水下目标检测与跟踪:GVF Snake和Mean Shift
首发时间:2014-01-22
摘要:针对水下光学图像清晰度低和物体颜色失真造成水下目标检测困难的问题,本文提出了一种基于Mean Shift和GVF Snake混合模型的水下目标检测与跟踪方法。对水下图像进行预处理后,运用GVF Snake算法对图像进行分割,提取目标轮廓,然后利用Mean Shift跟踪算法对目标进行实时跟踪。实验结果表明,本文采用的方法能对感兴趣的水下目标进行准确的检测与跟踪。
关键词: 目标检测 目标跟踪 GVF Snake Mean Shift
For information in English, please click here
Underwater target detection and tracking: GVF Snake and Mean Shift
Abstract:In view of the low underwater optical image resolution and the color distortion in underwater target detection, a method of underwater target detection and tracking based on Mean Shift and GVF Snake hybrid model is proposed in this paper. After preprocessing for the underwater image, we segment the image with the GVF Snake algorithm, and extract the object contour, then employ the Mean Shift tracking algorithm for real-time target tracking. Experimental results show that the method can effectively detect the object areas of interest and track accurately.in the underwater image.
Keywords: object detection object tracking GVF-Snake Mean Shift
基金:
论文图表:
引用
No.4581041949290138****
同行评议
共计0人参与
勘误表
水下目标检测与跟踪:GVF Snake和Mean Shift
评论
全部评论0/1000