摘要
结合CNN的特点,提出了一种基于OTSU算法的细胞神经网络视频对象分割算法,通过仿真实验证明了此算法的可行性。本算法是对差分图像合并算法的一种改进,原理简单,易实现,处理速度快且精度高。
Combining with the features of CNN, this paper puts forward a kind of video object segmentation algorithm based on OTSU algorithm, and through simulation experiments to prove its feasibility. The algorithm is the improvement of subtraction merged image algorithm. The algorithm is simple and easy to implement, and it has high accuracy and fast speed.
出处
《现代工业经济和信息化》
2015年第21期83-85,共3页
Modern Industrial Economy and Informationization
关键词
细胞神经网络
视频对象分割
OTSU算法
阈值
cellular neural network
video object segmentation
OTSU algorithm
threshold