Loading...

An Enhanced Algorithm for Concealed Object Detection in Millimeter Wave Imaging

Rezaei, Vahid | 2020

567 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 52892 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Shabany, Mahdi; Kavehvash, Zahra
  7. Abstract:
  8. One of the most important alternative technologies in the field of security monitoring is millimeter-wave imaging technology, which is a good alternative both for performance and cost-effectiveness. Conventional security monitoring techniques use optical images or metal detectors to control people in crowded, sensitive places, but with the help of electromagnetic waves, these technologies can be obtained. This way, metal and non-metallic objects hidden inside clothing, bags or shoes can also be detected that are not identifiable by conventional security-control methods. This thesis examines the implementation of an improved algorithm for automatic detection of objects in millimeter-wave images to search for individuals and their associated objects. Due to issues such as privacy and ethical issues, automatic detection of prohibited objects is of paramount importance. In this thesis, new methods have been used to automatically detect the object and improve millimeter-wave images visibility. The basis of the methods used is deep Convolutional Neural Networks, which in this thesis will specifically consider both multi-labels networks and Region-based Convolutional Neural Network, Autoencoder Network for this purpose
  9. Keywords:
  10. Convolutional Neural Network ; Autoencoder ; Millimeter-Wave Imaging ; Region-Based Discrete Wavelet ; Multiclass Network ; Region-Based Convolutional Neural Network

 Digital Object List

 Bookmark

No TOC