专栏首页机器学习、深度学习人群密度估计--Learning a perspective-embedded deconvolution network for crowd counting

人群密度估计--Learning a perspective-embedded deconvolution network for crowd counting

Learning a perspective-embedded deconvolution network for crowd counting 没有找到代码

本文在人群密度估计这个问题上的创新点: fuse the perspective into a deconvolution network

首先看看 Perspective Perspective is an inherent property of most surveillance scenes

所谓的 Perspective 就是同一个尺寸的物体,在图像中位置的不同其在图像中的尺寸也是不一样的。距离相机越远其尺寸越小,距离相机越近其尺寸越大。在人群图像中的表现就是离相机远的人其在图像中就显得比较小,离相机比较近的人其在图像中显得比较大。 Perspective distortions need to be compensated in regression-based crowd counting methods

真值密度图的生成还是 人头位置的 Gaussian kernels 的求和,使用 perspective maps 来矫正 perspective distortion,主要根据这个 perspective maps 来设置 Gaussian kernels 中参数 the ground truth density map is defined as a summation of all the Gaussian kernels centering at each center of the objects. Due to the varying sizes of pedestrians caused by perspective distortion, it is necessary to incorporate specific scene geometric information to cover the size variations

下面接着来看这个 deconvolution network

网络的输入是 RGB images and the perspective maps L2 loss between the estimated and ground truth density maps is used to train our netowrk:

4.2. Baseline model: the counting FCN 基于语义分割框架 FCN的 baseline model (CFCN): the CFCN network constitutes layers from conv1 to conv4, with filter sizes of 32 7×7×3, 32 7×7×32, 64 5×5×32 for the first three layers.

4.3. Deconvolution network CFCN-DCN:加了两个卷积层 conv5 with filter size 5 × 5 and conv6 with filter size 7 × 7 are learnable kernels for precisely dense output a full-resolution output map

4.4. Perspective fusion the perspective-embedded deconvolution network (PE-CFCN-DCN) 这里看 图2 比较直接明了 A perspective map pyramid is constructed at different resolutions according to the network. Then fusion layer is implemented by direct concatenation of the feature maps from the RGB input and the correspondingly-sized perspective map. Each fusion layer is inserted before each deconvolution block for guided interpolation.

the labeled perspective map 这个怎么得到了?

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

我来说两句

0 条评论
登录 后参与评论

相关文章

  • 相机标定--A Flexible New Technique for Camera Calibration

    版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.n...

    用户1148525
  • 图像拼接--Seam Carving for Content-Aware Image Resizing

    Seam Carving for Content-Aware Image Resizing 智能图像缩放 ACM Transactions on graph...

    用户1148525
  • 统计学习导论 Chapter2--What Is Statistical Learning?

    Book: An Introduction to Statistical Learning with Appli...

    用户1148525
  • 使用VisualVM进行Java应用的性能测量

    Recently I am trying to find a handy tool to measure the performance of my Java ...

    Jerry Wang
  • SAP Fiori OData取数据的同步模式和异步模式比较

    Yesterday I was challenged by my colleague: in the CRM Fiori application “My Opp...

    Jerry Wang
  • webIDE里创建extension project时遇到错误的解决方案

    Suppose you try to create a new extension project based on one existing project:

    Jerry Wang
  • 如何处理WebIDE里运行UI5应用遇到的404 not found错误

    how to resolve 404 not found error for sap-ui-core.js after project is cloned to...

    Jerry Wang
  • Codeforces Round #415 (Div. 2)(A,暴力,B,贪心,排序)

    A. Straight «A» time limit per test:1 second memory limit per test:256 megabytes...

    Angel_Kitty
  • [security] Go 1.11.3 and Go 1.10.6 pre-announcement

    We plan to issue Go 1.11.3 and Go 1.10.6 on Wednesday, December 12 at

    李海彬
  • SAP WebClient UI和business switch相关的逻辑介绍

    Do you know the meaning of these two checkboxes in F2 popup?

    Jerry Wang

扫码关注云+社区

领取腾讯云代金券