摘要
为了及早地发现监控区域的SF6毒气泄漏的问题,提出了基于ROI块累计思想的区域检测算法.针对SF6面临成像微弱,难以检测的特点,先对采集到红外视频图像序列进行运动帧间差提取ROI块,然后对本底图像做自适应算子去噪处理,提取背景,最后在一定的时间窗内,对提取的运动区域做块运动累计,增强目标区域位置.试验结果表明,该算法可以很好地检测出SF6气体泄露区域和位置.
To discover the SF6 gas leakage in the monitoring area, a detecting algorithm based on ROI block accumulation is proposed. However, gas imaging is too blurred to distinguish. So the motion area by interfmme difference algorithm in the infrared image sequence is extracted at first. Then,the raw image is de-noised by adaptive operator to extract the background. The extracted motion area blocks are accumulated in an appropriate time window. At last, the target area location is enhanced. The experiment shows the method proposed in the paper can detect the area and location where gas leaks.
出处
《南昌工程学院学报》
CAS
2012年第1期24-27,共4页
Journal of Nanchang Institute of Technology
基金
Supported by Youth Foundation of Nanchang Institute of Technology(No.2010KJ017)~~
