卫星视频运动目标检测算法

发布时间：2018-05-20 09:46

本文选题：卫星视频 + 运动目标监测　；参考：《液晶与显示》2017年02期

【摘要】：为了实现对卫星视频图像序列的运动目标进行跟踪,提出了一种背景建模与添加实际条件约束相结合的卫星视频运动目标检测算法。首先,针对卫星视频图像序列的背景建立背景模型。然后,把接下来各帧图像同该模型相比较,进行减法运算,所得偏差为运动区域。最后添加满足卫星实际情况的约束条件,根据卫星视频的分辨率估算出运动目标合理的像元尺寸,从而滤掉噪声。将本算法在PC端进行实现,并与三帧差法和背景建模法的检测准确度进行对比。实验结果表明:本算法对卫星视频图像序列运动目标检测的准确度可达83.6%,三帧差法检测准确度为6.1%,背景建模法检测准确度为21.0%。从实验结果可以看出,本文算法可以比较准确地对卫星视频图像序列进行运动目标检测。
[Abstract]:In order to track the moving targets of satellite video sequences, a moving target detection algorithm based on background modeling and practical condition constraints is proposed. Firstly, the background model of satellite video sequence is established. Then, the next frame images are compared with the model, and the subtraction operation is carried out, and the deviation is the moving region. Finally, the reasonable pixel size of the moving object is estimated according to the resolution of the satellite video, and the noise is filtered by adding the constraint conditions that satisfy the actual situation of the satellite. The algorithm is implemented on PC and compared with three frame difference method and background modeling method. The experimental results show that the accuracy of the algorithm is 83.6for moving target detection of satellite video sequences, 6.1 for the three-frame difference method and 21.0 for the background modeling method. It can be seen from the experimental results that the proposed algorithm can detect the moving targets of satellite video sequences more accurately.
【作者单位】：中国科学院长春光学精密机械与物理研究所;中国科学院大学;长光卫星技术有限公司;
【基金】：国家重点研发计划项目(No.2016YFB0502602)~~
【分类号】：TP391.41

【相似文献】