A Hierarchical Scheme for Video-Based Person Re-identification Using Lightweight PCANet and Handcrafted LOMO Features

LI Youjiao; ZHUO Li; LI Jiafeng; ZHANG Jing

doi:10.1049/cje.2021.02.001

Volume 30 Issue 2

Apr. 2021

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2021 > 30(2): 289-295

LI Youjiao, ZHUO Li, LI Jiafeng, et al., “A Hierarchical Scheme for Video-Based Person Re-identification Using Lightweight PCANet and Handcrafted LOMO Features,” Chinese Journal of Electronics, vol. 30, no. 2, pp. 289-295, 2021, doi: 10.1049/cje.2021.02.001

Citation:

LI Youjiao, ZHUO Li, LI Jiafeng, et al., “A Hierarchical Scheme for Video-Based Person Re-identification Using Lightweight PCANet and Handcrafted LOMO Features,” Chinese Journal of Electronics, vol. 30, no. 2, pp. 289-295, 2021, doi: 10.1049/cje.2021.02.001

Citation:

PDF( 6351 KB)

A Hierarchical Scheme for Video-Based Person Re-identification Using Lightweight PCANet and Handcrafted LOMO Features

doi: 10.1049/cje.2021.02.001

LI Youjiao^{1, 2, 3
,},
ZHUO Li^{1, 2
,
,},
LI Jiafeng^{1, 2
,},
ZHANG Jing^{1, 2
,}

1.
Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing 100124, China
2.
Faculty of Information Technology, College of Micro-electronics, Beijing University of Technology, Beijing 100124, China
3.
College of Computer Science and Technology, Shandong University of Technology, Zibo 255000, China

Funds:

the National Natural Science Foundation of China 61531006

the National Natural Science Foundation of China 61602018

the National Natural Science Foundation of China 61701011

Beijing Municipal Natural Science Foundation Cooperation Beijing Education Committee 201910005007

Beijing Municipal Natural Science Foundation Cooperation Beijing Education Committee KZ201810005002

More Information

Author Bio:
LI Youjiao   is a Ph., D. candidate at the Faculty of Information Technology, Beijing University of Technology. He is now a lecturer of Shandong University of Technology. His research interest covers computer vision and deep learning. (Email: liyoujiao@emails.bjut.edu.cn)

LI Jiafeng   is a assistant professor at Signal & Information Processing Laboratory, Beijing University of Technology. He was in the Department of Neurosurgery, University of Pittsburgh as a visiting scholar from 2014 to 2015. His research interest covers computer vision, image enhancement, and image restoration. (Email: lijiafeng@bjut.edu.cn)

ZHANG Jing  received her Ph.D. degree from Beijing University of Technology in 2008. She is a professor at the Beijing University of Technology. She is also a research scholar in the Department of Computer Science, the University of Texas at San Antonio. She is the author of more than 50 journal papers and has written three book chapters. Her current research interests include image processing, image recognition, and image retrieval. (Email: zhj@bjut.edu.cn)
Corresponding author: ZHUO Li (corresponding author) is a professor at Beijing University of Technology. She received her bachelor degree in radio technology from the University of Electronic Science and Technology in 1992, master degree in signal & information processing from the Southeast University in 1998, and Ph.D. degree in pattern recognition and intellectual system from Beijing University of Technology in 2004. Her research interest covers image/video coding and transmission, multimedia content analysis, and multimedia information security. Corresponding author of this paper. (Email: zhuoli@bjut.edu.cn)
Received Date: 2019-06-19
Accepted Date: 2019-08-01
Publish Date: 2021-03-01

Abstract

Abstract

A two-level hierarchical scheme for videobased person re-identification (re-id) is presented, with the aim of learning a pedestrian appearance model through more complete walking cycle extraction. Specifically, given a video with consecutive frames, the objective of the first level is to detect the key frame with lightweight Convolutional neural network (CNN) of PCANet to reflect the summary of the video content. At the second level, on the basis of the detected key frame, the pedestrian walking cycle is extracted from the long video sequence. Moreover, local features of Local maximal occurrence (LOMO) of the walking cycle are extracted to represent the pedestrian' s appearance information. In contrast to the existing walking-cycle-based person re-id approaches, the proposed scheme relaxes the limit on step number for a walking cycle, thus making it flexible and less affected by noisy frames. Experiments are conducted on two benchmark datasets: PRID 2011 and iLIDS-VID. The experimental results demonstrate that our proposed scheme outperforms the six state-of-art video-based re-id methods, and is more robust to the severe video noises and variations in pose, lighting, and camera viewpoint.
- Video-based person re-identification,
- Convolutional neural network,
- Key frame detection,
- Walking cycle extraction

FullText(HTML)

References(18)

References

[1]	F. Tan, et al., "Person re-identification across multiple non-overlapping cameras by grouping similarity comparison model", Chinese Journal of Electronics, Vol. 26, No. 5, pp. 905–911, 2017. doi: 10.1049/cje.2016.08.007
[2]	Y. Li, et al., "Video-based person re-identification by deep feature guided pooling", Proc. of IEEE Computer Vision and Pattern Recognition Workshops, USA, 2017.
[3]	L. Zheng, et al., "Mars: A video benchmark for large-scale person re-identification", Proc. of IEEE European Conference on Computer Vision, 2016. doi: 10.1007%2F978-3-319-46466-4_52
[4]	W. Zhang, et al., "Video-based pedestrian re-identification by adaptive spatio-temporal appearance model", IEEE Transactions on Image Processing, Vol. 99, 2017. http://ieeexplore.ieee.org/document/7859378
[5]	T. Chang, et al., "Pcanet: A Simple deep learning baseline for image classification?", IEEE Transactions on Image Processing, Vol. 24, No. 12, pp. 5017–5032, 2015. doi: 10.1109/TIP.2015.2475625
[6]	S. Liao, et al., "Person re-identification by local maximal occurrence representation and metric learning", Proc. of IEEE Computer Vision and Pattern Recognition, USA, 2015.
[7]	L. Fei, et al., "Training restricted boltzmann machine using gradient fixing based algorithm", Chinese Journal of Electronics, Vol. 27, No. 4, pp. 694–703, 2018. doi: 10.1049/cje.2018.05.007
[8]	L. Wu, et al., "A multi-semantics classification method based on deep learning for incredible messages on social media", Chinese Journal of Electronics, Vol. 28, No. 4, pp. 754–763, 2019. doi: 10.1049/cje.2019.05.002
[9]	J. Li, et al., "Computer-assisted detection of colonic polyps using improved faster R-CNN", Chinese Journal of Electronics, Vol. 28, No. 4, pp. 718–724, 2019. doi: 10.1049/cje.2019.03.005
[10]	F. Wang, et al., "Deep auto-encoded clustering algorithm for community detection in complex networks", Chinese Journal of Electronics, Vol. 28, No. 3, pp. 489–496, 2019. doi: 10.1049/cje.2019.03.019
[11]	G. Cheng, et al., "Using highway connections to enable deep small-footprint Lstm-Rnns for speech recognition", Chinese Journal of Electronics, Vol. 28, No. 1, pp. 107–112, 2019. doi: 10.1049/cje.2018.11.008
[12]	N. McLaughlin, et al., "Recurrent convolutional network for video-based person re-identification", Proc. of IEEE Computer Vision and Pattern Recognition, USA, 2016.
[13]	J. You, et al., "Top-push video-based person re-identification", Proc. of IEEE Computer Vision and Pattern Recognition, USA, 2016.
[14]	T. Wang, et al., "Person re-identification by video ranking", Proc. of IEEE European Conference on Computer Vision, 2014. doi: 10.1007/978-3-319-10593-2_45
[15]	F. Gao, et al., "Automatic change detection in synthetic aperture radar images based on pcanet", IEEE Geoscience & Remote Sensing Letters, Vol. 99, pp. 1–5, 2016. http://ieeexplore.ieee.org/document/7589111/
[16]	M. Hirzer, et al., "Person re-identification by descriptive and discriminative classification", Proc. of Scandinavian conference on Image analysis, 2011. http://www.zentralblatt-math.org/ioport/en/?q=an%3A05958925
[17]	M. Ye, et al., "Robust anchor embedding for unsupervised video person re-identification in the wild", Proc. of IEEE European Conference on Computer Vision, 2018. doi: 10.1007/978-3-030-01234-2_11
[18]	F. Ma, et al., "Multi-view coupled dictionary learning for person re-identification", Neurocomputing, 2018. http://www.sciencedirect.com/science/article/pii/S0925231218312797