IEICE TRANSACTIONS on Information
Dual-Task Integrated Network for Fast Pedestrian Detection in Crowded Scenes
Summary :
Pedestrian detection is a critical problem in computer vision with significant impact on many real-world applications. In this paper, we introduce an fast dual-task pedestrian detector with integrated segmentation context (DTISC) which predicts pedestrian location as well as its pixel-wise segmentation. The proposed network has three branches where two main branches can independently complete their tasks while useful representations from each task are shared between two branches via the integration branch. Each branch is based on fully convolutional network and is proven effective in its own task. We optimize the detection and segmentation branch on separate ground truths. With reasonable connections, the shared features introduce additional supervision and clues into each branch. Consequently, the two branches are infused at feature spaces increasing their robustness and comprehensiveness. Extensive experiments on pedestrian detection and segmentation benchmarks demonstrate that our joint model improves the performance of detection and segmentation against state-of-the-art algorithms.
- Publication
- IEICE TRANSACTIONS on Information Vol.E103-D No.6 pp.1371-1379
- Publication Date
- 2020/06/01
- Publicized
- 2020/03/19
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2019EDP7285
- Type of Manuscript
- PAPER
- Category
- Artificial Intelligence, Data Mining
Authors
Chen CHEN
National University of Defense Technology
Huaxin XIAO
National University of Defense Technology
Yu LIU
National University of Defense Technology
Maojun ZHANG
National University of Defense Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Chen CHEN, Huaxin XIAO, Yu LIU, Maojun ZHANG, "Dual-Task Integrated Network for Fast Pedestrian Detection in Crowded Scenes" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 6, pp. 1371-1379, June 2020, doi: 10.1587/transinf.2019EDP7285.
Abstract: Pedestrian detection is a critical problem in computer vision with significant impact on many real-world applications. In this paper, we introduce an fast dual-task pedestrian detector with integrated segmentation context (DTISC) which predicts pedestrian location as well as its pixel-wise segmentation. The proposed network has three branches where two main branches can independently complete their tasks while useful representations from each task are shared between two branches via the integration branch. Each branch is based on fully convolutional network and is proven effective in its own task. We optimize the detection and segmentation branch on separate ground truths. With reasonable connections, the shared features introduce additional supervision and clues into each branch. Consequently, the two branches are infused at feature spaces increasing their robustness and comprehensiveness. Extensive experiments on pedestrian detection and segmentation benchmarks demonstrate that our joint model improves the performance of detection and segmentation against state-of-the-art algorithms.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7285/_p
Copy
@ARTICLE{e103-d_6_1371,
author={Chen CHEN, Huaxin XIAO, Yu LIU, Maojun ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Dual-Task Integrated Network for Fast Pedestrian Detection in Crowded Scenes},
year={2020},
volume={E103-D},
number={6},
pages={1371-1379},
abstract={Pedestrian detection is a critical problem in computer vision with significant impact on many real-world applications. In this paper, we introduce an fast dual-task pedestrian detector with integrated segmentation context (DTISC) which predicts pedestrian location as well as its pixel-wise segmentation. The proposed network has three branches where two main branches can independently complete their tasks while useful representations from each task are shared between two branches via the integration branch. Each branch is based on fully convolutional network and is proven effective in its own task. We optimize the detection and segmentation branch on separate ground truths. With reasonable connections, the shared features introduce additional supervision and clues into each branch. Consequently, the two branches are infused at feature spaces increasing their robustness and comprehensiveness. Extensive experiments on pedestrian detection and segmentation benchmarks demonstrate that our joint model improves the performance of detection and segmentation against state-of-the-art algorithms.},
keywords={},
doi={10.1587/transinf.2019EDP7285},
ISSN={1745-1361},
month={June},}
Copy
TY - JOUR
TI - Dual-Task Integrated Network for Fast Pedestrian Detection in Crowded Scenes
T2 - IEICE TRANSACTIONS on Information
SP - 1371
EP - 1379
AU - Chen CHEN
AU - Huaxin XIAO
AU - Yu LIU
AU - Maojun ZHANG
PY - 2020
DO - 10.1587/transinf.2019EDP7285
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2020
AB - Pedestrian detection is a critical problem in computer vision with significant impact on many real-world applications. In this paper, we introduce an fast dual-task pedestrian detector with integrated segmentation context (DTISC) which predicts pedestrian location as well as its pixel-wise segmentation. The proposed network has three branches where two main branches can independently complete their tasks while useful representations from each task are shared between two branches via the integration branch. Each branch is based on fully convolutional network and is proven effective in its own task. We optimize the detection and segmentation branch on separate ground truths. With reasonable connections, the shared features introduce additional supervision and clues into each branch. Consequently, the two branches are infused at feature spaces increasing their robustness and comprehensiveness. Extensive experiments on pedestrian detection and segmentation benchmarks demonstrate that our joint model improves the performance of detection and segmentation against state-of-the-art algorithms.
ER -
English
