基于无锚框网络的航拍航道船舶检测算法  

Channel Ship Detection Algorithm for Aerial Image Based on Anchor-Free Network

作　　者：光睿智 安博文[1] 潘胜达[1] GUANG Ruizhi;AN Bowen;PAN Shengda(College of Information Engineering,Shanghai Maritime University,Shanghai 201306,China)

机构地区：[1]上海海事大学信息工程学院,上海201306

出　　处：《计算机工程与应用》2021年第15期251-258,共8页Computer Engineering and Applications

基　　金：国家自然科学基金(61302132,61504078,41701523)。

摘　　要：针对无人机航拍航道船舶影像中船舶目标较小、尺度变换大、背景复杂等问题,提出了一种基于FoveaBox网络的单阶段无锚框的航道船舶检测算法FoveaSDet。为提升小目标的检测精度,该算法使用基于残差网络改进的SEResNeXt-I作为骨干网。为改善尺度变换问题,FoveaSDet采用Foveahead实现无锚框目标检测。同时为提高复杂背景下检测框的定位精度,使用完全交并比损失实现边框回归。经实验测试,FoveaSDet算法在实景航拍数据集上的平均准确率(AP)和小目标准确率(APS)分别为71.6%和47.0%,相较于原始的FoveaBox提高了4.9%和6.2%,体现了更好的总体检测精度和小目标检测能力。In this paper,a one-stage anchor-free channel ship detection algorithm called FoveaSDet is proposed to address the problem of the small size ship,large scale transformation,and complex background in the image of drone aerial.FoveaSDet uses a backbone called SEResNeXt-I,which improves from ResNeXt,to increase the detection accuracy of small objects.Next,to solve the large scale transformation problem,the proposed method uses Foveahead to achieve anchor-free box object detection.The complete IOU loss has used to accomplish the bounding box regression so that the positioning accuracy of the detection box under a complex background can be raised.The experiment results show that the average precision and small objects’average precision of the FoveaSDet is 71.6%and 47.0%testing on the real aerial image dataset.It has increased by 4.9%and 6.2%compared with FoveaBox,reflecting better detection accuracy and small object detection ability.

关 键 词：深度学习 目标检测 特征提取 无锚框 损失函数 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]