公共场所枪声特征提取及识别方法分析-仪器仪表工程专业论文.docx

重庆大学硕士学位 重庆大学硕士学位论文 英文摘要 PAGE PAGE VI ABSTRACT The security of public places for social stability and harmony, peoples lives and property is of great significance. Currently, video surveillance in public places with the core technology of video monitoring platform has played a positive role on reducing the crime rate and improving the efficiency of investigation and scientific evidence collection. Gunshot signal often contains very important information including the type of weapon, the size of the fire and so on. This information provides first-hand information including criminal fire intelligence and clues to solve crimes. Feature extractions of gunshot mostly follow the traditional methods of speech signal processing. Gunshot signal in public places is the typical non-speech signal with non-stationary and nonlinear. So, the study of gunshot signal provides a new train of thought for processing other types of non-speech signal. Therefore, Gunshot feature extraction and classification in public places is of significant practical value and academic significance. In this paper, First analysis gunshot signal of public and environmental background noise characteristics, then proposed an Ensemble Empirical Mode Decomposition (EEMD) model of the gunshot signal feature extraction and recognition method and final results are verified through the experiment. This paper main work is as follows: ① Feature analyze of the typical gunshot and background noise in public places. Several kinds of typical gunshot signal and he background noise characteristics analyzed such as time domain, frequency domain, frequency domain, cepstrum domain have been done. Though statistical analysis of relevant features, this paper argues that gunshot has common property of nonlinear, non stability and the different types of shots such as pistols, rifles, machine guns have more similarities than differences. Environment in public places such as square, station, wharf and other background noise is