Dong Yakui, Fei Cheng, Zhao Guopeng, Wang Lili, Liu Yunxia, Liu Junliang, Fan Shuzhen, Li Yongfu, Zhao Xian
Key Laboratory of Laser & Infrared System, Ministry of Education, Shandong University, Qingdao, China.
Center for Optics Research and Engineering, Shandong University, Qingdao, China.
Heliyon. 2023 Mar 2;9(3):e14166. doi: 10.1016/j.heliyon.2023.e14166. eCollection 2023 Mar.
In this paper, a modified infrared and visible image registration method based on contour feature is proposed. Our method firstly extracts the feature contour and eliminates sparkling waves contour of the sea surface, determines the main direction of the contour based on the contour image, then uses the improved Scale Invariant Feature Transform (SIFT) method as the feature point to construct the descriptor, completes the registration of the two images. 30 sets of infrared and visible-band vessels images were selected for registration experiments. Compared with previous reports, the experimental results showed that the proportion of effective feature points detected by this method can reach 70%, and the average number of effective feature points detected by proposed method can reach 196 in visible band image and 279 in infrared image. The running time was 5.3599s, shortened by 25% compared with previous reports, and the average Root Mean Square Error (RMSE) value was 2.3566, smaller by 75% compared with previous reports. An effective registration method is provided, which can be used for infrared and visible image processing and comprehensive utilization of information in marine scenes.
本文提出了一种基于轮廓特征的改进型红外与可见光图像配准方法。该方法首先提取海面的特征轮廓并消除海面闪烁波浪轮廓，根据轮廓图像确定轮廓的主方向，然后采用改进的尺度不变特征变换（SIFT）方法作为特征点来构建描述符，完成两幅图像的配准。选取30组红外和可见光波段的船舶图像进行配准实验。与以往报道相比，实验结果表明，该方法检测到的有效特征点比例可达70%，在可见光波段图像中平均检测到的有效特征点数可达196个，在红外图像中可达279个。运行时间为5.3599秒，与以往报道相比缩短了25%，平均均方根误差（RMSE）值为2.3566，比以往报道小75%。提供了一种有效的配准方法，可用于红外与可见光图像处理以及海洋场景信息的综合利用。
