Abstract
In this work, models for re-identification of pedestrians, based on deep learning, are studied. The models considered here use only images of pedestrians and do not require additional spatiotemporal information that can vary in different instances. A modification of the investigated models is proposed, based on the normalization of feature maps. In the best case, an assessment of the accuracy of the model demonstrates a 10% improvement over unmodified models.
© 2020 Optical Society of America
PDF Article
More Like This
Blood species identification based on deep learning analysis of Raman spectra
Shan Huang, Peng Wang, Yubing Tian, Pengli Bai, DaQing Chen, Ce Wang, JianSheng Chen, ZhaoBang Liu, Jian Zheng, WenMing Yao, JianXin Li, and Jing Gao
Biomed. Opt. Express 10(12) 6129-6144 (2019)
Cited By
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription