论文部分内容阅读
序列图像中运动点目标的检测按图像的成像系统不同,可分为红外图像中运动点目标的检测和可见光图像中运动点目标的检测,而现有检测算法多是针对前者。为寻找一种适用于两种类型图像的运动点目标的检测方法,以多云天空为研究背景,提出了一种新的运动点目标检测算法。采用高通滤波和形态学滤波相结合的方法进行背景抑制,基于检测前跟踪(TBD)的基本思想,根据相邻三帧进行目标分割,利用轨迹能量累积方法完成目标检测。理论分析和仿真结果表明,该算法简单易行,既适用于红外图像又适用于可见光图像的运动点目标,而且对目标的运动速度和方向无任何限制。
The detection of moving-point targets in sequence images can be divided into the detection of moving-point targets in infrared images and the detection of moving-point targets in visible-light images according to the image imaging system. However, the existing detection algorithms mostly focus on the former. In order to find a detection method for moving-point targets which is suitable for both types of images, a new moving-point detection algorithm is proposed based on cloudy sky. Based on the basic idea of pre-test tracking (TBD), the target segmentation is carried out on the basis of three adjacent frames, and the trajectory energy accumulation method is used to accomplish the target detection. The theoretical analysis and simulation results show that the proposed algorithm is simple and feasible, which is not only suitable for moving images of infrared images but also for visible images, and has no limitation on the moving speed and direction of the target.