School of Computer Science and Technology, East China Normal University, Shanghai 200062, China.
Sensors (Basel). 2020 Jul 6;20(13):3781. doi: 10.3390/s20133781.
The goal of crowd counting is to estimate the number of people in the image. Presently, use regression to count people number became a mainstream method. It is worth noting that, with the development of convolutional neural networks (CNN), methods that are based on CNN have become a research hotspot. It is a more interesting topic that how to locate the site of the person in the image than simply predicting the number of people in the image. The perspective transformation present is still a challenge, because perspective distortion will cause differences in the size of the crowd in the image. To devote perspective distortion and locate the site of the person more accuracy, we design a novel framework named Adaptive Learning Network (CAL). We use the VGG as the backbone. After each pooling layer is output, we collect the 1/2, 1/4, 1/8, and 1/16 features of the original image and combine them with the weights learned by an adaptive learning branch. The object of our adaptive learning branch is each image in the datasets. By combining the output features of different sizes of each image, the challenge of drastic changes in the size of the image crowd due to perspective transformation is reduced. We conducted experiments on four population counting data sets (i.e., ShanghaiTech Part A, ShanghaiTech Part B, UCF_CC_50 and UCF-QNRF), and the results show that our model has a good performance.
人群计数的目标是估计图像中的人数。目前，使用回归来计数已成为主流方法。值得注意的是，随着卷积神经网络（CNN）的发展，基于 CNN 的方法已成为研究热点。如何在图像中定位人的位置比简单地预测图像中的人数更有趣。目前的透视变换仍然是一个挑战，因为透视失真会导致图像中人群大小的差异。为了更准确地进行透视失真和定位人的位置，我们设计了一个名为自适应学习网络（CAL）的新框架。我们使用 VGG 作为骨干。在输出每个池化层之后，我们收集原始图像的 1/2、1/4、1/8 和 1/16 特征，并将它们与自适应学习分支学习到的权重结合起来。我们自适应学习分支的目标是数据集内的每张图像。通过结合每张图像不同大小的输出特征，减少了由于透视变换导致图像人群大小急剧变化的挑战。我们在四个人群计数数据集（即 ShanghaiTech Part A、ShanghaiTech Part B、UCF_CC_50 和 UCF-QNRF）上进行了实验，结果表明我们的模型具有良好的性能。
