针对传统实时人群密度估计方法存在误差大、分类效果不佳等缺陷,提出了基于卷积神经网络的实时人群密度估计方法。通过对比4种常见网络结构:Alex Net、VGGNet、Goog Le Net和Res Net的准确度与实时性,选择综合性较好的Goog Le Net作为...针对传统实时人群密度估计方法存在误差大、分类效果不佳等缺陷,提出了基于卷积神经网络的实时人群密度估计方法。通过对比4种常见网络结构:Alex Net、VGGNet、Goog Le Net和Res Net的准确度与实时性,选择综合性较好的Goog Le Net作为人群密度估计的模型,利用关键帧截取技术实现人群密度的实时估计并简要分析人群密度特征图。最后用实例验证了该方法的实时性与准确度,证明了其可行性。展开更多
考虑目前对具有透视畸变的高密度人群图像进行特征提取的局限性,提出了一种融合全局特征感知网络(GFPNet)和局部关联性特征感知网络(LAFPNet)的人群计数模型LMCNN。GFPNet是LMCNN的主干网络,将其输出的特征图进一步序列化并作为LAFPNet...考虑目前对具有透视畸变的高密度人群图像进行特征提取的局限性,提出了一种融合全局特征感知网络(GFPNet)和局部关联性特征感知网络(LAFPNet)的人群计数模型LMCNN。GFPNet是LMCNN的主干网络,将其输出的特征图进一步序列化并作为LAFPNet的输入,再利用循环神经网络(RNN)在时序维度上对局部关联性特征感知的特点将单一的空间静态特征映射到具有局部序列关联性特征的特征空间,从而有效地削减了透视畸变对人群密度估计造成的影响。为了验证所提模型的有效性,在Shanghaitech Part A子集和UCF_CC_50数据集上与原子卷积空间金字塔网络(ACSPNet)进行对比,结果表明所提模型的平均绝对误差(MAE)分别至少减小了18.7%和20.30%,均方误差(MSE)分别至少减小了22.3%和22.6%。LMCNN注重空间维度上前后特征的相关性,通过对空间维度特征与单图像内序列特征的充分融合,减小了由透视畸变引起的人群计数误差,能更加准确地预测密集区域人数,提高人群密度回归精度。展开更多
Crowd counting has been applied to a variety of applications such as video surveillance,traffic monitoring,assembly control,and other public safety applications.Context information,such as perspective distortion and b...Crowd counting has been applied to a variety of applications such as video surveillance,traffic monitoring,assembly control,and other public safety applications.Context information,such as perspective distortion and background interference,is a crucial factor in achieving high performance for crowd counting.While traditional methods focus merely on solving one specific factor,we aggregate sufficient context information into the crowd counting network to tackle these problems simultaneously in this study.We build a fully convolutional network with two tasks,i.e.,main density map estimation and auxiliary semantic segmentation.The main task is to extract the multi-scale and spatial context information to learn the density map.The auxiliary semantic segmentation task gives a comprehensive view of the background and foreground information,and the extracted information is finally incorporated into the main task by late fusion.We demonstrate that our network has better accuracy of estimation and higher robustness on three challenging datasets compared with state-of-the-art methods.展开更多
文摘针对传统实时人群密度估计方法存在误差大、分类效果不佳等缺陷,提出了基于卷积神经网络的实时人群密度估计方法。通过对比4种常见网络结构:Alex Net、VGGNet、Goog Le Net和Res Net的准确度与实时性,选择综合性较好的Goog Le Net作为人群密度估计的模型,利用关键帧截取技术实现人群密度的实时估计并简要分析人群密度特征图。最后用实例验证了该方法的实时性与准确度,证明了其可行性。
文摘考虑目前对具有透视畸变的高密度人群图像进行特征提取的局限性,提出了一种融合全局特征感知网络(GFPNet)和局部关联性特征感知网络(LAFPNet)的人群计数模型LMCNN。GFPNet是LMCNN的主干网络,将其输出的特征图进一步序列化并作为LAFPNet的输入,再利用循环神经网络(RNN)在时序维度上对局部关联性特征感知的特点将单一的空间静态特征映射到具有局部序列关联性特征的特征空间,从而有效地削减了透视畸变对人群密度估计造成的影响。为了验证所提模型的有效性,在Shanghaitech Part A子集和UCF_CC_50数据集上与原子卷积空间金字塔网络(ACSPNet)进行对比,结果表明所提模型的平均绝对误差(MAE)分别至少减小了18.7%和20.30%,均方误差(MSE)分别至少减小了22.3%和22.6%。LMCNN注重空间维度上前后特征的相关性,通过对空间维度特征与单图像内序列特征的充分融合,减小了由透视畸变引起的人群计数误差,能更加准确地预测密集区域人数,提高人群密度回归精度。
基金the National Natural Science Foundation of China(Nos.61702186,61672236,and 61602459)。
文摘Crowd counting has been applied to a variety of applications such as video surveillance,traffic monitoring,assembly control,and other public safety applications.Context information,such as perspective distortion and background interference,is a crucial factor in achieving high performance for crowd counting.While traditional methods focus merely on solving one specific factor,we aggregate sufficient context information into the crowd counting network to tackle these problems simultaneously in this study.We build a fully convolutional network with two tasks,i.e.,main density map estimation and auxiliary semantic segmentation.The main task is to extract the multi-scale and spatial context information to learn the density map.The auxiliary semantic segmentation task gives a comprehensive view of the background and foreground information,and the extracted information is finally incorporated into the main task by late fusion.We demonstrate that our network has better accuracy of estimation and higher robustness on three challenging datasets compared with state-of-the-art methods.
