Counting people or objects with significantly varying scales and densities has attracted much interest from the research community and yet it remains an open problem. In this paper, we propose a simple but efficient and effective network, named DENet, which is composed of two components, i.e., a detection network (DNet) and an encoder-decoder estimation network (ENet). We first run the DNet on the input image to detect and count individuals who can be segmented clearly. Then, the ENet is utilized to estimate the density maps of the remaining areas, typically with low resolution and high densities where individuals cannot be detected. For this purpose, we propose a modified Xception network as the encoder for feature extraction and a combination of dilated convolution and transposed convolution as the decoder. When evaluated on the ShanghaiTech Part A, UCF and WorldExpo’10 datasets, our DENet has achieved lower Mean Absolute Error (MAE) than those of the state-of-the-art methods.

中文翻译：

---

DENet：用于计算不同密度和规模人群的通用网络


对规模和密度差异很大的人或物体进行计数引起了研究界的极大兴趣，但这仍然是一个悬而未决的问题。在本文中，我们提出了一种简单但高效且有效的网络，称为DENet，它由两个组件组成，即检测网络（DNet）和编码器-解码器估计网络（ENet）。我们首先在输入图像上运行 DNet，以检测和计数可以清晰分割的个体。然后，利用 ENet 来估计剩余区域的密度图，这些区域通常具有低分辨率和高密度，无法检测到个体。为此，我们提出了一种改进的 Xception 网络作为特征提取的编码器，以及扩张卷积和转置卷积的组合作为解码器。当在上海科技大学 A 部分、UCF 和 WorldExpo'10 数据集上进行评估时，我们的 DENet 实现了比最先进方法更低的平均绝对误差 (MAE)。