多尺度特征融合下的高帧频图像关键目标识别
Key Target Recognition in High Frame Rate Images Based on Multi-Scale Feature Fusion
林琳1
作者信息
- 1. 厦门海洋职业技术学院海洋机电学院,福建厦门 361100;厦门市智慧渔业重点实验室,福建厦门 361100
- 折叠
摘要
为优化高帧频图像目标识别效果,提出基于多尺度特征融合的高帧频图像关键目标识别方法.结合空域双边滤波算法和双树复小波变换算法去除高帧频图像噪声.通过多个卷积模块提取图像特征,并在分支空间注意力机制、改进通道注意力网络下融合多尺度特征.引入联合稀疏概念表征融合后的多尺度特征,并将其输入卷积神经网络结构中进一步学习,输出关键目标识别结果.实验结果表明,所提方法应用后AUC值为0.91,满足了高帧频图像处理要求.
Abstract
To optimize the target recognition performance of high frame rate images,a key target recognition method based on multi-scale feature fusion is proposed for high frame rate images.Combining spatial bilateral fil-tering algorithm and dual tree complex wavelet transform algorithm to remove noises from high frame rate images.Extract image features through multiple convolutional modules and fus multi-scale features under branch spatial attention mechanisms and improved channel attention networks.Introduce the concept of joint sparsity to repre-sent the fused multi-scale features,and input them into the convolutional neural network structure for further learning,outputting key target recognition results.The experimental results show that the AUC value of the pro-posed method after application is 0.91,which meets the requirements of high frame rate image processing.
关键词
帧频图像/特征融合/空间注意力/空域双边滤波/目标识别Key words
frame rate image/multi-scale feature fusion/spatial attention/bilateral filtering/target identi-fication引用本文复制引用
基金项目
福建省海洋与渔业局海洋经济发展专项(FJHJF-L-2021-12)
福建省教育厅智慧渔业应用技术协同创新中心项目(XTZX-ZHYY-1914)
出版年
2024
NETL
NSTL
万方数据