Imperial College London
Dr Panagiota (Tania) Stathaki

Dr Panagiota (Tania) Stathaki

Faculty of Engineering, Department of Electrical and Electronic Engineering

Reader in Signal Processing
 
 
 
//

Contact

 

+44 (0)20 7594 6229t.stathaki Website

 
 
//

Assistant

 

Miss Vanessa Rodriguez-Gonzalez +44 (0)20 7594 6267

 
//

Location

 

812Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Liu:2020:10.1109/tip.2020.3038371,
author = {Liu, T and Luo, W and Ma, L and Huang, J-J and Stathaki, T and Dai, T},
doi = {10.1109/tip.2020.3038371},
journal = {IEEE Transactions on Image Processing},
pages = {754--766},
title = {Coupled network for robust pedestrian detection with gated multi-layer feature extraction and deformable occlusion handling},
url = {http://dx.doi.org/10.1109/tip.2020.3038371},
volume = {30},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, detecting ismall-scaled pedestrians and occluded pedestrians remains a challenging problem. In this paper, we propose a pedestrian detection method with a couple-network to simultaneously address these two issues. One of the sub-networks, the gated multi-layer feature extraction sub-network, aims to adaptively generate discriminative features for pedestrian candidates in order to robustly detect pedestrians with large variations on scale. The second sub-network targets on handling the occlusion problem of pedestrian detection by using deformable regional region of interest (RoI)-pooling. We investigate two different gate units for the gated sub-network, namely, the channel-wise gate unit and the spatio-wise gate unit, which can enhance the representation ability of the regional convolutional features among the channel dimensions or across the spatial domain, repetitively. Ablation studies have validated the effectiveness of both the proposed gated multi-layer feature extraction sub-network and the deformable occlusion handling sub-network. With the coupled framework, our proposed pedestrian detector achieves promising results on both two pedestrian datasets, especially on detecting small or occluded pedestrians. On the CityPersons dataset, the proposed detector achieves the lowest missing rates (i.e. 40.78% and 34.60%) on detecting small and occluded pedestrians, surpassing the second best comparison method by 6.0% and 5.87%, respectively.
AU  - Liu,T
AU  - Luo,W
AU  - Ma,L
AU  - Huang,J-J
AU  - Stathaki,T
AU  - Dai,T
DO  - 10.1109/tip.2020.3038371
EP  - 766
PY  - 2020///
SN  - 1057-7149
SP  - 754
TI  - Coupled network for robust pedestrian detection with gated multi-layer feature extraction and deformable occlusion handling
T2  - IEEE Transactions on Image Processing
UR  - http://dx.doi.org/10.1109/tip.2020.3038371
UR  - https://ieeexplore.ieee.org/document/9271862
VL  - 30
ER  -
Download