Mo Hong, Ren Wenqi, Xiong Yuan, Pan Xiaoqi, Zhou Zhong, Cao Xiaochun, Wu Wei
IEEE Trans Image Process. 2020 Aug 6;PP. doi: 10.1109/TIP.2020.3009030.
Crowd counting is a challenging problem due to the diverse crowd distribution and background interference. In this paper, we propose a new approach for head size estimation to reduce the impact of different crowd scale and background noise. Different from just using local information of distance between human heads, the global information of the people distribution in the whole image is also under consideration. We obey the order of far- to near-region (small to large) to spread head size, and ensure that the propagation is uninterrupted by inserting dummy head points. The estimated head size is further exploited, such as dividing the crowd into parts of different densities and generating a high-fidelity head mask. On the other hand, we design three different head mask usage mechanisms and the corresponding head masks to analyze where and which mask could lead to better background filtering1. Based on the learned masks, two competitive models are proposed which can perform robust crowd estimation against background noise and diverse crowd scale. We evaluate the proposed method on three public crowd counting datasets of ShanghaiTech [2], UCFQNRF [3] and UCFCC_50 [4]. Experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art crowd counting approaches.
由于人群分布多样和背景干扰，人群计数是一个具有挑战性的问题。在本文中，我们提出了一种新的头部尺寸估计方法，以减少不同人群规模和背景噪声的影响。与仅使用人头之间距离的局部信息不同，我们还考虑了整个图像中人群分布的全局信息。我们按照从远到近区域（从小到大）的顺序来扩展头部尺寸，并通过插入虚拟头部点来确保传播不中断。进一步利用估计的头部尺寸，例如将人群划分为不同密度的部分并生成高保真头部掩码。另一方面，我们设计了三种不同的头部掩码使用机制以及相应的头部掩码，以分析何处以及哪种掩码可以带来更好的背景过滤效果。基于学习到的掩码，我们提出了两种具有竞争力的模型，它们可以针对背景噪声和多样的人群规模进行稳健的人群估计。我们在上海科技大学[2]、UCFQNRF[3]和UCFCC_50[4]这三个公开的人群计数数据集上对所提出的方法进行了评估。实验结果表明，所提出的算法优于当前最先进的人群计数方法。
