消防水炮射流轨迹图像的分割与识别算法研究  

Image Segmentation and Recognition Algorithm for the Fire Cannon's Jet Trajectory

作　　者：陈静[1] 赵敏[1] 

机构地区：[1]南京航空航天大学自动化学院,江苏南京210016

出　　处：《电子科技》2010年第3期43-45,49,共4页Electronic Science and Technology

摘　　要：提出了一种基于改进OSTU法和区域生长相结合的消防水炮射流轨迹图像的分割与识别算法。首先对OSTU法进行改进,快速确定射流轨迹差分图像的最佳分割阈值,再用区域生长法分割得到可能的目标区域。对消防水炮喷射水流的形态特征进行了研究和分析,并以此为判据对可疑目标区域进行判断,最后识别出真正的射流轨迹。实验结果表明:该算法在不同光照条件、背景情况下,基本可以摒除干扰物,准确识别目标,且处理速度较快。A segmentation and recognition algorithm based on the improved OSTU method and region growing is proposed for the fire cannon＇s jet trajectory image. First, the method of OSTU is improved to obtain the optimal segmentation threshold of jet trajectory＇s difference image quickly. Then, the possible target areas are segmented by the region growing method. On the basis of in-depth research on and analysis of jet trajectory＇s shape features, the real jet trajectory is identified from the possible target areas. The experimental results show that in the case of different lighting conditions and complex backgrounds, the method presented in this paper can eliminate the interference and identify the target accurately with a high processing speed.

关 键 词：图像分割 OSTU算法 最佳分割阈值 区域生长 射流轨迹识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]