摘要
针对人群分析任务中往往存在的因监控与人群距离不同而导致的尺度变化大的问题,提出一种基于正态逆伽马分布的多尺度融合人群计数算法MSF(Multi-Scale Fusion crowd counting)。首先,使用传统骨架提取公共特征,通过多尺度信息提取模块获得图像中不同尺度的行人信息;其次,每个尺度的网络各自包含一个人群密度估计模块和一个用于评估每个尺度预测结果可信度的不确定估计模块;最后,多尺度预测融合模块依据可信度对多尺度预测结果进行动态融合,以获得更准确的密度回归结果。实验结果表明,现有算法密集场景识别网络(CSRNet)在通过多尺度可信融合扩展后,在UCF-QNRF数据集上人群计数的平均绝对误差(MAE)和均方误差(MSE)分别减小了4.43%和1.37%,验证了MSF算法的合理性和有效性。此外,与现有算法不同,MSF算法不仅可以预测人群密度,还可以在部署阶段提供预测的可信程度,从而使算法在实际应用中能及时预警模型预测不准确的区域,降低后续分析任务出现错误预判的风险。
To solve the problem of large variation caused by different distances between monitoring camera and crowd in the crowd analysis tasks,a crowd counting algorithm with multi-scale fusion based on normal inverse Gamma distribution was proposed,named MSF(Multi-Scale Fusion crowd counting)algorithm.Firstly,the common features were extracted with the traditional backbone,and then the pedestrian information of different scales was obtained with the multi-scale information extraction module.Secondly,a crowd density estimation module and an uncertainty estimation module for evaluating the reliability of the prediction results of each scale were contained in each scale network.Finally,more accurate density regression results were obtained by dynamically fusing the multi-scale prediction results based on the reliability in the multiscale prediction fusion module.The experimental results show that after the expansion of the existing method Converged Scene Recognition Network(CSRNet)by multi-scale trusted fusion,the Mean Absolute Error(MAE)and Mean Squared Error(MSE)of crowd counting on UCF-QNRF dataset are significantly decreased by 4.43%and 1.37%,respectively,which verifies the rationality and effectiveness of MSF algorithm.In addition,different from the existing methods,the MSF algorithm can not only predict the crowd density,but also provide the reliability of the prediction during the deployment stage,so that the inaccurate areas predicted by the algorithm can be timely warned in practical applications,reducing the wrong prediction risks in subsequent analysis tasks.
作者
李伟
张晓蓉
陈鹏
李清
张长青
LI Wei;ZHANG Xiaorong;CHEN Peng;LI Qing;ZHANG Changqing(The 28th Research Institute,China Electronics Technology Group Corporation,Nanjing Jiangsu 210007,China;College of Intelligence and Computing,Tianjin University,Tianjin 300354,China)
出处
《计算机应用》
CSCD
北大核心
2024年第7期2243-2249,共7页
journal of Computer Applications
基金
国家自然科学基金资助项目(61976151)。
关键词
人群计数
多尺度
可信融合
人群密度估计
不确定性
crowd counting
multi-scale
trustworthy fusion
crowd density estimation
uncertainty
