Unsupervised dense crowd detection by multiscale texture analysis

Fagette, Antoine; Courty, Nicolas; Racoceanu, Daniel; Dufour, Jean-Yves

doi:10.1016/j.patrec.2013.09.020

Cited by 24 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments with human operators showed that the system leads to a significant reduction of missed people by using the interactive functionality, especially for large time intervals [5]. The tracking system was integrated and validated in a crowded [13] [19] shopping mall in the Netherlands, in collaboration with five SMEs [4]. The system performed consistently and robustly.…”

Section: Graphical User Interfacementioning

confidence: 99%

Finding suspects in multiple cameras for improved railway protection

et al. 2014

View full text Add to dashboard Cite

The capability to find individuals using CCTV cameras is important for surveillance applications at large areas such as railway stations, airports and shopping centers. However, it is laborious to track and trace people over multiple cameras post incident. In this paper, we describe the live demonstration of our interactive re-identification system in a railway station. The system performs real-time track generation in multiple cameras and live re-identification and refinding of suspects which was live demonstrated in Poland. The system allows fast interactive retrieval of an individual by showing only similar candidates. An operator can find the origin or destination of a person more efficiently, especially over large time and space intervals.

show abstract

Section: Graphical User Interfacementioning

confidence: 99%

Finding suspects in multiple cameras for improved railway protection

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Sample results are shown in Figure 14. Similarly, Fagette et al [136] proposed an unsupervised method using multi-scale texture-based features to detect and localize dense crowds in images. The unsupervised method allows detection on images without the need to have prior knowledge of the scene or context.…”

Section: Crowd Segmentationmentioning

confidence: 99%

Crowd behavior analysis: A review where physics meets biology

2016

View full text Add to dashboard Cite

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 with the understanding of the emergent behavior in physics (complex systems) and biology (animal swarm). These studies, which are inspired by biology and physics, share surprisingly common insights, and interesting contradictions. However, this aspect of discussion has not been fully explored. Therefore, this survey provides the readers with a review of the state-of-the-art methods in crowd behavior analysis from the physics and biologically inspired perspectives. We provide insights and comprehensive discussions for a broader understanding of the underlying prospect of blending physics and biology studies in computer vision.

show abstract

“…Terrestrial cameras already provide the major part of this information as images and videos. In general, a lot of research has been done to process this huge amount of data automatically [1][2][3][4], and most often with the goal of crowd counting [5][6][7][8], person tracking [9,10], or behavior understanding [11,12]. However, all these methods are tested on benchmark datasets containing terrestrial images or videos, and do not consider aerial images for crowd counting.…”

Section: Background and Motivationmentioning

confidence: 99%

Detection of High-Density Crowds in Aerial Images Using Texture Classification

2016

View full text Add to dashboard Cite

Automatic crowd detection in aerial images is certainly a useful source of information to prevent crowd disasters in large complex scenarios of mass events. A number of publications employ regression-based methods for crowd counting and crowd density estimation. However, these methods work only when a correct manual count is available to serve as a reference. Therefore, it is the objective of this paper to detect high-density crowds in aerial images, where counting-or regression-based approaches would fail. We compare two texture-classification methodologies on a dataset of aerial image patches which are grouped into ranges of different crowd density. These methodologies are: (1) a Bag-of-words (BoW) model with two alternative local features encoded as Improved Fisher Vectors and (2) features based on a Gabor filter bank. Our results show that a classifier using either BoW or Gabor features can detect crowded image regions with 97% classification accuracy. In our tests of four classes of different crowd-density ranges, BoW-based features have a 5%-12% better accuracy than Gabor.

show abstract

Unsupervised dense crowd detection by multiscale texture analysis

Cited by 24 publications

References 19 publications

Finding suspects in multiple cameras for improved railway protection

Finding suspects in multiple cameras for improved railway protection

Crowd behavior analysis: A review where physics meets biology

Detection of High-Density Crowds in Aerial Images Using Texture Classification

Contact Info

Product

Resources

About