A Study on Deep Convolutional Neural Network Based Approaches for Person Re-identification

• Published in: Pattern Recognition and Machine Intelligence Vol. 10597; pp. 543 - 548
• Main Authors: Chahar, Harendra, Nain, Neeta
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2017; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Convolutional neural network; Person re-identification
• ISBN: 3319698990; 9783319698991
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-69900-4_69

Person re-identification is a process to identify the same person again viewed by disjoint field of view of cameras. It is a challenging problem due to visual ambiguity in a person’s appearance across different camera views. These difficulties are often compounded by low resolution surveillance images, occlusion, background clutter and varying lighting conditions. In recent years, person re-identification community obtained large size of annotated datasets and deep learning architecture based approaches have obtained significant improvement in the accuracy over the years as compared to hand-crafted approaches. In this survey paper, we have classified deep learning based approaches into two categories, i.e., image-based and video-based person re-identification. We have also presented the currently ongoing under developing works, issues and future directions for person re-identification.