Hangzhou Dianzi University, Baiyang Road No. 2, Hangzhou, China.
Comput Intell Neurosci. 2021 Nov 11;2021:9996232. doi: 10.1155/2021/9996232. eCollection 2021.
The most advanced method for crowd counting uses a fully convolutional network that extracts image features and then generates a crowd density map. However, this process often encounters multiscale and contextual loss problems. To address these problems, we propose a multiscale aggregation network (MANet) that includes a feature extraction encoder (FEE) and a density map decoder (DMD). The FEE uses a cascaded scale pyramid network to extract multiscale features and obtains contextual features through dense connections. The DMD uses deconvolution and fusion operations to generate features containing detailed information. These features can be further converted into high-quality density maps to accurately calculate the number of people in a crowd. An empirical comparison using four mainstream datasets (ShanghaiTech, WorldExpo'10, UCF_CC_50, and SmartCity) shows that the proposed method is more effective in terms of the mean absolute error and mean squared error. The source code is available at https://github.com/lpfworld/MANet.
最先进的人群计数方法使用全卷积网络来提取图像特征，然后生成人群密度图。然而，这个过程经常会遇到多尺度和上下文损失问题。为了解决这些问题，我们提出了一种多尺度聚合网络（MANet），它包括特征提取编码器（FEE）和密度图解码器（DMD）。FEE 使用级联尺度金字塔网络来提取多尺度特征，并通过密集连接获得上下文特征。DMD 使用反卷积和融合操作生成包含详细信息的特征。这些特征可以进一步转换为高质量的密度图，以准确计算人群中的人数。使用四个主流数据集（ShanghaiTech、WorldExpo'10、UCF_CC_50 和 SmartCity）进行的实证比较表明，该方法在平均绝对误差和均方误差方面更有效。源代码可在 https://github.com/lpfworld/MANet 上获得。
