不变伪线矩算法在运动船只目标识别中的应用  

Application of invariant pseudo-line moment method on target recognition of moving vessels

作　　者：袁昕[1] 陈潇君[1] 陈祖爵[1] 

机构地区：[1]江苏大学计算机科学与通信工程学院,江苏镇江212013

出　　处：《江苏大学学报（自然科学版）》2010年第1期82-87,共6页Journal of Jiangsu University：Natural Science Edition

基　　金：国家自然科学基金资助项目(40674060)

摘　　要：为准确得到港口运动船只的特征、且在节约系统资源的同时快速高效地跟踪目标,结合传统不变矩和不变线矩的特点,提出了一种基于不变伪线矩的目标识别算法.进行计算复杂性分析,验证了算法的快速性;同时分析了不变伪线矩的稳定性.使用新算法得到图像中各目标的计算区域,并对计算区域进行边缘检测预处理,通过二值图像计算得到不变伪线矩.评估了新算法的不变伪线矩性能,并进行了仿真测试与分析.结果表明,该算法在准确得到运动目标所在区域特征的同时提高了运算速度,并成功应用于运动船只智能监测系统.In order to obtain precisely the features of moving vessels at the port and track the target quickly and efficiently while saving system resources, a target recognition algorithm based on invariant pseudo-line moment was proposed by combining the characteristics of traditional moment invariants and invariant line moment. The computational complexity was analyzed and the rapidity of the algorithm was verified. Meanwhile, the stability of invariant pseudo-line moments was also analyzed. The computational domain of each target for an image was obtained, and the pretreatment of edge detection was completed. Finally, the invariant pseudo-line moments were derived by calculating binary image. In addition, the performance of the invariant pseudo-line moments was evaluated, and simulation test and analysis were conducted. The results show that the algorithm can accurately obtain the features of the moving objects＇ regions while improving the computing speed, and the new method has been successfully applied in the intelligent monitoring system for moving vessels.

关 键 词：矩 线矩 不变伪线矩 智能视觉监测 运动目标检测 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]