浮动阈值算法在小目标图像提取中的应用

Application of Floating Threshold Algorithm in Small Target Image Extraction Process

针对相对复杂图像目标对象的提取问题,介绍了像素图像处理常用算法(背景差法、光流法、帧间差分法)的优点和缺点及适用范围。提出浮动阈值在小目标图像提取的方法及算法流程设计的详细组成。实验表明,这种方法能快速准确提取目标,还原模糊分类后的图像目标,并使背景部分替换成其他颜色,从而实现目标的提取。

Aiming at the problem of the extraction for the target object in the complex images, the advantages and disadvantages of the common algorithm （background subtraction, optical flow and frames differences） in the pixel image processing and the applicable range are introduced. The method of the floating threshold in the small target image extraction and the algorithm design process are proposed. The experiment shows that the object can be quickly extracted by using this method, the image object after fuzzy classification is restored and the background is replaced by other color. The object extraction can be realized.