%T Investigating the Impact of Illumination and Viewpoint Variations on Transformer-based Person Re-Identification
%A T.I. Amosa
%A P. Sebastian
%A L.I. Izhar
%A O. Ibrahim
%I Institute of Electrical and Electronics Engineers Inc.
%P 130-135
%K Computer vision; Deep learning, Deep learning; Identification modeling; Illumination-adaptive; Large-scale datasets; Performance; Person re identifications; Re identifications; Synthetic datasets; Visual; Visual condition, Large dataset
%X Variations in visual factors such as illumination, viewpoint, resolution, background, pose, and so on are commonly regarded as significant issues in object re-identification (re-ID). Despite widespread recognition of their importance in determining the performance of an object re-ID model, not enough attention is paid to how these factors affect re-ID systems. One of the major impediments to investigating how these factors affect the performance of re-ID models is the lack of datasets with unbiased distribution of these difficult visual conditions. To make up for the lack of large-scale datasets with a balanced distribution of such photometric and geometric transforms, recent studies suggest using game engines to generate synthetic datasets. This study proposes a quantitative investigation of the impact of two critical visual factors: illumination and Tranfomer-based re-ID models on synthetic dataset. © 2022 IEEE.
%O cited By 0; Conference of 2022 International Conference on Future Trends in Smart Communities, ICFTSC 2022 ; Conference Date: 1 December 2022 Through 2 December 2022; Conference Code:186671
%J 2022 International Conference on Future Trends in Smart Communities, ICFTSC 2022
%L scholars17241
%D 2022
%R 10.1109/ICFTSC57269.2022.10039913