RECURRENT CONVOLUTIONAL NETWORK FOR VIDEO-BASED PERSON RE-IDENTIFICATION

Network Architecture for our proposed video re-identification system

Abstract

In this paper we propose a novel recurrent neural network architecture for video-based person re-identification. Given the video sequence of a person, features are extracted from each frame using a convolutional neural network that incorporates a recurrent final layer, which allows information to flow between time-steps. The features from all time-steps are then combined using temporal pooling to give an overall appearance feature for the complete sequence. The convolutional network, recurrent layer, and temporal pooling layer, are jointly trained to act as a feature extractor for video-based re-identification using a Siamese network architecture. Our approach makes use of colour and optical flow information in order to capture appearance and motion information which is useful for video re-identification. Experiments are conducted on the iLIDS-VID and PRID-2011 datasets to show that this approach outperforms existing methods of video-based re-identification.

The structure of the CNN in our network architecture

 

Results

Video re-identification results for our system tested on the PRID 2011 and iLIDS-VID datasets.

 

Citation

Recurrent Convolutional Network for Video-based Person Re-Identification

N McLaughlin, J Martinez Del Rincon, P Miller

CVPR 2016

  

bibtex

@INPROCEEDINGS{Mclaughlin2016,

author={McLaughlin, N. and Martinez del Rincon, J. and Miller, P.},

booktitle={CVPR},

title={Recurrent Convolutional Network for Video-based Person Re-Identification},

year={2016},

month={Jul},

}

Additional

Poster