论文标题

BBA-NET:一个双分支注意力网络,用于人群计数

BBA-net: A bi-branch attention network for crowd counting

论文作者

Hou, Yi, Li, Chengyang, Yang, Fan, Ma, Cong, Zhu, Liping, Li, Yuan, Jia, Huizhu, Xie, Xiaodong

论文摘要

在人群计数的领域中,当前基于CNN的主流回归方法只需在没有找到每个人的位置的情况下提取行人的密度信息即可。这使得网络的输出经常被发现包含不正确的响应,这可能会错误地估计总数,并且不利于解释算法。为此,我们提出了一个双分支注意力网络(BBA-net)进行人群计数,该网络具有三个创新点。 i)使用两个分支机构架构来分别估计密度信息和位置信息。 ii)注意机制用于促进特征提取,这可以减少错误的反应。 iii)引入了一种新的密度图生成方法,结合了几何适应和伏诺诺。我们的方法可以整合行人的头和身体信息,以增强密度图的特征表达能力。在两个公共数据集上进行的广泛实验表明,与其他最新方法相比,我们的方法达到了较低的人群计数错误。

In the field of crowd counting, the current mainstream CNN-based regression methods simply extract the density information of pedestrians without finding the position of each person. This makes the output of the network often found to contain incorrect responses, which may erroneously estimate the total number and not conducive to the interpretation of the algorithm. To this end, we propose a Bi-Branch Attention Network (BBA-NET) for crowd counting, which has three innovation points. i) A two-branch architecture is used to estimate the density information and location information separately. ii) Attention mechanism is used to facilitate feature extraction, which can reduce false responses. iii) A new density map generation method combining geometric adaptation and Voronoi split is introduced. Our method can integrate the pedestrian's head and body information to enhance the feature expression ability of the density map. Extensive experiments performed on two public datasets show that our method achieves a lower crowd counting error compared to other state-of-the-art methods.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源