Resumen de Person re-identification by Siamese Network
Newlin Shebiah R, Arivazhagan S, Amrith S G, Adarsh S
The re-identification of individuals aims to retrieve persons across multiple non-overlapping cameras. With the advancement of deep learning features and the increase in the number of surveillance videos, the computer vision community has experienced significant progress. However, person re-identification is still faced with various challenges such as low resolution images and pose variations. To overcome these challenges, state-of-the-art algorithms for person re-identification are supported by convolutional neural networks. This paper proposes the use of a Siamese network, which is a neural architecture that takes a pair of images or videos as input and predicts the similarity or dissimilarity of a person across two cameras. The output includes the prediction of similar and dissimilar persons along with their prediction scores. The proposed method was evaluated using iLIDS-VID and PRID 2011 datasets, and achieved recognition accuracy of 79.52% and 85.82%, respectively. These results demonstrate the effectiveness of the Siamese network for person re-identification tasks. Overall, this study contributes to the ongoing research on improving the accuracy of person re-identification across multiple cameras in surveillance videos.
