Home > Research > Publications & Outputs > Distant Pedestrian Detection in the Wild using ...

Electronic data

  • IJCNN_July

    Rights statement: ©2019 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 1.38 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks. / Dinakaran, R.; Easom, P.; Zhang, L. et al.
2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019. 8851859.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Dinakaran, R, Easom, P, Zhang, L, Bouridane, A, Jiang, R & Edirisinghe, E 2019, Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks. in 2019 International Joint Conference on Neural Networks (IJCNN)., 8851859, IEEE. https://doi.org/10.1109/IJCNN.2019.8851859

APA

Dinakaran, R., Easom, P., Zhang, L., Bouridane, A., Jiang, R., & Edirisinghe, E. (2019). Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks. In 2019 International Joint Conference on Neural Networks (IJCNN) Article 8851859 IEEE. https://doi.org/10.1109/IJCNN.2019.8851859

Vancouver

Dinakaran R, Easom P, Zhang L, Bouridane A, Jiang R, Edirisinghe E. Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks. In 2019 International Joint Conference on Neural Networks (IJCNN). IEEE. 2019. 8851859 Epub 2019 Jul 19. doi: 10.1109/IJCNN.2019.8851859

Author

Dinakaran, R. ; Easom, P. ; Zhang, L. et al. / Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks. 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019.

Bibtex

@inproceedings{6e4ed1fdb68c434c998701f8250df818,
title = "Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks",
abstract = "In this work, we examine the feasibility of applying Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) as data-processing technique to handle with the challenge of pedestrian detection in the wild. Specifically, we attempted to use in-fill completion to generate random transformations of images with missing pixels to expand existing labelled datasets. In our work, GAN's been trained intensively on low resolution images, in order to neutralize the challenges of the pedestrian detection in the wild, and considered humans, and few other classes for detection in smart cities. The object detector experiment performed by training GAN model along with SSD provided a substantial improvement in the results. This approach presents a very interesting overview in the current state of art on GAN networks for object detection. We used Canadian Institute for Advanced Research (CIFAR), Caltech, KITTI data set for training and testing the network under different resolutions and the experimental results with comparison been showed between DCGAN cascaded with SSD and SSD itself.",
author = "R. Dinakaran and P. Easom and L. Zhang and A. Bouridane and R. Jiang and E. Edirisinghe",
note = "{\textcopyright}2019 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. ",
year = "2019",
month = sep,
day = "30",
doi = "10.1109/IJCNN.2019.8851859",
language = "English",
isbn = "9781728119861",
booktitle = "2019 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks

AU - Dinakaran, R.

AU - Easom, P.

AU - Zhang, L.

AU - Bouridane, A.

AU - Jiang, R.

AU - Edirisinghe, E.

N1 - ©2019 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2019/9/30

Y1 - 2019/9/30

N2 - In this work, we examine the feasibility of applying Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) as data-processing technique to handle with the challenge of pedestrian detection in the wild. Specifically, we attempted to use in-fill completion to generate random transformations of images with missing pixels to expand existing labelled datasets. In our work, GAN's been trained intensively on low resolution images, in order to neutralize the challenges of the pedestrian detection in the wild, and considered humans, and few other classes for detection in smart cities. The object detector experiment performed by training GAN model along with SSD provided a substantial improvement in the results. This approach presents a very interesting overview in the current state of art on GAN networks for object detection. We used Canadian Institute for Advanced Research (CIFAR), Caltech, KITTI data set for training and testing the network under different resolutions and the experimental results with comparison been showed between DCGAN cascaded with SSD and SSD itself.

AB - In this work, we examine the feasibility of applying Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) as data-processing technique to handle with the challenge of pedestrian detection in the wild. Specifically, we attempted to use in-fill completion to generate random transformations of images with missing pixels to expand existing labelled datasets. In our work, GAN's been trained intensively on low resolution images, in order to neutralize the challenges of the pedestrian detection in the wild, and considered humans, and few other classes for detection in smart cities. The object detector experiment performed by training GAN model along with SSD provided a substantial improvement in the results. This approach presents a very interesting overview in the current state of art on GAN networks for object detection. We used Canadian Institute for Advanced Research (CIFAR), Caltech, KITTI data set for training and testing the network under different resolutions and the experimental results with comparison been showed between DCGAN cascaded with SSD and SSD itself.

U2 - 10.1109/IJCNN.2019.8851859

DO - 10.1109/IJCNN.2019.8851859

M3 - Conference contribution/Paper

SN - 9781728119861

BT - 2019 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

ER -