IEEE Access · 2022 · 10 citations · 31 references
ComputingComputer ScienceBayesian Data AnalysisComputer VisionMachine LearningBayesian ComputationBayesian InferenceBayesian StatisticsDeep LearningStatistical InferenceBayesian Deep LearningBayesian Loss ModelingCrowd CountingCrowd Scene AnalysisProbabilistic Deep Learning
Deep learning-based crowd density estimation can greatly improve the accuracy of crowd counting. Though a Bayesian loss method resolves the two problems of the need of a hand-crafted ground truth (GT) density and noisy annotations, counting accurately in high-congested scenes remains a challenging issue. In a crowd scene, people’s appearances change according to the scale of each individual ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , the person-scale). Also, the lower the sparsity of a local region ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , the crowd-sparsity), the more difficult it is to estimate the crowd density. In this paper, we propose a novel congestion-aware Bayesian loss method that considers the person-scale and crowd-sparsity. We estimate the person-scale based on scene geometry, and we then estimate the crowd-sparsity using the estimated person-scale. The estimated person-scale and crowd-sparsity are utilized in the novel congestion-aware Bayesian loss method to improve the supervising representation of the point annotations. We verified the effectiveness of each proposed component through several ablation experiments, and in the various experiments on public datasets, our proposed method achieved state-of-the-art performance.
31
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
Yingying Zhang, Desen Zhou, Siqin Chen et al. · 2016 · 2.3K citations
Cross-scene crowd counting via deep convolutional neural networks
Cong Zhang, Hongsheng Li, Xiaogang Wang et al. · 2015 · 1.2K citations
Multi-source Multi-scale Counting in Extremely Dense Crowd Images
Haroon Idrees, Imran Saleemi, Cody Seibert et al. · 2013 · 1.1K citations · Full text