验室开放基金项目(B201801029)。

摘　　要：目的海洋锋的高效检测对海洋生态环境变化、渔业资源评估、渔情预报及台风路径预测等具有重要意义。海洋锋具有边界信息不明显且多变的弱边缘性,传统基于梯度阈值法及边缘检测的海洋锋检测方法,存在阈值选择不固定、判定指标不一致导致检测精度较低的问题。针对上述问题,基于Mask R-CNN(region convolutional neural network)提出一种改进的海洋锋自动检测方法。方法兼顾考虑海洋锋的小数据量及弱边缘性,首先对数据扩增,并基于不同算法对海表温度(sea surface temperatures,SST)遥感影像进行增强;其次,基于迁移学习的思想采用COCO(common objects in context)数据集对网络模型进行初始化;同时,对Mask R-CNN中残差神经网络(residual neural network,ResNet)和特征金字塔模型(feature pyramid network,FPN)分别进行改进,在充分利用低层特征高分辨率和高层特征的高语义信息的基础上,对多个尺度的融合特征图分别进行目标预测,提升海洋锋的检测精度。结果为验证本文方法的有效性,从训练数据和实验模型上分别设计多组对比实验。实验结果表明,相比常用的Mask R-CNN和YOLOv3(you only look once)神经网络,本文方法对SST梯度影像数据集上的海洋锋检测效果最好,海洋锋的定位准确率(intersection over union,IoU)及检测平均精度均值(mean average precision,mAP)达0.85以上。此外,通过对比分析实验结果发现,本文方法对强海洋锋的检测效果明显优于弱海洋锋。结论本文根据专家经验设立合理的海洋锋检测标准,更好地考虑了海洋锋的弱边缘性。通过设计多组对比实验,验证了本文方法对海洋锋的高精度检测效果。Objective The efficient detection of ocean front is of great significance to study the efficient detection of ocean front for marine ecosystem,fishery resources assessment,fishery forecast and typhoon track prediction.Gradient threshold method and edge detection algorithm have been widely used in ocean front detection.Traditional gradient method mainly depends on the gradient threshold,the sea area with gradient value greater than the set threshold has been regarded as the existence of ocean front.However,the selection criteria of threshold cannot tailor the requirements of accurate detection of complex and diverse ocean fronts due to artificial setting dependence,so it is more suitable for the object detection with fixed edge(such as land).During to the weak edge information of ocean front,it is difficult to achieve the good effect through the traditional edge extraction algorithm.A new automatic detection method to detect the small data volume and weak marginal characteristics of ocean fronts has been considering.Based on the advantages of the Mask R-CNN(region convolutional neural network)for instance segmentation,an improved Mask R-CNN network has been applied to the detection of ocean fronts.The ocean front detection method based on the modified Mask R-CNN has evolved the establishment of ocean front detection standards and data preprocessing,such as data expansion,data enhancement and labeling operations.High-precision detection of ocean fronts has been realized based on multiple iterations of training and parameter correction.Method First,the remote sensing images have been performed expansion operations for the small amount of data and the weak edge characteristics,such as rotating,flipping and cropping.Total 2100 images have been obtained including 800 original images,500 rotation and flip processing images and 800 random cropping processing images.Meanwhile,sea surface temperatures(SST)remote sensing images have been enhanced based on deep closest point(DCP)and contrast limited adaptive histogram equali

关 键 词：深度学习 Mask R-CNN 弱边缘性 图像增强 海洋锋检测 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]