摘要
在倾斜摄影测量技术中,人工内业像控点识别的像片分辨率有限。为了更好地发挥倾斜摄影测量在国民基建测绘中的优势,提高作业效率,提出了基于HSV色彩空间的影像增强算法,结合深度学习技术对筛选出的图像进行高效率像控点几何中心标志识别,以提升内业像控点的识别效率和精度。实验结果表明,与传统的识别算法相比,本算法在准确率和定位精度上均有提高。
In oblique photogrammetry technology,the image resolution of artificial indoor image control point recognition is limited.In order to give full play to the advantages of oblique photogrammetry in national infrastructure surveying and mapping and improve the efficiency of operation,an image enhancement algorithm based on HSV color space is proposed.Combined with deep learning technology,the selected images are identified with high-efficiency geometric center marks of image control points to improve the recognition efficiency and accuracy of internal image control points.Experimental results show that compared with the traditional recognition algorithm,this algorithm has improved the accuracy and positioning accuracy.
作者
丁涛
刘春阳
DING Tao;LIU Chunyang(Anhui Nuclear Industry Exploration Technology General Institute,Wuhu Anhui 234001,China;School of Spatial Information and Surveying Engineering,Anhui University of Science and Technology,Huainan Anhui 232001,China)
出处
《重庆科技学院学报(自然科学版)》
CAS
2022年第6期71-76,共6页
Journal of Chongqing University of Science and Technology:Natural Sciences Edition
基金
安徽省自然科学基金面上项目“顾及用户动态偏好与时空关联模式的深度学习POI推荐方法”(2108085MD130)。