Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Naval Aeronautical and Astronautical University》 2018-02
Add to Favorite Get Latest Update

Mosaic Method of UAV Images Based on the Improved SURF

YAO Hongyuan;WANG Haipeng;JIAO Li;LIN Xueyuan;Naval Aviation University;Yantai Zhifu Teacher Training School;  
Due to the traditional SIFT algorithm, there are many problems such as slow operation, mis-matching and computational complexity in UAV remote sensing image splicing, which can not meet the real-time requirements of remote sensing image processing, and there are exposure differences between the collected images. In this case, the direct superposition and splicing may cause ghosting misalignment at the boundary. In this paper, an improved SURF algorithm and fusion algorithm for remote sensing image mosaic of drones were proposed. Firstly, in the feature detection phase, the SURF algorithm and the Harris corner detection algorithm were combined to obtain the feature points and feature descriptors of the image quickly. In the feature matching stage, it was divided into two steps, whinch were rough matching and fine matching. The rough matching of the feature points between the stitched images and the fine matching of the mismatched points were eliminated by using the RANSAC algorithm. In the image fusion stage, a weighted average algorithm based on distance was used for image fusion. The final experiment showed that the processing speed of the proposed algorithm was improved by nearly 5 times compared with the traditional SUFT algorithm. Compared with other improved algorithms, the matching accuracy was also improved, and this algorithm could effectively improve the quality of the image mosaic. The effect solved the problem that the splicing marks, ghosts, dislocations and other phenomena might occur.
【Fund】: 国家自然科学基金资助项目(61471383)
【CateGory Index】: TP751
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved