Chunbin Qin^*, Xiaotian Ran

CMC-Computers, Materials & Continua, Vol.79, No.1, pp. 1319-1334, 2024, DOI:10.32604/cmc.2024.048850 - 25 April 2024

Abstract Traditional feature-based image stitching techniques often encounter obstacles when dealing with images lacking unique attributes or suffering from quality degradation. The scarcity of annotated datasets in real-life scenes severely undermines the reliability of supervised learning methods in image stitching. Furthermore, existing deep learning architectures designed for image stitching are often too bulky to be deployed on mobile and peripheral computing devices. To address these challenges, this study proposes a novel unsupervised image stitching method based on the YOLOv8 (You Only Look Once version 8) framework that introduces deep homography networks and attention mechanisms. The methodology… More >

Zhenzhou Wang¹, Jiashuo Li¹, Xiang Wang^1,*, Xuanhao Niu²

CMC-Computers, Materials & Continua, Vol.72, No.2, pp. 4157-4171, 2022, DOI:10.32604/cmc.2022.027017 - 29 March 2022

Abstract At present, underwater terrain images are all strip-shaped small fragment images preprocessed by the side-scan sonar imaging system. However, the processed underwater terrain images have inconspicuous and few feature points. In order to better realize the stitching of underwater terrain images and solve the problems of slow traditional image stitching speed, we proposed an improved algorithm for underwater terrain image stitching based on spatial gradient feature block. First, the spatial gradient fuzzy C-Means algorithm is used to divide the underwater terrain image into feature blocks with the fusion of spatial gradient information. The accelerated-KAZE (A-KAZE)… More >

Tao Zhang^1,*, Yi Cao²

Intelligent Automation & Soft Computing, Vol.33, No.3, pp. 1677-1685, 2022, DOI:10.32604/iasc.2022.027082 - 24 March 2022

Abstract The images generated by the image stitching algorithm have false shadow and poor real-time performance, and are difficult to maintain visual consistency. For this reason, a panoramic image stitching algorithm based on genetic algorithm is proposed. First, the oriented fast and rotated brief (ORB) algorithm is used to quickly perform detection and description of feature, then the initial feature point pairs are extracted according to the Euclidean distance for feature point rough matching, the parallelism of genetic algorithm is used to optimize the feature point matching performance. Finally, the PROSAC algorithm is used to remove More >