【作者】 王睿； 国智； 王凤宇；

【Author】 Wang Rui, Guo Zhi, Wang Fengyu(The institute of instrumentation science and Opto-electronics engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China)

【机构】 北京航空航天大学仪器科学与光电工程学院；

【摘要】 针对复杂场景下红外图像序列中运动目标的检测问题,提出了一种基于动态参数的运动目标检测算法。首先构建由帧运动参数和动态矩阵组成的动态参数,帧运动参数值由红外序列的图像帧信息计算而得,而动态矩阵中的各元素值是图像帧中每一像素点运动状态的反映,根据帧运动参数和动态矩阵的变化建立背景图像,然后将当前帧图像和背景图像差分,并通过自适应形态学阈值获得二值化图像,从而实现运动目标的检测。实验结果表明,本文提出的方法可以在复杂背景下有效地检测出红外运动目标,且算法具有较高的实时性。更多还原

【Abstract】 A novel method for moving targets detection in infrared Image based on dynamic parameter was presented. Firstly, the dynamic parameter comprising the frame level moving character value and the dynamic matrix was built. Rather than only relying upon the motion state of each pixel stored in the matrix, frame level fast update method was adopted. Background model was established after analyzing properties of object motion in image pixels and temporal frames. Then,the background subtraction and adaptive threshold were proposed to identify the real moving targets. Experimental results not only show that this method is practical and easy to perform, but also confirm that the algorithm has dominance in the effect of the processing time.更多还原