Training approach using the shallow model and hard triplet mining for person re‐identification. Issue 2 (1st February 2020)

• Record Type: Journal Article
• Authors: Choi, Hyunguk; Yow, Kin Choong; Jeon, Moongu
• Is Part Of: IET image processing. Volume 14:Issue 2(2020)
• Page Start: 256
• Page End: 266
• Publication Date: 2020-02-01
• Subjects: data mining -- sensor fusion -- learning (artificial intelligence) -- matrix algebra -- target tracking -- image matching -- neural nets -- cameras; shallow model -- hard triplet mining -- multitarget tracking -- nonoverlapping camera network -- person re‐identification problem -- backbone model -- fusion model -- mAP performance -- relationship matrices -- rank‐1 performance -- DukeMTMC‐reID dataset -- Market1501 dataset; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0334
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Multi‐target tracking in a non‐overlapping camera network is an active research field, and one of the important problems in it is the person re‐identification problem. In this study, the authors propose an approach to improve the performance of the backbone model in the person re‐identification. Their approach focuses on training a fusion model with a shallow model and making hard triplets with relationship matrices quickly and efficiently. The proposed approach is simple, but it improves the performance of the backbone. In addition, the hard triplet mining in their process is much faster than the conventional approach. Experimental evaluation shows that the proposed approach can improve the performances of the backbone model. The proposed approach improves rank‐1 and mean average precision (mAP) performance by more than 12.54 and 15.44%, respectively, over the backbone models in the Market1501 and DukeMTMC‐reID dataset. The approach also achieves competitive performances compared with state‐of‐the‐art approaches.