Abstract: Due to the low illumination, low contrast and similar color between target and environment in a coal mine, problems of undetected objects and false detections appear. An improved miner target detection method was proposed, integrating Gaussian Mixture Model (GMM) with Local Binary Pattern (LBP). The color information of background was fitted by means of GMM, and the texture information was extracted by employing LBP, then the miners targets were detected by integrating the color and the texture information. The simulation results indicate that the proposed algorithm decreases the problems of undetected objects and false detections, and can detect miner target in real-time with high precision.

Key words: camouflage, Gaussian Mixture Model (GMM), Local Binary Pattern (LBP), color information, texture information

摘要： 针对矿井下某些地段低光照低对比度导致矿工目标与环境颜色相似，呈现伪装色特点，一般场景目标检测方法易产生矿工漏检、误检的问题，提出了采用高斯混合模型(GMM)和局部二值模式(LBP)纹理模型线性融合的方法对目标矿工进行检测。首先利用高斯混合模型拟合背景颜色信息，然后通过局部二值模式纹理模型提取图像纹理信息，最后将颜色信息和纹理信息线性融合对矿工进行检测。实验结果表明，在满足实时性的同时，减少了矿工目标出现漏检、误检的问题，该方法可对具有伪装色特征的矿工目标进行实时检测，准确性高。

关键词: 伪装色, 高斯混合模型, 局部二值模式, 颜色信息, 纹理信息