TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Pedestrian Density Analysis in Public Scenes with Spatio-Temporal Tensor Features

Tutkimustuotosvertaisarvioitu

Standard

Pedestrian Density Analysis in Public Scenes with Spatio-Temporal Tensor Features. / Chen, Ke; Kämäräinen, Joni-Kristian.

julkaisussa: IEEE Transactions on Intelligent Transportation Systems, Vuosikerta 17, Nro 7, 2016, s. 1968 - 1977.

Tutkimustuotosvertaisarvioitu

Harvard

Chen, K & Kämäräinen, J-K 2016, 'Pedestrian Density Analysis in Public Scenes with Spatio-Temporal Tensor Features', IEEE Transactions on Intelligent Transportation Systems, Vuosikerta. 17, Nro 7, Sivut 1968 - 1977. https://doi.org/10.1109/TITS.2016.2516586

APA

Vancouver

Author

Chen, Ke ; Kämäräinen, Joni-Kristian. / Pedestrian Density Analysis in Public Scenes with Spatio-Temporal Tensor Features. Julkaisussa: IEEE Transactions on Intelligent Transportation Systems. 2016 ; Vuosikerta 17, Nro 7. Sivut 1968 - 1977.

Bibtex - Lataa

@article{26265346f15546dc914a5dda35aabd9d,
title = "Pedestrian Density Analysis in Public Scenes with Spatio-Temporal Tensor Features",
abstract = "Pedestrian density estimation is one of the key problems in intelligent transportation systems and has been widely applied to a number of applications in other fields of engineering. Counting-by-regression methods are more favorable for coping with such a problem owing to their robustness against interperson occlusion and relaxing the impractical requirement of a high video frame rate, compared to counting-by-detection and counting-by-clustering methods. However, imagery features in the existing counting-by-regression approaches are extracted from the whole region or spatially localized cells/pixels of each single video frame, which omits the unique motion patterns of the same pedestrians across the neighboring frames. In the light of this, this paper exploits a novel tensor-formed spatiotemporal feature representation and applies it in a multilinear regression learning framework, which can capture spatially distributed dynamic crowd patterns by discovering the latent multidimensional structural correlations of tensor features along both spatial (i.e., horizontal and vertical) and temporal dimensions. Extensive evaluation with the public UCSD and Shopping Mall benchmarks demonstrate superior performance of our approach to the state-of-the-art counting methods even when the surveillance data has a low frame rate.",
author = "Ke Chen and Joni-Kristian K{\"a}m{\"a}r{\"a}inen",
year = "2016",
doi = "10.1109/TITS.2016.2516586",
language = "English",
volume = "17",
pages = "1968 -- 1977",
journal = "IEEE Transactions on Intelligent Transportation Systems",
issn = "1524-9050",
publisher = "Institute of Electrical and Electronics Engineers",
number = "7",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Pedestrian Density Analysis in Public Scenes with Spatio-Temporal Tensor Features

AU - Chen, Ke

AU - Kämäräinen, Joni-Kristian

PY - 2016

Y1 - 2016

N2 - Pedestrian density estimation is one of the key problems in intelligent transportation systems and has been widely applied to a number of applications in other fields of engineering. Counting-by-regression methods are more favorable for coping with such a problem owing to their robustness against interperson occlusion and relaxing the impractical requirement of a high video frame rate, compared to counting-by-detection and counting-by-clustering methods. However, imagery features in the existing counting-by-regression approaches are extracted from the whole region or spatially localized cells/pixels of each single video frame, which omits the unique motion patterns of the same pedestrians across the neighboring frames. In the light of this, this paper exploits a novel tensor-formed spatiotemporal feature representation and applies it in a multilinear regression learning framework, which can capture spatially distributed dynamic crowd patterns by discovering the latent multidimensional structural correlations of tensor features along both spatial (i.e., horizontal and vertical) and temporal dimensions. Extensive evaluation with the public UCSD and Shopping Mall benchmarks demonstrate superior performance of our approach to the state-of-the-art counting methods even when the surveillance data has a low frame rate.

AB - Pedestrian density estimation is one of the key problems in intelligent transportation systems and has been widely applied to a number of applications in other fields of engineering. Counting-by-regression methods are more favorable for coping with such a problem owing to their robustness against interperson occlusion and relaxing the impractical requirement of a high video frame rate, compared to counting-by-detection and counting-by-clustering methods. However, imagery features in the existing counting-by-regression approaches are extracted from the whole region or spatially localized cells/pixels of each single video frame, which omits the unique motion patterns of the same pedestrians across the neighboring frames. In the light of this, this paper exploits a novel tensor-formed spatiotemporal feature representation and applies it in a multilinear regression learning framework, which can capture spatially distributed dynamic crowd patterns by discovering the latent multidimensional structural correlations of tensor features along both spatial (i.e., horizontal and vertical) and temporal dimensions. Extensive evaluation with the public UCSD and Shopping Mall benchmarks demonstrate superior performance of our approach to the state-of-the-art counting methods even when the surveillance data has a low frame rate.

U2 - 10.1109/TITS.2016.2516586

DO - 10.1109/TITS.2016.2516586

M3 - Article

VL - 17

SP - 1968

EP - 1977

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

SN - 1524-9050

IS - 7

ER -