基于小波提升框架的图像序列中运动目标检测算法

图像序列中运动目标的检测和跟踪是智能监测系统中的重要问题，为了提高运动目标识别的效率和准确性，同时解决日标运动中的形变造成的检测困难，首先针对传统的运动日标检测算法所存在的局限．把小波提升框架运用到运动目标的检测中，然后充分利用小波的多分辨率特性和提升框架可以直接在时空域内设计的优点，再结合可变模板方法，提出了一种新的基于小波提升框架的运动目标检测算法。实验结果表明，新方法较好地解决了目标运动中因形变造成的检测困难，并提高了检测效率和速度。

A New Algorithm of Moving Target Detection in Image Sequence Based on the Lifting Scheme

In surveillance system, moving target detection in image sequence is a very significant and difficult problem. The objective of this research was to present a new detection method to enhance the efficiency and accuracy of moving target recognition,and to resolve the difficulties brought by target distortion. The detail theory and algorithm of a new detection method, which was based on the lifting scheme of wavelet and deformable template technique, were described. The multi-scale images were used to improve the target matching efficiency, and the deformable templates were used to tracking the target distortions. The results indicated that the moving objects detected by the new method based on the lifting scheme were more robust than those detected by traditional methods. In addition, the detection speed became more rapid. The results seem to suggest that the new method be with efficiency and accuracy advantages in computer version.