Related papers: Learning Extremely High Density Crowds as Active M…

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose…

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. While effective, these data-driven approaches rely on large amount of data annotation to achieve good performance, which stops…

Crowd scenes captured by cameras at different locations vary greatly, and existing crowd models have limited generalization for unseen surveillance scenes. To improve the generalization of the model, we regard different surveillance scenes…

Compared with single image based crowd counting, video provides the spatial-temporal information of the crowd that would help improve the robustness of crowd counting. But translation, rotation and scaling of people lead to the change of…

Accurately estimating the number of objects in a single image is a challenging yet meaningful task and has been applied in many applications such as urban planning and public safety. In the various object counting tasks, crowd counting is…

Video activity recognition by deep neural networks is impressive for many classes. However, it falls short of human performance, especially for challenging to discriminate activities. Humans differentiate these complex activities by…

State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors. In crowded scenes, however, detectors often fail to…

Human motion modelling is crucial in many areas such as computer graphics, vision and virtual reality. Acquiring high-quality skeletal motions is difficult due to the need for specialized equipment and laborious manual post-posting, which…

Crowd counting has recently attracted significant attention in the field of computer vision due to its wide applications to image understanding. Numerous methods have been proposed and achieved state-of-the-art performance for real-world…

Stochastic particle--based models are useful tools for describing the collective movement of large crowds of pedestrians in crowded confined environments. Using descriptions based on the simple exclusion process, two populations of…

Video-based human pose estimation in crowded scenes is a challenging problem due to occlusion, motion blur, scale variation and viewpoint change, etc. Prior approaches always fail to deal with this problem because of (1) lacking of usage of…

This study enhances a crowd density estimation algorithm originally designed for image-based analysis by adapting it for video-based scenarios. The proposed method integrates a denoising probabilistic model that utilizes diffusion processes…

Safe and efficient crowd navigation for mobile robot is a crucial yet challenging task. Previous work has shown the power of deep reinforcement learning frameworks to train efficient policies. However, their performance deteriorates when…

In this paper, we present a data-driven approach to generate realistic steering behaviors for virtual crowds in crowd simulation. We take advantage of both rule-based models and data-driven models by applying the interaction patterns…

Large crowds exhibit intricate behaviors and significant emergent properties, yet existing crowd simulation systems often lack behavioral diversity, resulting in homogeneous simulation outcomes. To address this limitation, we propose…

While the performance of crowd counting via deep learning has been improved dramatically in the recent years, it remains an ingrained problem due to cluttered backgrounds and varying scales of people within an image. In this paper, we…

This paper presents a new approach to behavioral-social dynamics of human crowds. First order models are derived based on mass conservation at the macroscopic scale, while methods of the kinetic theory are used to model the decisional…

Dense pedestrian crowds may pose significant safety risks, yet their underlying dynamics remain insufficiently understood to reliably prevent accidents. In these environments, physical interactions and contact forces fundamentally shape the…

In this work, we tackle the problem of crowd counting in images. We present a Convolutional Neural Network (CNN) based density estimation approach to solve this problem. Predicting a high resolution density map in one go is a challenging…

Crowd localization is a new computer vision task, evolved from crowd counting. Different from the latter, it provides more precise location information for each instance, not just counting numbers for the whole crowd scene, which brings…