越线人群计数--Crossing-line Crowd Counting with Two-phase Deep Neural Networks

Crossing-line Crowd Counting with Two-phase Deep Neural Networks
ECCV2016

人群计数有两种做法：1） region-of-interest (ROI) 感兴趣区域计数，2） line-of-interest (LOI) 感兴趣线计数，就是通过图像中某一条线的人流量。

大多数算法关注 ROI 计数问题，但是我们认为 LOI 计数问题更有实际应用价值，对于人群密集的大型公共区域，我们想通过监控相机对所有区域进行人群计数是不现实的。但是我们可以对出口和入口进行 LOI 计数从而推理出公共区域里的人数总量。

传统的 LOI 方法是通过提取视频中对应 LOI 那条线上的信息生成 2D temporal slices
generating 2D temporal slices by temporally concatenating video frame lines at the LOI

基于 temporal slices 我们来估计通过画线的人流总量，这种方法在某些情况下效果不太好
When the scene is not crowded and pedestrians walks in normal speed (Fig. 1(b, row 1)), people can be well recognized in the temporal slices. However, we observe that temporal slices are not robust to scenes with high crowd density, slow walking speed, and low camera viewing angles. In Fig. 1(b, row2), the temporal slice shows excess jitters and people in it are no longer recognizable

本文使用 CNN 网络从视频序列中学习特征，分两个步骤来解决计数问题

3 Method
3.1 Pixel-level supervision maps

根据视频序列帧，我们得到中间结果 Density map 和 Velocity map，有了这两个信息，再去得到 Supervision crowd counting map
The crowd counting map can then be obtained as the elementwise multiplication of the density and velocity maps
相应位置数值相乘得到 crowd counting map

3.2 Deep Convolutional Neural Network for LOI crowd counting

我们的网络结构如下：

We propose to train the CNN in two phases. In the first training phase, the network is trained to predict the crowd density map D t and the crowd velocity map V t simultaneously
我们是分步训练上面的网络的，首先训练 predict the crowd density map 和 crowd velocity map，再微调 fine-tune the trained network in the second phase with
supervision of the crossing-line crowd counting map

3.3 From crowd counting map to LOI counts
这一步主要是根据 crowd counting map 我们计算得到画线的随时间变化的人流量

4 Experiments
我们针对越线人群计数，建立了一个新的数据库

越线人群计数--Crossing-line Crowd Counting with Two-phase Deep Neural Networks相关推荐

《Improved Crowd Counting Method Based onScale-Adaptive Convolutional Neural Network》论文笔记
<Improved Crowd Counting Method Based onScale-Adaptive Convolutional Neural Network>论文笔记论文地址 ...
【人群计数】Crossing the Line: Crowd Counting by Integer Programming with Local Features
Abstract 作者提出了一种对于视频中穿过关注线的行人数量实时整数规划方法.视频首先被转换为时序序列,然后人数会通过一系列有重叠的窗口进行估计,使用了一种从局部特征到数量的回归函数进行映射.考虑到 ...
人群密度估计--Fully Convolutional Crowd Counting On Highly Congested Scenes
Fully Convolutional Crowd Counting On Highly Congested Scenes The 12th International Conference on C ...
crowd counting
crowd counting 人群密度估计之MCNN https://blog.csdn.net/qq_14845119/article/details/68946727 2016年 --Single ...
GitHub：人群计数最全资料集锦
作者:gjy3035 | 编辑:Amusi 前言 CVer 陆续分享了GitHub上优质的AI/CV资料集锦,如图像分类.目标检测.语义分割等,之前的分享详见文末.很多同学反映这个系列很棒,因此系列将 ...
人群计数数据集汇总和详细介绍,全网最全，crowd counting datasets
Crowd Counting数据集汇总视频监控=video surveillance https://github.com/gjy3035/Awesome-Crowd-Counting/blob/m ...
crowd counting 综述分析
Crowd counting 人群计数目前从两个角度来解决,一类方法是回归计数,直接得到图像中总人数的估计,另一类方法是先估计密度图,再有密度图积分求和得到总人数.目前来说密度图提供的信息更多些,得到 ...
人群计数最全代码、数据、论文合集
2021.11.19更新: 人群计数 /Crowd Counting Rethinking Counting and Localization in Crowds:A Purely Point-Bas ...
图片人群计数模型代码运行指南
PaperWithCode 八大数据集模型排名:https://paperswithcode.com/task/crowd-counting 搜索关键词 "人群计数"(crowd ...

越线人群计数--Crossing-line Crowd Counting with Two-phase Deep Neural Networks

越线人群计数--Crossing-line Crowd Counting with Two-phase Deep Neural Networks相关推荐

最新文章

热门文章