TY - JOUR
T1 - Two-stream multirate recurrent neural network for video-based pedestrian reidentification
AU - Zeng, Zhiqiang
AU - Li, Zhihui
AU - Cheng, De
AU - Zhang, Huaxiang
AU - Zhan, Kun
AU - Yang, Yi
PY - 2018/7
Y1 - 2018/7
N2 - Video-based pedestrian reidentification is an emerging task in video surveillance and is closely related to several real-world applications. Its goal is to match pedestrians across multiple nonoverlapping network cameras. Despite the recent effort, the performance of pedestrian reidentification needs further improvement. Hence, we propose a novel two-stream multirate recurrent neural network for video-based pedestrian reidentification with two inherent advantages: First, capturing the static spatial and temporal information; Second,Author: Figure II is not cited in the text. Please cite it at the appropriate place. dealing with motion speed variance. Given video sequences of pedestrians, we start with extracting spatial and motion features using two different deep neural networks. Then, we explore the feature correlation which results in a regularized fusion network integrating the two aforementioned networks. Considering that pedestrians, sometimes even the same pedestrian, move in different speeds across different camera views, we extend our approach by feeding the two networks into a multirate recurrent network to exploit the temporal correlations. Extensive experiments have been conducted on two real-world video-based pedestrian reidentification benchmarks: iLIDS-VID and PRID 2011 datasets. The experimental results confirm the efficacy of the proposed method. Our code will be released upon acceptance.
AB - Video-based pedestrian reidentification is an emerging task in video surveillance and is closely related to several real-world applications. Its goal is to match pedestrians across multiple nonoverlapping network cameras. Despite the recent effort, the performance of pedestrian reidentification needs further improvement. Hence, we propose a novel two-stream multirate recurrent neural network for video-based pedestrian reidentification with two inherent advantages: First, capturing the static spatial and temporal information; Second,Author: Figure II is not cited in the text. Please cite it at the appropriate place. dealing with motion speed variance. Given video sequences of pedestrians, we start with extracting spatial and motion features using two different deep neural networks. Then, we explore the feature correlation which results in a regularized fusion network integrating the two aforementioned networks. Considering that pedestrians, sometimes even the same pedestrian, move in different speeds across different camera views, we extend our approach by feeding the two networks into a multirate recurrent network to exploit the temporal correlations. Extensive experiments have been conducted on two real-world video-based pedestrian reidentification benchmarks: iLIDS-VID and PRID 2011 datasets. The experimental results confirm the efficacy of the proposed method. Our code will be released upon acceptance.
KW - Person reidentification
KW - recurrent neural networks
KW - video surveillance
UR - http://www.scopus.com/inward/record.url?scp=85032744122&partnerID=8YFLogxK
U2 - 10.1109/TII.2017.2767557
DO - 10.1109/TII.2017.2767557
M3 - Article
AN - SCOPUS:85032744122
VL - 14
SP - 3179
EP - 3186
JO - IEEE Transactions on Industrial Informatics
JF - IEEE Transactions on Industrial Informatics
SN - 1551-3203
IS - 7
ER -