Tampere University of Technology

TUTCRIS Research Portal

Pedestrian Counting With Back-Propagated Information and Target Drift Remedy

Research output: Contribution to journalArticleScientificpeer-review

Standard

Pedestrian Counting With Back-Propagated Information and Target Drift Remedy. / Chen, Ke; Zhang, Zhaoxiang.

In: IEEE Transactions on Systems, Man, and Cybernetics: Systems, Vol. 47, No. 4, 2017, p. 639-647.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Chen, K & Zhang, Z 2017, 'Pedestrian Counting With Back-Propagated Information and Target Drift Remedy', IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 47, no. 4, pp. 639-647. https://doi.org/10.1109/TSMC.2016.2618916

APA

Chen, K., & Zhang, Z. (2017). Pedestrian Counting With Back-Propagated Information and Target Drift Remedy. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 47(4), 639-647. https://doi.org/10.1109/TSMC.2016.2618916

Vancouver

Chen K, Zhang Z. Pedestrian Counting With Back-Propagated Information and Target Drift Remedy. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2017;47(4):639-647. https://doi.org/10.1109/TSMC.2016.2618916

Author

Chen, Ke ; Zhang, Zhaoxiang. / Pedestrian Counting With Back-Propagated Information and Target Drift Remedy. In: IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2017 ; Vol. 47, No. 4. pp. 639-647.

Bibtex - Download

@article{7c9ede1bde3d45a4958dba043ecd2889,
title = "Pedestrian Counting With Back-Propagated Information and Target Drift Remedy",
abstract = "Pedestrian density is one of the important factors in designing visual surveillance and intelligent transportation systems, but it is challenging to obtain accurate and robust estimates because of both inconsistent crowd patterns in the scenes and target drift caused by imbalanced data distribution. Most of existing global regression frameworks focus on the former challenge to improve the robustness of regression learning, but very few work concerns on mitigating the suffering from the latter one. This paper proposes a novel counting-by-regression framework to utilize the importance of training samples to improve the robustness against inconsistent feature-target relationship based on a recently-proposed learning paradigm--learning with privileged information. To this end, the concept of back-propagation is for the first time considered to select more informative samples contributed to robust fitting performance. Moreover, the direction of target drift along the continuously-changing target dimension is discovered by learning local classifiers under different situation of pedestrian density, which can thus be exploited in our algorithm to further boost the performance. Experimental evaluation on the public UCSD and shopping Mall benchmarks verifies that our approach significantly beats the state-of-the-art counting-by-regression frameworks.",
author = "Ke Chen and Zhaoxiang Zhang",
year = "2017",
doi = "10.1109/TSMC.2016.2618916",
language = "English",
volume = "47",
pages = "639--647",
journal = "IEEE Transactions on Systems, Man, and Cybernetics: Systems",
issn = "2168-2216",
publisher = "IEEE Advancing Technology for Humanity",
number = "4",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Pedestrian Counting With Back-Propagated Information and Target Drift Remedy

AU - Chen, Ke

AU - Zhang, Zhaoxiang

PY - 2017

Y1 - 2017

N2 - Pedestrian density is one of the important factors in designing visual surveillance and intelligent transportation systems, but it is challenging to obtain accurate and robust estimates because of both inconsistent crowd patterns in the scenes and target drift caused by imbalanced data distribution. Most of existing global regression frameworks focus on the former challenge to improve the robustness of regression learning, but very few work concerns on mitigating the suffering from the latter one. This paper proposes a novel counting-by-regression framework to utilize the importance of training samples to improve the robustness against inconsistent feature-target relationship based on a recently-proposed learning paradigm--learning with privileged information. To this end, the concept of back-propagation is for the first time considered to select more informative samples contributed to robust fitting performance. Moreover, the direction of target drift along the continuously-changing target dimension is discovered by learning local classifiers under different situation of pedestrian density, which can thus be exploited in our algorithm to further boost the performance. Experimental evaluation on the public UCSD and shopping Mall benchmarks verifies that our approach significantly beats the state-of-the-art counting-by-regression frameworks.

AB - Pedestrian density is one of the important factors in designing visual surveillance and intelligent transportation systems, but it is challenging to obtain accurate and robust estimates because of both inconsistent crowd patterns in the scenes and target drift caused by imbalanced data distribution. Most of existing global regression frameworks focus on the former challenge to improve the robustness of regression learning, but very few work concerns on mitigating the suffering from the latter one. This paper proposes a novel counting-by-regression framework to utilize the importance of training samples to improve the robustness against inconsistent feature-target relationship based on a recently-proposed learning paradigm--learning with privileged information. To this end, the concept of back-propagation is for the first time considered to select more informative samples contributed to robust fitting performance. Moreover, the direction of target drift along the continuously-changing target dimension is discovered by learning local classifiers under different situation of pedestrian density, which can thus be exploited in our algorithm to further boost the performance. Experimental evaluation on the public UCSD and shopping Mall benchmarks verifies that our approach significantly beats the state-of-the-art counting-by-regression frameworks.

U2 - 10.1109/TSMC.2016.2618916

DO - 10.1109/TSMC.2016.2618916

M3 - Article

VL - 47

SP - 639

EP - 647

JO - IEEE Transactions on Systems, Man, and Cybernetics: Systems

JF - IEEE Transactions on Systems, Man, and Cybernetics: Systems

SN - 2168-2216

IS - 4

ER -