摘要
基于提升算法的小波变换具有算法简单、运算速度快、占用存储空间小的特点[1,2]。针对火灾图像实时性强、火焰边缘含有大量火灾特征信息等特点,结合图像处理技术和小波分析理论,提出基于提升小波变换的火灾图像识别方法。运用小波提升算法提取视频帧图像的边缘,通过火焰面积判据和火焰尖角判据识别是否有火灾发生,实验证明基于提升小波变换的火灾图像识别方法准确性高,实时性强。
Wavelet transform based on lifting scheme has some characters, such as the simple algorithm, the fast speed and the small storage space. The paper presents the method of distinguish of fire image based on lifting wavelet transform, aiming at the realtime character of fire image and many fire characters in fire edge, combined image processing technology with wavelet analysis theory. In the paper, firstly, the edge of frame image is picked up by the algorithm, and then the fireis distinguished by the flame area criterion and flame angle criterion. The experiments demonstrate that this method has good veracity and strong real time.
出处
《计算技术与自动化》
2008年第2期81-84,共4页
Computing Technology and Automation
基金
陕西省教育厅专项基金资助项目(07JK295)
关键词
火灾图像
边缘检测
提升小波
火灾识别
fire image
edge detection
lifting wavelet
fire distinguish
