%0 Journal Article
%T 深度学习和APAP模型结合的大视差图像拼接算法<br>Large Parallax Image Mosaic Algorithm Based on Deep Learning and APAP Model
%A 熊禹
%A 尹希庆
%A 吴志运
%J Journal of Image and Signal Processing
%P 104-115
%@ 2325-6745
%D 2023
%I Hans Publishing
%R 10.12677/JISP.2023.122011
%X 图像间位置偏差较大时，图像拼接容易出现错位、重影问题。提出一种深度学习和APAP模型结合的大视差图像拼接算法，该算法使用基于学习的SuperPoint网络同时提取图像特征点和描述符，采用SuperGlue网络对特征点进行筛选和最优匹配，最后通过APAP模型求取局部投影变换完成拼接。实际结果显示，在Mikolajczyk数据集上，基于学习的SuperPoint和SuperGlue网络在特征点提取和匹配方面相比传统算法重复率提升20%左右，准确率达到99%，鲁棒性更强，准确率更高。最终拼接图相比传统算法图像质量评价指标NIQE降低6.5%左右，基本消除错位、重影问题，更符合视觉效果。<br />
When the position deviation between images is large, image Mosaic is easy to appear dislocation and double image problems. A large parallax image stitching algorithm combining deep learning and APAP model is proposed. The algorithm uses learn-based SuperPoint network to simultaneously extract image feature points and descriptors, and uses SuperGlue network to screen and optimize the feature points. Finally, APAP model is used to obtain local projection transform to complete the stitching. The actual results show that on the Mikolajczyk dataset, the repetition rate of the SuperPoint and SuperGlue networks based on learning is improved by about 20% compared with the traditional algorithm in feature point extraction and matching, and the accuracy rate is up to 99%, with stronger robustness and higher accuracy. Compared with the image quality evaluation index NIQE of the traditional algorithm, the final Mosaic image is about 6.5% lower, basically eliminating the dislocation and double image problems, and is more in line with the visual effect.
%K 图像拼接，深度学习，APAP模型，SuperPoint网络，SuperGlue网络<br>Image Mosaic
%K Deep Learning
%K APAP Model
%K SuperPoint Network
%K SuperGlue Network
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=64187