基于SIFT与SVM的应急救援图像检测方法研究*

针对公共安全突发事件应急救援的封闭空间场景（Confined Space Scene，CSS）信息采集不通畅、不全面而影响救援等问题，提出1种基于不变特征转换（Scale invariant feature transform，SIFT）和支持向量机（Support Vector Machine，SVM）的图像信息异常检测方法。在场景内外信息传递“断环”情况下，该方法可利用物联网技术采集的图片，或以网络图片信息、历史类似场景数据等作为补充，通过SIFT特征提取、K means聚类处理以及SVM分类，实现场景的智能识别。经仿真分析，该方法能实现封闭空间内外部图像信息互通，“接补”因无法了解事件内部情况而产生的救援环节链条的“断环”，为救援提供决策参考。

Study on image detection method of emergency rescue based on SIFT and SVM

Aiming at the problem that the information collection is unsmooth and incomplete in the Closed Space Scene (CSS) of emergency rescue for the public security emergencies,which affect the rescue,a detection method of image information anomaly based on the scale invariant feature transform (SIFT) and support vector machine (SVM) was put forward.In the case of "ring breaking" of information transmission inside and outside the scene,the method could use the pictures collected by the Internet of things technology,or take the network picture information and historical similar scene data as the supplement,and realize the intelligent recognition of the scene by the SIFT feature extraction，K means clustering processing and SVM classification.The simulation results showed that the method could realize the image information exchange between the inside and outside of the closed space,and supplement the "ring breaking" in the rescue link chain caused by the failure to understand the internal situation of the event,so as to provide decision reference for the rescue.