基于轻量化多尺度下采样网络的红外图像非均匀性校正算法

Infrared Image Non-uniformity Correction Algorithm Based on Lightweight Multiscale Downsampling Network

红外成像系统常由于探测单元的非均匀性导致成像结果出现条纹噪声。基于深度学习的红外图像非均匀校正算法为取得较好的校正结果,通常采用复杂度高的网络结构,导致计算量庞大。本文提出了一种轻量化网络的红外图像非均匀校正算法,并针对Unet网络的编码过程设计了一种轻量化多尺度下采样模块(Lightweight Multi-scale Downsampling Module,LMDM)。LMDM通过像素拆分和通道重构实现特征图下采样,利用多个串联的深度可分离卷积(Depth-wise Separable Convolution,DSC)实现多尺度特征提取。此外,该算法引入轻量化通道注意力机制用于调整特征权重,实现更好的上下文信息融合。实验结果表明,与对比算法相比,本文提出的算法在保证校正图像纹理清晰、细节丰富和边缘锐利的前提下,内存占用降低70%以上,红外图像处理速度提升24%以上。

Infrared imaging systems often produce fringe noise in imaging results owing to the non-uniformity of the detection unit.To obtain better correction results,most deep learning-based infrared image non-uniformity correction algorithms adopt complex network structures,which increase the computational cost.This study proposes a lightweight network-based infrared image non-uniformity correction algorithm and designs a lightweight multi-scale downsampling module(LMDM)for the encoding process of the Unet network.The LMDM uses pixel splitting and channel reconstruction to realize feature map downsampling and realizes multi-scale feature extraction using multiple cascaded depth-wise separable convolutions(DSC).In addition,the algorithm introduces a lightweight channel attention mechanism for adjusting feature weights to achieve better contextual information fusion.The experimental results show that the proposed algorithm reduces memory use by more than 70%and improves the processing speed of the infrared images by more than 24%compared with the comparison algorithm while ensuring that the corrected image has a clear texture,rich details,and sharp edges.