宣扬,吕宏强,安慰,刘学军.基于改进的无锚框目标检测算法的涡检测[J].数据采集与处理,2023,(1):150-161 |
基于改进的无锚框目标检测算法的涡检测 |
Vortex Detection Based on Improved Anchor-Free Object Detection Algorithm |
投稿时间:2022-01-04 修订日期:2022-02-24 |
DOI:10.16337/j.1004-9037.2023.01.013 |
中文关键词: 涡检测 细长目标检测 无锚框目标检测算法 特征自适应 细长样本挖掘 |
英文关键词:vortex detection slender object detection anchor-free object detection feature adaptation slender sample mining |
基金项目:航空科学基金(2018ZA52002,2019ZA052011);空气动力学国家重点实验室基金(SKLA20180102);气动噪声控制重点实验室基金(ANCL20190103)。 |
|
摘要点击次数: 32 |
全文下载次数: 32 |
中文摘要: |
在流体运动中涡对各种流场结构的生成和维持起着至关重要的作用,涡的识别和检测有助于理解流体流动规律。传统涡识别方法别存在定义不准确、严重依赖经验阈值、泛化性能差等问题,因此涡检测具有一定挑战性。本文从计算机视觉的角度出发,提出了一个基于目标检测算法的涡检测模型。针对原始目标检测模型对极端宽高比的细长涡检测效果不理想的问题,对两种不同类型涡的数据特性进行分析,并提出了基于可变形卷积(Deformable convolutional network, DCN)的特征自适应模块和基于改进损失函数的细长样本挖掘方法。采用圆柱尾流涡和潜艇尾部涡数据集对所提模型进行验证,实验结果表明改进后的模型检测精确率显著提高,并在细长涡的检测精确率上有显著提升,有效地平衡了各类型的涡检测性能。 |
英文摘要: |
Vortex plays a crucial role in the formation and maintenance of various flow structures in fluid motion. The identification and detection of vortices are helpful to understand the flow laws. Traditional vortex detection methods have many shortcomings, such as inaccurate definition, heavy dependence on empirical threshold and poor generalization performance, which make vortex detection challenging. In this paper, a vortex detection model based on object detection algorithm is proposed from the perspective of computer vision. Aiming at the problem that the original object detection model has unsatisfactory detection accuracy on slender vortices with extreme aspect ratio, this paper analyzes the data characteristics of two different types of vortices. A feature adaptive module based on deformable convolutional network (DCN) and a slender sample mining method based on improved loss function are proposed. The cylindrical wake vortex and submarine tail vortex data sets are used to verify the proposed model. Experimental results show that the improved model improves the detection accuracy significantly, and the detection accuracy of slender vortex is especially significantly improved, which effectively balances the performance of various types of vortex detection. |
查看全文 HTML 查看/发表评论 |