一种改进的高斯混合模型煤矸石视频检测方法

来源期刊:中南大学学报(自然科学版)2018年第1期

论文作者:郭一楠 程健 王东伟 杨凌凯 张美玲

文章页码:118 - 124

关键词:皮带运输机;高斯混合模型;粒子群优化算法;煤矸石检测

Key words:conveyer belt; Gaussian mixture model; particle swarm optimization; coal gangue detection

摘    要:基于皮带运输机的监控视频,实现煤流中矸石的检测。由于皮带运输机视觉场景复杂、视频图像质量差,所以,采用改进的高斯混合模型提取视频背景,实现视频背景分离,从而实现煤矸石的检测和识别。为提高算法性能,采用粒子群优化算法对高斯混合模型参数进行优化与自整定。研究结果表明:所提算法对矸石的检测准确率达到95.83%,能够对皮带运输机上的煤矸石实现有效检测,为提高煤炭质量、保证皮带运输机安全运行提供有效保障。

Abstract: A new approach was put forward to realize the detection of coal gangue via the monitoring video of conveyer belt. Considering the complex scene and the poor video quality of the conveyer belt, coal gangue was detected and recognized by an improved Gaussian mixture model (GMM) which extracts and subtracts the background of the video. In order to improve the algorithm performance, the particle swarm optimization was employed to find the better parameters of GMM. The results show that the average discrimination ratio is 95.38%. The proposed method can effectively detect coal gangue in the coal flow on the conveyer belt, which is good for improving the quality of coal and the safe operation of conveyer belt.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号