Deep Person Re-identification Using Supervised Learning with Ranking Method




Moosavi, Shahla

Journal Title

Journal ISSN

Volume Title



In the present world packed with cameras at every corner the data generated from digital surveillance has become so substantial that it is impossible for human operators to make sense out of. Correspondingly, the intensification of machine vision algorithms that can invest through such data and return consequential perceptions has offered some solutions. Computer Vision techniques such as face detection/recognition and person re-identification has proven their worth into cameras and social medias. Person re-identification is correlating with images of the same person yet taken from different cameras or from the same camera in different incidents. Simply put, allocating a person in multi-camera setting. Us humans, we are easily able to re-identify others by easily descriptors based on the person's appearance (face, height, and build, clothing, hair style, walkingpattern, etc.) but this easy task, is more difficult for a machine to unscramble.


This item is available only to currently enrolled UTSA students, faculty or staff. To download, navigate to Log In in the top right-hand corner of this screen, then select Log in with my UTSA ID.


Deep Learning, Learning, Person, Ranking Method, Re-identification, Supervised



Electrical and Computer Engineering