Loading...

Analysis of People Appearance Variation in Multi-Camera Networks

Moradipour, Mostafa | 2020

372 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53592 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Behroozi, Hamid; Mohammadzadeh, Narges Hoda
  7. Abstract:
  8. Analysis of people appearance variation in multi-camera networks for person re-identification or person retrieval is a very challenging problem due to the many intra-class variations between different cameras. Like any problem in the field of machine vision, it is generally divided into two parts. The first part is feature extraction and the second part is feature matching for person retrieval. So far, various methods have been proposed for the extraction of discriminative features, which are generally divided into three categories: stripe-based, patch-based, and body-based methods. However, methods based on stripes, although simpler, have performed better due to their greater compatibility with the vertical position of the person in the image. Recently, with the use of deep neural networks, significant progress has been made in this area. Therefore, in this study, by using deep networks and applying a strip approach in the feature space, using a graph network to combine features and collecting and applying various network training tricks, we achieved great performance in image and video person re-identification, respectively on Market1501 and MARS datasets
  9. Keywords:
  10. Feature Matching ; Graph Neural Network ; Machine Learning ; Multicamera Tracking ; Person Reidentification ; Stripe Based Divided ; Intraclass Variations

 Digital Object List

 Bookmark

No TOC