Title: Stargan-based camera style transfer for person retrieval

Authors: Yuanyuan Wang; Zhijian Wang; Mingxin Jiang

Addresses: College of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian, China; College of Computer and Information, Hohai University, Nanjing, China ' College of Computer and Information, Hohai University, Nanjing, China ' College of Electronic Information Engineering, Huaiyin Institute of Technology, Huaian, China

Abstract: Person retrieval is also known as person re-identification (ReID) aiming to match person among cross cameras. Although the results of the person ReID have performed well in small datasets, the issues of the large number of identities in real scenarios or with more cameras have not been fully investigated. Being an image retrieval task under cross multi-cameras of intelligent video security, person ReID is influenced by the image style change caused by different camera illumination and view angles. The number of cameras in the latest datasets is increasing and more camera transfer models need to be trained. Traditional methods of generative adversarial network (GAN) can only handle transfer of two domains. To facilitate the research towards solving these problems, we use star generative adversarial networks (StarGAN) to transfer the image from one camera to another camera in the latest large benchmark datasets. We train multiple transfer models simultaneously, minimising the bias among different cameras. Label smooth regularisation (LSR) algorithm is utilised to mitigate the effects of noise in the model. We learn part-based descriptors from pedestrian samples to generate robust feature representation. Our work is competitive compared to the state-of-the-art.

Keywords: StarGAN; person retrieval; LSR.

DOI: 10.1504/IJICT.2020.105100

International Journal of Information and Communication Technology, 2020 Vol.16 No.1, pp.1 - 16

Received: 02 Nov 2018
Accepted: 24 Nov 2018
Published online: 13 Feb 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article