Back to articles
Volume: 31 | Article ID: art00019
Improving person re-identification performance by customized dataset and person detection
  DOI :  10.2352/ISSN.2470-1173.2019.11.IPAS-268  Published OnlineJanuary 2019

For person re-identification (re-ID), nearly all person re-ID algorithms use public person re-ID datasets, where these datasets all consist of predefined image crops containing a single person. Unfortunately, these image crops are not optimal for video analysis, so that the person detection becomes suboptimal and person re-ID obtains a lower performance score. In this work, several techniques are presented that customize the person images of a popular public person re-ID dataset. These techniques consist of customization algorithms based on postprocessing the person-detection bounding boxes using the original frames, resulting in several customized datasets to better facilitate person re-identification. We have evaluated five different ways for customization, based on widening the image crops, various aspect ratios and resolutions, and person instance segmentation. We have obtained a significant increase in performance with widened image crops, yielding a convincing performance increase of nearly 3% in the resulting Rank-1 score. Furthermore, when the applied random-cropping process is further optimized to this customization technique, an increase of even more than 4% is obtained. Both performance gains are a strong indication that any future person re-ID system may benefit from customizations based on the original video frames or from specializing the person detector.

Subject Areas :
Views 21
Downloads 1
 articleview.views 21
 articleview.downloads 1
  Cite this article 

Herman G.J Groot, Egor Bondarev, Peter H.N. de With, "Improving person re-identification performance by customized dataset and person detectionin Proc. IS&T Int’l. Symp. on Electronic Imaging: Image Processing: Algorithms and Systems XVII,  2019,  pp 268-1 - 268-9,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2019
Electronic Imaging
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA