On the efficacy of texture analysis for crowd monitoring

Marana, Aparecido Nilceu; Costa, L.F.; Lotufo, Roberto de Alencar; Velastín, Sergio A.

doi:10.1109/sibgra.1998.722773

Cited by 125 publications

(76 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has a multitude of reasons: from limited applications to indoor environments with controlled lighting (e.g. subway platforms) [10]- [13], [15]; to ignoring crowd dynamics (i.e. treating people moving in different directions as the same) [10]- [14], [16]; to assumptions of homogeneous crowd density (i.e.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Counting People With Low-Level Features and Bayesian Regression

Chan

Vasconcelos

2012

IEEE Trans. on Image Process.

359

232

View full text Add to dashboard Cite

Abstract-An approach to the problem of estimating the size of inhomogeneous crowds, composed of pedestrians that travel in different directions, without using explicit object segmentation or tracking is proposed. Instead, the crowd is segmented into components of homogeneous motion, using the mixture of dynamic textures motion model. A set of holistic low-level features is extracted from each segmented region, and a function that maps features into estimates of the number of people per segment is learned with Bayesian regression. Two Bayesian regression models are examined. The first is a combination of Gaussian process regression (GPR) with a compound kernel, which accounts for both the global and local trends of the count mapping, but is limited by the real-valued outputs that do not match the discrete counts. We address this limitation with a second model, which is based on a Bayesian treatment of Poisson regression that introduces a prior distribution on the linear weights of the model. Since exact inference is analytically intractable, a closedform approximation is derived that is computationally efficient and kernelizable, enabling the representation of non-linear functions. An approximate marginal likelihood is also derived for kernel hyperparameter learning. The two regression-based crowd counting methods are evaluated on a large pedestrian dataset, containing very distinct camera views, pedestrian traffic, and outliers, such as bikes or skateboarders. Experimental results show that regression-based counts are accurate, regardless of the crowd size, outperforming the count estimates produced by stateof-the-art pedestrian detectors. Results on two hours of video demonstrate the efficiency and robustness of regression-based crowd size estimation over long periods of time.

show abstract

Section: Introductionmentioning

confidence: 99%

“…spacing between people) [15]; to measuring a surrogate of the crowd size (e.g. crowd density or percent crowding) [10], [11], [15]; to questionable scalability to scenes involving more than a few people [16]; to limited experimental validation of the proposed algorithms [10]- [12], [14], [15].…”

Section: Introductionmentioning

confidence: 99%

Counting People With Low-Level Features and Bayesian Regression

Chan

Vasconcelos

2012

IEEE Trans. on Image Process.

359

232

View full text Add to dashboard Cite

show abstract

“…However, people often walk in groups, that are composed of a number of people that are fully visible, and just side by side, or cause little occlusion [12,13,14]. A crowd is, on the other hand, a group in which people are so close that the occlusion level is sensibly high, and a few people (or even none) are fully visible [11]. This definition is coherent with computer vision techniques that are used in these two scenarios: when dealing with groups, a common people detector can be used to analyse the scene, while when dealing with crowds, such techniques fail and specific algorithms need to be created in order to understand the scene.…”

Section: Crowd and Groupsmentioning

confidence: 99%

Texture-Based Crowd Detection and Localisation

Ghidoni¹,

Cielniak

Menegatti³

2013

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

This paper presents a crowd detection system based on texture analysis. The state-of-the-art techniques based on co-occurrence matrix have been revisited and a novel set of features proposed. These features provide a richer description of the co-occurrence matrix, and can be exploited to obtain stronger classification results, especially when smaller portions of the image are considered. This is extremely useful for crowd localisation: acquired images are divided into smaller regions in order to perform a classification on each one. A thorough evaluation of the proposed system on a real world data set is also presented: this validates the improvements in reliability of the crowd detection and localisation.

show abstract

“…Marana et al [26] analyzed four methods used in texture analysis and three classifiers to deal with the crowd density estimation problem. Regarding texture analysis, they compared the following four methods: gray-level dependence matrix, straight lines segments, Fourier analysis, and fractal dimension.…”

Section: Texture Analysismentioning

confidence: 99%