车辆密度估计–Understanding Traffic Density from Large-Scale Web Camera Data
Understanding Traffic Density from Large-Scale Web Camera Data
CVPR2017
https://arxiv.org/abs/1703.05868
本文介绍了两个算法用于车辆密度估计：1）OPT-RC 根据背景差得到车辆运动区域，对于图像的不同区域学习到一个对应的权值矩阵用于估计车辆密度
2）FCN-MT 使用 FCN 分割框架来进行车辆密度估计
车辆密度估计问题还是比较难的，类似于人群密度估计
Optimization Based Vehicle Density Estimation with RankConstraint(OPT-RC)
we propose a regression model to learn different weights for different blocks to increase the degrees of freedom on the weights, and embed geometry information
用一个回归模型来学习图像区域对应不同的密度估计权值矩阵，嵌入了几何信息
FCN Based Multi-Task Learning for Vehicle Counting (FCN-MT)
网络分为 convolution network, decovolution network , 将卷积层各个层的特征融合起来，输入到反卷积网络中进行特征图放大
the large buses/trucks (oversized vehicles) in close view induce sporadically large errors in the counting results. To solve this problem, we propose a deep multi-task learning framework based on FCN to jointly learn vehicle density map and vehicle count.
为了解决个别大型车辆在图像中占有大面积导致车辆数估计有大的错误，这里使用了多目标学习
- Experiments
这里我们建立了一个数据库 WebCamT
