针对单幅图像中的行人检测问题,提出了基于自适应增强算法(Adaboost)和支持向量机(Support vector machine,SVM)的两级检测方法,应用粗细结合的思想有效提高检测的精度.粗级行人检测器通过提取四方向特征(Four direction features,FDF)...针对单幅图像中的行人检测问题,提出了基于自适应增强算法(Adaboost)和支持向量机(Support vector machine,SVM)的两级检测方法,应用粗细结合的思想有效提高检测的精度.粗级行人检测器通过提取四方向特征(Four direction features,FDF)和GAB(Gentle Adaboost)级联训练得到,精密级行人检测器用熵梯度直方图(Entropy-histograms of oriented gradients,EHOG)作为特征,通过支持向量机学习得到.本文提出的EHOG特征考虑到熵,通过分布的混乱程度描述,具有分辨行人和类似人的物体能力.实验结果表明,本文提出的EHOG、粗细结合的两级检测方法能准确地检测出复杂背景下不同姿势的直立行人,检测精度优于以往Adaboost方法.展开更多
针对视频中的行人检测问题,提出了LW-PGD(locating windows based on the pixel gradient direction of the top of head)快速定位头肩部和基于融合特征检测的方法。首先利用头顶像素点的梯度方向具有固定范围这一特性在前景中找出头顶...针对视频中的行人检测问题,提出了LW-PGD(locating windows based on the pixel gradient direction of the top of head)快速定位头肩部和基于融合特征检测的方法。首先利用头顶像素点的梯度方向具有固定范围这一特性在前景中找出头顶候选点,根据该点快速确定人体头肩部区域,将其作为待测窗口;然后提取待测窗口的方向梯度直方图(histogram of oriented gradient,HOG)特征和HSV(hue saturation value)颜色特征;最后采用支持向量机(support vector machine,SVM)训练得到人体头肩部的分类器。实验表明,与传统的滑动窗口搜索方法相比,根据头顶点可以快速选取含有人体头肩部的待测窗口,提高了检测的效率;HOG和HSV多特征融合提高了检测的精确性,从而提出的算法有助于后续的行人分析。展开更多
Since the outbreak of Coronavirus Disease 2019(COVID-19),people are recommended to wear facial masks to limit the spread of the virus.Under the circumstances,traditional face recognition technologies cannot achieve sa...Since the outbreak of Coronavirus Disease 2019(COVID-19),people are recommended to wear facial masks to limit the spread of the virus.Under the circumstances,traditional face recognition technologies cannot achieve satisfactory results.In this paper,we propose a face recognition algorithm that combines the traditional features and deep features of masked faces.For traditional features,we extract Local Binary Pattern(LBP),Scale-Invariant Feature Transform(SIFT)and Histogram of Oriented Gradient(HOG)features from the periocular region,and use the Support Vector Machines(SVM)classifier to perform personal identification.We also propose an improved Convolutional Neural Network(CNN)model Angular Visual Geometry Group Network(A-VGG)to learn deep features.Then we use the decision-level fusion to combine the four features.Comprehensive experiments were carried out on databases of real masked faces and simulated masked faces,including frontal and side faces taken at different angles.Images with motion blur were also tested to evaluate the robustness of the algorithm.Besides,the experiment of matching a masked face with the corresponding full face is accomplished.The experimental results show that the proposed algorithm has state-of-the-art performance in masked face recognition,and the periocular region has rich biological features and high discrimination.展开更多
文摘针对单幅图像中的行人检测问题,提出了基于自适应增强算法(Adaboost)和支持向量机(Support vector machine,SVM)的两级检测方法,应用粗细结合的思想有效提高检测的精度.粗级行人检测器通过提取四方向特征(Four direction features,FDF)和GAB(Gentle Adaboost)级联训练得到,精密级行人检测器用熵梯度直方图(Entropy-histograms of oriented gradients,EHOG)作为特征,通过支持向量机学习得到.本文提出的EHOG特征考虑到熵,通过分布的混乱程度描述,具有分辨行人和类似人的物体能力.实验结果表明,本文提出的EHOG、粗细结合的两级检测方法能准确地检测出复杂背景下不同姿势的直立行人,检测精度优于以往Adaboost方法.
文摘针对视频中的行人检测问题,提出了LW-PGD(locating windows based on the pixel gradient direction of the top of head)快速定位头肩部和基于融合特征检测的方法。首先利用头顶像素点的梯度方向具有固定范围这一特性在前景中找出头顶候选点,根据该点快速确定人体头肩部区域,将其作为待测窗口;然后提取待测窗口的方向梯度直方图(histogram of oriented gradient,HOG)特征和HSV(hue saturation value)颜色特征;最后采用支持向量机(support vector machine,SVM)训练得到人体头肩部的分类器。实验表明,与传统的滑动窗口搜索方法相比,根据头顶点可以快速选取含有人体头肩部的待测窗口,提高了检测的效率;HOG和HSV多特征融合提高了检测的精确性,从而提出的算法有助于后续的行人分析。
基金Supported by the Postgraduate Research and Practice Innovation Program of Nanjing University of Aeronautics and Astronautics(XCXJH20220318)。
文摘Since the outbreak of Coronavirus Disease 2019(COVID-19),people are recommended to wear facial masks to limit the spread of the virus.Under the circumstances,traditional face recognition technologies cannot achieve satisfactory results.In this paper,we propose a face recognition algorithm that combines the traditional features and deep features of masked faces.For traditional features,we extract Local Binary Pattern(LBP),Scale-Invariant Feature Transform(SIFT)and Histogram of Oriented Gradient(HOG)features from the periocular region,and use the Support Vector Machines(SVM)classifier to perform personal identification.We also propose an improved Convolutional Neural Network(CNN)model Angular Visual Geometry Group Network(A-VGG)to learn deep features.Then we use the decision-level fusion to combine the four features.Comprehensive experiments were carried out on databases of real masked faces and simulated masked faces,including frontal and side faces taken at different angles.Images with motion blur were also tested to evaluate the robustness of the algorithm.Besides,the experiment of matching a masked face with the corresponding full face is accomplished.The experimental results show that the proposed algorithm has state-of-the-art performance in masked face recognition,and the periocular region has rich biological features and high discrimination.
