基于深度特征提取的深海序列图像拼接网络  

Deep feature extraction-based sequential image stitchingnetwork for deep-sea environments

作　　者：赵帅 张春堂[1] 樊春玲[1] Zhao Shuai;Zhang Chuntang;Fan Chunling(College of Automation and Electronic Engineering,Qingdao University of Science and Technology,Qingdao 266061,China)

机构地区：[1]青岛科技大学自动化与电子工程学院,青岛266061

出　　处：《电子测量技术》2025年第3期180-187,共8页Electronic Measurement Technology

摘　　要：利用图像拼接获得海底全景图对了解深海地形地貌具有重要意义。受限于深海环境,海底图像特征模糊,序列图像的连续拼接需要一种稳定、有效的拼接网络。针对上述问题,本研究提出一种结合改进ALIKED(ALIKED-P)和LightGlue的深海序列图像拼接网络AP-LG。首先,用可变形卷积v2替代ALIKED网络中可变形卷积,引入调节机制,增强网络的特征捕获能力;然后,通过特征金字塔网络实现多尺度特征融合,增强网络对环境变化的鲁棒性;最后,以LightGlue特征匹配网络为核心,基于单应性估计策略,实现多张序列图像的连续对齐拼接。实验结果表明,在UIEBD和DISD数据集上,AP-LG网络分别以32.91%和49.41%匹配率使得86.00%和93.60%的图像对匹配到100对以上的有效特征点,所提方法能够稳定提取深海图像特征,有效实现特征匹配,完成深海序列图像拼接。Obtaining a panoramic view of the seafloor through image stitching is of great significance for understanding deep-sea topography and geomorphology.Due to the challenges posed by the deep-sea environment,seafloor image features are often blurred,making the continuous stitching of sequential images require a stable and efficient stitching network.To address the issue,this paper proposes a deep-sea sequential image stitching network called AP-LG,which combines an improved ALIKED with LightGlue.Firstly,Deformable ConvNets v2 is used to replace the original deformable convolutional networks in ALIKED,introducing an adjustment mechanism to enhance the network′s feature capture capability.Then,multi-scale feature fusion is achieved through feature pyramid networks,improving robustness of the network to environmental changes.Finally,LightGlue is employed as the core feature matching network,and based on homography estimation strategies,continuous alignment and stitching of multiple sequential images are achieved.The experimental results indicate that on the UIEBD and DISD datasets,the AP-LG network achieved matching rates of 32.91%and 49.41%,respectively,enabling 86.00%and 93.60%of the image pairs to be matched with over 100 valid feature points.The proposed method can stably extract seafloor image features,achieve feature matching,and effectively complete the stitching of sequential seafloor images.

关 键 词：图像拼接 特征提取 特征匹配 ALIKED LightGlue 

分 类 号：TN98[电子电信—信息与通信工程]