In this paper, we propose a method called Convolutional Neural Network-Markov Random Field (CNN-MRF) to estimate the crowd count in a still image. We first divide the dense crowd visible image into overlapping patches and then use a deep convolutional neural network to extract features from each patch image, followed by a fully connected neural network to regress the local patch crowd count. Si...

Although the traits emerged in a mass gathering are often non-deliberative, the act of mass impulse may lead to irrevocable crowd disasters. The two-fold increase of carnage in crowd since the past two decades has spurred significant advances in the field of computer vision, towards effective and proactive crowd surveillance. Computer vision studies related to crowd are observed to resonate wit...

Diversifying participation in crowd work can benefit the worker and requester. Increasing numbers of older adults are online, but little is known about their awareness of or how they engage in mainstream crowd work. Through an online survey with 505 seniors, we found that most have never heard of crowd work but would be motivated to complete tasks by earning money or working on interesting or s...

Online labor marketplaces offer the potential to automate a variety of tasks too difficult for computers, but present requesters with significant difficulties in obtaining accurate results. We share experiences from building MobileWorks, a crowd platform that departs from the marketplace model to provide robust, high-quality results. Three architectural contributions yield measurably improved a...

This paper proposes an image textural analytical method for estimating the crowd density and counting. At first, the target detection is conducted to obtain the foreground image. This crowd image is used to calculate the gray level co-occurrence matrix (GLCM). Then, according to the characteristic values of the gray level co-occurrence matrix, i.e., energy, entropy, contrast, homogeneity, we us...

In this paper a new and original technique to animate a crowd of human beings is presented. Following the success of data-driven animation models (such as motion capture) in the context of articulated figures control, we propose to derivate a similar type of approach for crowd motions. In our framework, the motion of the crowds are represented as a time series of velocity fields estimated from ...

In this paper, we propose a method to estimate crowd density using improved Harris and Optics Algorithms. We pre-processed the raw images at first and the corner features of the crowd were detected by the improved Harris algorithm, then the formed density point data were used to analyze the corner characters of crowd density by the optics density clustering theory. This theory is related to the...

Detecting individual pedestrians in a crowd remains a challenging problem since the pedestrians often gather together and occlude each other in real-world scenarios. In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem. Then, we propose a novel bounding box regression loss...

Large-scale crowd simulations require distributed computer architectures and efficient parallel techniques to achieve the rendering of visually plausible images while simulating the behaviour of crowds of autonomous agents. The Java-based multiagent platforms, devoted to provide the agents with the required lifecycle, represent a key middleware in crowd systems. However, since they are oriented...

Due to the poor transfer organization in urban public transport terminal, pedestrian crowd are often forced to weaving in their transfer flow lines. Frequent weaving behaviors not only decrease passengers’ transfer comfort, but may also trigger serious crowd disaster such as trampling. In order to get accurate understanding of the weaving features of pedestrian crowd and analyze the relevant ev...