| 引用本文: | 刘进博,郭鹏宇,李鑫.基于梯度直方图的交叉点检测方法.[J].国防科技大学学报,2021,43(1):33-40.[点击复制] |
| LIU Jinbo,GUO Pengyu,LI Xin.Detection method for intersection points based on gradient-histogram[J].Journal of National University of Defense Technology,2021,43(1):33-40[点击复制] |
|
| |
|
|
| 本文已被：浏览 7182次 下载 5378次 |
| 基于梯度直方图的交叉点检测方法 |
| 刘进博1,郭鹏宇2,李鑫1 |
|
(1. 中国空气动力研究与发展中心 超高速空气动力研究所, 四川 绵阳 621000;2. 军事科学院 国防科技创新研究院, 北京 100071)
|
| 摘要: |
| 提出基于梯度直方图的交叉点检测方法:统计像素点邻域梯度信息生成特征描述子,通过判定准则筛选候选交叉点,基于欧氏距离对候选交叉点进行聚类后,利用灰度加权法定位图像交叉点坐标。仿真实验验证了算法的正确性与可行性,结果表明:该方法适用于交叉角为65°~90°范围内的交叉点检测,定位精度优于0.6像素,检测率大于90%；该方法可以很好地抵抗图像旋转,定位精度和检测率基本不受图像旋转影响。该方法具有良好的抗噪性能,可满足一般透视变换下的图像交叉点检测需求,适用于结构光三维重建中的系统标定和形貌测量。 |
| 关键词: 图像识别 交叉点 梯度直方图 特征描述子 旋转不变 三维重建 |
| DOI：10.11887/j.cn.202101005 |
| 投稿日期：2019-07-15 |
| 基金项目:国家自然科学基金资助项目(11802321) |
|
| Detection method for intersection points based on gradient-histogram |
| LIU Jinbo1, GUO Pengyu2, LI Xin1 |
|
(1. Hypervelocity Aerodynamics Institute, China Aerodynamics Research and Development Center, Mianyang 621000, China;2. National Innovation Institute of Defense Technology, Academy of Military Sciences, Beijing 100071, China)
|
| Abstract: |
| A detection method for intersection points based on gradient-histogram was proposed. The feature descriptor was generated for each image pixel using gradient of neighborhood pixels. The candidate intersection points were taken from all image pixels according to specific constraints. The candidate intersection points were clustered into different categories based on Euclidean distance. The subpixel positions were computed for each intersection points by the weighting method. The proposed method was validated by simulations. The results show that the method can be used to detect the intersection points of crossing angle 65°~90° with the precision of 0.6 pixel and the detection rate exceeds 90%, and the precision and detection rate of proposed method is invariant to image rotating. The method is robust to image noise and can satisfy the need of detecting intersection points on image under normal prospective transformation. It can be applied to the calibration and surface measurement of structure light 3D reconstruction system. |
| Keywords: image recognition intersection point gradient-histogram feature descriptor rotating-invariant 3D reconstruction |
|
|
|
|
|
