Small targets detection algorithm based on triangle match space
-
摘要: 由于天基平台拍摄天空图片时,背景和相机同时发生相对运动,造成相邻帧之间无法通过简单的帧差法得到运动的小目标,造成了空间目标检测的难度。在分析星空图像模型的基础上,提出了一种提取特征点组成匹配三角形的图像配准方法。首先对图像进行预处理,通过最优阈值的选取对单帧图像进行分割,去除背景噪声。将星点按面积大小划分,对符合条件的星点组成特征三角形并在相邻帧中进行匹配得到运动参数。在配准时为了减小计算量,忽略背景插值只针对星点坐标矩阵进行处理。最后通过多帧轨迹关联检测出目标的运动轨迹。仿真实验表明,在运动的序列图像中,该方法能实现高检测率和低虚警率的实时检测。Abstract: While the star images were pictured by space-based platform, there was a simultaneous relative motion between the background and the camera. The moving small object cannot be obtained through simple frame difference between adjacent frames. Thus, it was difficult to had the space object inspection. Based on the analysis of star image model, proposes an image registration method via extracting feature points and then matching the triangle. Firstly, it was the pretreatment of the images, which was to had a single-frame image segmentation from the selection of optimal thresholds, in order to remove the background noise. Then, divide the stars according to area sizes. For those eligible stars, make the feature triangles, and acquire the parameters from the matching in the adjacent frames. In order to minimize the calculation, the ignorance of the background interpolation was only applied to star coordinate matrices. Finally, detect the moving trace of the object according to multiple-frame connection. As the simulation experiments indicate, in the sequence images, the method can real time inspection in a high detection rate and a low false alarm rate.
-
Key words:
- target detection /
- optimal threshold /
- image registration /
- track association /
- space target
-
[1] Wang Zhaokui, Zhang Yulin. Algorithm for CCD star imagerapid locating [J]. Chinese Journal of Space Science, 2006,26(3): 209-214. (in Chinese)王兆魁, 张育林. 一种CCD 星图星点快速定位算法[J]. 空间科学学报, 2006, 26(3): 209-214. [2] [3] Zhang T X, Meng L, Zuo Z R. Moving dim point targetdetection with three-dimensional wide-to-exact searchdirectional filtering [J]. Pattern Recognition Letters, 2007,28(2): 246-253. [4] [5] [6] Davey S J, Rutten M G, Cheung B. A comparision ofdetection performance for several Track-before-detectalgorithms [C]//11th International Conference on InformationFusion,2008: 1-8. [7] Wang Xuewei, Wang Chunxin, Zhang Yuye. Detection ofsmall space target by dynamic programming [J]. Optics andPrecision Engineering, 2010, 18(2): 477-484. (in Chinese)王学伟, 王春歆, 张玉叶, 等. 空间小目标动态规划检测[J]. 光学精密工程, 2010, 18(2): 477-484. [8] [9] [10] Diani M, Corsini G, Baldacci A. Space-time processing forthe detection of airborne targets in IR image sequences [J].IEEE Proc Vision Image Signal Proc, 2001, 148(3): 151-157. [11] [12] Luo Huan, Wang Fang, Chen Zhongqi. Infrared targetdetecting based on symmetrical displaced frame difference and optical flow estimation[J]. Acta Optica Sinica, 2010, 30(6): 1715-1720. (in Chinese)罗寰, 王芳, 陈中起. 基于对称差分和光流估计的红外弱小目标检测[J]. 光学学报, 2010, 30(6): 1715-1720. [13] [14] Jiang Lei, Zhang Yanning, Sun Jinqiu. Trajectory detectionby non-uniform quantitative Hough transform in segmentedblocks[J]. Chinese Journal of Stereology and Mageanalysis,2009, 14(1): 60-66. (in Chinese)姜磊, 张艳宁, 孙瑾秋. 基于分块的非均匀Hough 变换轨迹检测方法[J]. 中国体视学与图像分析, 2009, 14(1):60-66. [15] Hao Zhicheng, Zhu Ming. Serial image registration based onmultiple restriction matching algorithm [J]. Acta OpticaSinica, 2010, 30(3): 702-708. (in Chinese)郝志成, 朱明. 基于多约束准则匹配算法的序列图像配准[J]. 光学学报, 2010, 30(3): 702-708. [16] [17] [18] Jae Hak Lee, Yong Sun Kim and atac. Robust CCD and IRimage registration using gradient-based statistical information[J]. IEEE Signal Processing Letters, 2010, 17(4): 347-350. [19] [20] Zhu Minghan, Luo Dayong. Moving objects detection andtracking based on two consecutive frames subtractionbackground model [J]. Computer Measurement Control,2006, 14(8): 1004-1007. (in Chinese)朱明旱, 罗大庸. 基于帧间差分背景模型的运动物体检测与跟踪[J]. 计算机测量与控制, 2006, 14(8): 1004-1007. [21] Chu P L. Efficient Detection of small moving objects [R].US: Lincoln Laboratory Technology Report ADA213314,1989, 6: 1-77.
计量
- 文章访问数: 361
- HTML全文浏览量: 46
- PDF下载量: 313
- 被引次数: 0