CAJ | 학술논문

针对某基地提出的基于机器视觉的火箭跟踪伺服系统对火箭目标分割提取的要求,提出了带有衰减因子的Prewitt边缘检测算子与改进的最大类间方差法相结合的图像分割方法.根据火箭的形态特征提出了一种带方向非线性滤波去噪法,对分割后所得到的图像做了进一步去噪处理,除去了与火箭形态无关的边缘.仿真实验表明,采用该方法对火箭目标正确分割率为96.5%,并能够实时有效地对火箭序列图像进行有效分割.
침대모기지제출적기우궤기시각적화전근종사복계통대화전목표분할제취적요구,제출료대유쇠감인자적Prewitt변연검측산자여개진적최대류간방차법상결합적도상분할방법.근거화전적형태특정제출료일충대방향비선성려파거조법,대분할후소득도적도상주료진일보거조처리,제거료여화전형태무관적변연.방진실험표명,채용해방법대화전목표정학분할솔위96.5%,병능구실시유효지대화전서렬도상진행유효분할.
To satisfy machine vision based rocket tracking servo system's requirements for rocket target segmentation, a segmentation method combined with Prewitt edge detection operator with decaying factor and improved Otsu algorithm was proposed. Based on the rocket's morphological characteristics, a nonlinear filter de-noising method was presented to denoise and remove the non-rocket edge. Simulation results show that the proposed method has 96.5% successful segmentation rate for rocket target, and can effectively segment rocket image sequence in real-time.