检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:宋强 张颖[1] SONG Qiang;ZHANG Ying(School of Electronic and Information Engineering,University of Science and Technology Liaoning,Anshan 114051,China)
机构地区:[1]辽宁科技大学电子与信息工程学院,辽宁鞍山114051
出 处:《辽宁科技大学学报》2021年第5期371-378,共8页Journal of University of Science and Technology Liaoning
摘 要:针对视频监控中移动的人脸图像光照强度不同、遮挡、快速变化等问题,本文提出一种人脸识别视频压缩感知跟踪算法。利用图像尖锐化处理突出目标图像边缘纹理,再利用矩形滤波器对人脸图像归一化处理并获取特征向量。通过压缩感知算法对目标样本和背景样本的Haar-like特征压缩,建立目标模型,训练Adaboost算法的贝叶斯级联分类器。最后根据人脸特征区分目标和背景图像,实现目标人脸图像的动态跟踪。实验结果表明,该算法能够实现视频中人脸图像移动、遮挡及光照强度不均匀、快速变化等情况下的有效跟踪。In order to solve the problems of different illumination intensity,occlusion,and rapid change of moving face image in video surveillance,a video compressed sensing tracking algorithm for face recognition was proposed.In this algorithm,the edge texture of the target image was highlighted by image sharpening,and then a rectangular filter was used to normalize the face image and obtain the feature vectors.Then dynamic compressed sensing algorithm was used to compress the Haar-like features of the target and background samples.The compressed Haar-like feature vectors were used to build the target model,and the Bayesian cascade classifier in Adaboost algorithm was trained.Finally,the classifier was used to distinguish the target image and the background image based on facial features,and to realize the dynamic tracking of face images.Experimental results show that this method can effectively track the movement,occlusion,uneven illumination intensity,and rapid change of facial images in video.
关 键 词:人脸识别 动态压缩感知 目标跟踪 特征提取 分类识别
分 类 号:TP391[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.229