A novel crowd density estimation technique using local binary pattern and Gabor features

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Crowd density estimation is an effective automated video surveillance technique to ensure crowd safety. In spite of various efforts being taken to estimate crowd density, it remains a challenging task. This paper proposes a new texture feature-based approach for the estimation of crowd density where two efficient texture features namely Local Binary Pattern (LBP) and Gabor Filter are used. The LBP features are computed using an extended version which reduces the dimension of conventional LBP and the Gabor features are extracted after convolving the original image with a bank of Log-Gabor filters computed at different scales and orientations. Finally, the LBP and Gabor features are concatenated to yield the final feature vector which is used to train a multi-class Support Vector Machine (SVM) classifier. The proposed technique is evaluated on the benchmarked PETS 2009 dataset, and a maximum accuracy of 90.3% is obtained for the proposed texture combination. The experimental results show the better performance of the proposed approach as compared to other conventional techniques.

Original languageEnglish
Title of host publication2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538629390
DOIs
Publication statusPublished - 20-10-2017
Event14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017 - Lecce, Italy
Duration: 29-08-201701-09-2017

Conference

Conference14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017
CountryItaly
CityLecce
Period29-08-1701-09-17

Fingerprint

Gabor filters
Textures
Support vector machines
Classifiers

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Pai, A. K., Karunakar, A. K., & Raghavendra, U. (2017). A novel crowd density estimation technique using local binary pattern and Gabor features. In 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017 [8078556] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AVSS.2017.8078556
Pai, Abhilash K. ; Karunakar, A. K. ; Raghavendra, U. / A novel crowd density estimation technique using local binary pattern and Gabor features. 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{aaa62061891a4151a98330a5e59a75ff,
title = "A novel crowd density estimation technique using local binary pattern and Gabor features",
abstract = "Crowd density estimation is an effective automated video surveillance technique to ensure crowd safety. In spite of various efforts being taken to estimate crowd density, it remains a challenging task. This paper proposes a new texture feature-based approach for the estimation of crowd density where two efficient texture features namely Local Binary Pattern (LBP) and Gabor Filter are used. The LBP features are computed using an extended version which reduces the dimension of conventional LBP and the Gabor features are extracted after convolving the original image with a bank of Log-Gabor filters computed at different scales and orientations. Finally, the LBP and Gabor features are concatenated to yield the final feature vector which is used to train a multi-class Support Vector Machine (SVM) classifier. The proposed technique is evaluated on the benchmarked PETS 2009 dataset, and a maximum accuracy of 90.3{\%} is obtained for the proposed texture combination. The experimental results show the better performance of the proposed approach as compared to other conventional techniques.",
author = "Pai, {Abhilash K.} and Karunakar, {A. K.} and U. Raghavendra",
year = "2017",
month = "10",
day = "20",
doi = "10.1109/AVSS.2017.8078556",
language = "English",
booktitle = "2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Pai, AK, Karunakar, AK & Raghavendra, U 2017, A novel crowd density estimation technique using local binary pattern and Gabor features. in 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017., 8078556, Institute of Electrical and Electronics Engineers Inc., 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017, Lecce, Italy, 29-08-17. https://doi.org/10.1109/AVSS.2017.8078556

A novel crowd density estimation technique using local binary pattern and Gabor features. / Pai, Abhilash K.; Karunakar, A. K.; Raghavendra, U.

2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 8078556.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A novel crowd density estimation technique using local binary pattern and Gabor features

AU - Pai, Abhilash K.

AU - Karunakar, A. K.

AU - Raghavendra, U.

PY - 2017/10/20

Y1 - 2017/10/20

N2 - Crowd density estimation is an effective automated video surveillance technique to ensure crowd safety. In spite of various efforts being taken to estimate crowd density, it remains a challenging task. This paper proposes a new texture feature-based approach for the estimation of crowd density where two efficient texture features namely Local Binary Pattern (LBP) and Gabor Filter are used. The LBP features are computed using an extended version which reduces the dimension of conventional LBP and the Gabor features are extracted after convolving the original image with a bank of Log-Gabor filters computed at different scales and orientations. Finally, the LBP and Gabor features are concatenated to yield the final feature vector which is used to train a multi-class Support Vector Machine (SVM) classifier. The proposed technique is evaluated on the benchmarked PETS 2009 dataset, and a maximum accuracy of 90.3% is obtained for the proposed texture combination. The experimental results show the better performance of the proposed approach as compared to other conventional techniques.

AB - Crowd density estimation is an effective automated video surveillance technique to ensure crowd safety. In spite of various efforts being taken to estimate crowd density, it remains a challenging task. This paper proposes a new texture feature-based approach for the estimation of crowd density where two efficient texture features namely Local Binary Pattern (LBP) and Gabor Filter are used. The LBP features are computed using an extended version which reduces the dimension of conventional LBP and the Gabor features are extracted after convolving the original image with a bank of Log-Gabor filters computed at different scales and orientations. Finally, the LBP and Gabor features are concatenated to yield the final feature vector which is used to train a multi-class Support Vector Machine (SVM) classifier. The proposed technique is evaluated on the benchmarked PETS 2009 dataset, and a maximum accuracy of 90.3% is obtained for the proposed texture combination. The experimental results show the better performance of the proposed approach as compared to other conventional techniques.

UR - http://www.scopus.com/inward/record.url?scp=85039919261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039919261&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2017.8078556

DO - 10.1109/AVSS.2017.8078556

M3 - Conference contribution

AN - SCOPUS:85039919261

BT - 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Pai AK, Karunakar AK, Raghavendra U. A novel crowd density estimation technique using local binary pattern and Gabor features. In 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. 8078556 https://doi.org/10.1109/AVSS.2017.8078556