人群分析--Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks
来源:互联网 发布:举报淘宝盗图 编辑:程序博客网 时间:2024/05/17 06:20
Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks - Counting, Detection, and Tracking
https://arxiv.org/abs/1705.10118
基于人群密度图估计的人群分析,这里我们主要对比各种 CNN-based density estimation methods 用于 counting, detection, and tracking,我们得到的结论是
high-quality density maps 对于 detection 和 tracking 都是有帮助的。
基于密度图估计的计数思想最早是由文献【3】提出的 Maximum Excess over Sub Array (MESA) distance。 随后各种 CNN 来估计密度图
本文主要考虑两个CNN网络生成 full-resolution density maps:CNN-pixel 和 FCNN-skip
对于 CNN-pixel,我们使用一个 classic CNN regressor for pixel-wise density prediction 也就是说用滑动窗口的方式来得到每个像素的预测结果
given an image patch, predict the density at the center pixel. The full-resolution density map is obtained using a sliding window to obtain density values for all pixels inside the ROI.
对于 Fully Convolutional Architecture: hole convolution 的效果要比 FCNN-skip 差
C. Detection from Density Maps
根据密度图来做检测,首先是文献【11】提出的
D. Improving Tracking with Density Maps
用密度图来改善跟踪
Experiments
实验使用的数据库:
UCSD dataset
Summary
In summary, CNN-pixel performs best on various metrics, including compactness, localization MAE, and temporal smoothness. This suggests that using full-resolution perpixel prediction of the density map can improve detection and tracking. In contrast, reduced-resolution maps that require either fixed upsampling (CNN-patch and MCNN) or learned upsampling-convolution (FCNN-skip and MCNN-up) had worse quality metrics, resulting in poorer detection/tracking accuracy. The downsampling operations in the CNN obfuscate the true position of the people in the reduced-resolution maps. This loss of spatial information can only be partially compensated using learned upsampling and skip connections.
However, dense prediction suffers from higher computational complexity, compared to fully-convolutional networks
一句话: CNN-pixel 效果好但是计算量大
- 人群分析--Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks
- 人群密度估计-Crowd Density
- 人群密度估计--CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd
- 人群密度估计--Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs
- 人群计数--Switching Convolutional Neural Network for Crowd Counting
- 人群密度估计--Spatiotemporal Modeling for Crowd Counting in Videos
- 人群行为分类数据库--Crowd-11: A Dataset for Fine Grained Crowd Behaviour Analysis
- 人群密度估计--CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
- 快速人群密度估计--Multi-scale Convolutional Neural Networks for Crowd Counting
- 人群密度估计--Learning a perspective-embedded deconvolution network for crowd counting
- 论文笔记:A survey of recent advances in CNN-based single image crowd counting and density estimation
- 人群场景分析--Slicing Convolutional Neural Network for Crowd Video Understanding
- Constructing module maps for integrated analysis of heterogeneous biological networks
- 人群分割--Fully Convolutional Neural Networks for Crowd Segmentation
- 人群计数--Mixture of Counting CNNs
- 人群行为分析--Understanding Pedestrian Behaviors from Stationary Crowd Groups
- 人群分析综述--Crowd Scene Understanding from Video: A Survey
- 人群计数:Single-Image Crowd Counting via Multi-Column Convolutional Neural Network(CVPR2016)
- client必要的一句话
- Ext JS开发实用工具总结
- Http2.2实现https
- Sypder
- 98. Validate Binary Search Tree
- 人群分析--Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks
- [BZOJ]1266: [AHOI2006]上学路线route spfa+最小割
- JDBC连接oracle数据库,并实现批量插入
- JavaSSM学习小结(3):Service层开发
- 模拟信号求解相位差(1)
- extern C作用总结
- postgresql删除主键
- Android三种姿势带你玩转360度全景图功能
- SSH中hibernate配置mysql乱码问题