| 引用本文: | 张军,谭志国,鲁敏,等.基于粒子群优化的点云场景拼接算法.[J].国防科技大学学报,2013,35(5):174-179.[点击复制] |
| ZHANG Jun,TAN Zhiguo,LU Min,et al.Particle swarm optimization based point cloud scene mosaic algorithm[J].Journal of National University of Defense Technology,2013,35(5):174-179[点击复制] |
|
| |
|
|
| 本文已被：浏览 7700次 下载 7012次 |
| 基于粒子群优化的点云场景拼接算法 |
| 张军1, 谭志国1,2, 鲁敏1, 黄毅1, 赵键1,3 |
|
(1.国防科技大学 电子科学与工程学院，湖南 长沙 410073;2.
2.77108部队，四川 崇州 611200;3.95380部队，广东 湛江 524329)
|
| 摘要: |
| 多视点三维点点云场景拼接是解决激光三维主动成像目标自遮挡或被遮挡情况下目标数据不完全问题的一种有效方法，它将直接影响到后续的目标检测与识别处理。提出了一种基于粒子群优化（PSO）的点云拼接算法，该方法通过计算点云的投影分布熵，构建并估计场景的独立坐标系，由此计算得到两者之间的空间变换关系，获取场景拼接初值。在此基础上，构建场景拼接目标函数，利用PSO方法，对目标函数进行优化，优化过程中利用最小概率误判法计算点云之间的匹配关系，最终获取拼接点云之间最优的空间变换关系，实现多视点场景的精确拼接。仿真实验结果表明，本文方法是一种有效可行的方法 |
| 关键词: 激光光学 点云场景拼接 粒子群优化算法 投影分布熵 |
| DOI： |
| 投稿日期：2013-03-28 |
| 基金项目:博士后科学基金资助项目（20100481511）；国家部委资助项目 |
|
| Particle swarm optimization based point cloud scene mosaic algorithm |
| ZHANG Jun1, TAN Zhiguo1,2, LU Min1, HUANG Yi1, ZHAO Jian1,3 |
|
(1.College of Electronic Science and Engineering, National University of Defense Technology, Changsha 410073, China;2.
2.Unit 77108, Chongzhou 611200,China;3.Unit 95380, Zhanjiang 524329,China)
|
| Abstract: |
| Multi-view point cloud scenes mosaic is an effective method to solve the incomplete object data problem while self-occlusion and occlusion happened in laser 3D imaging process. The mosaic method directly affects the object detection and recognition. In this research, a particle swarm optimization(PSO)based mosaic algorithm is proposed. The projective distribution entropy to construct the scene's coordinate was used, and the transformation between point cloud scenes by the coordinates was estimated. Based on this, the objective function for the mosaic was constructed, and the PSO for optimization was used. In the optimization process, the minimum miscarriage of justice method was used for searching the correspondence. In this way, the optimal transformation was found, and the fine mosaic was realized. Experimental results demonstrate the effectiveness and feasibility of the proposed algorithm. |
| Keywords: laser optics point cloud scenes mosaic particle swarm optimization projective distribution entropy |
|
|
|
|
|
