• Home
  • Search
  • Unifying Convolution and Transformer for Efficient Concealed Object Detection in Passive Millimeter-Wave Images
  • Cite Icon29
  • https://doi.org/10.1109/tcsvt.2023.3234311Copy DOI Icon

Unifying Convolution and Transformer for Efficient Concealed Object Detection in Passive Millimeter-Wave Images

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Passive millimeter-wave (PMMW) imaging is an ideal technique for concealed object detection in non-contact security inspection scenarios, and has been widely used in railway stations and airports. However, there are still several challenges that limit the accuracy of detection in PMMW images: low resolution, small objects and complex background interference. The existing deep learning-based methods mainly adopt two-stage architecture with convolutional neural networks (CNN) as the backbone for feature extraction, while the low speed of two-stage architecture and limited receptive field of CNN impede the further improvement of the intelligent inspection system. In this paper, we propose a one-stage anchor-free detector that combines the merits of CNN and transformer to solve these problems, and we avoid the tradeoff between accuracy and computational complexity that most hierarchical transformers make by constricting self-attention within pre-defined local windows. Specifically, we design a novel backbone to model low-level local and high-level global features at different scales via CNN and transformer. We also introduce object queries to guide the detector to perceive the concealed objects from the background noise, and these learnable queries are further utilized to form a full-size object-aware attention mechanism. Besides, to select the optimal positive samples for the anchor-free detector, we propose a novel label assignment strategy by employing Gaussian distribution to adaptively model the objects with various shapes. Experimental results on our self-developed PMMW imager demonstrate that the proposed method outperforms the state-of-the-art methods in terms of accuracy and speed.

Similar Papers
  • Research Article
  • Citations19

Source-Free Domain Adaptive Detection of Concealed Objects in Passive Millimeter-Wave Images

  • Jan 01, 2023
  • IEEE Transactions on Instrumentation and Measurement
  • Hao Yang +5
  • Conference Article
  • Citations1

Multi-channel millimeter wave image registration and segmentation for concealed object detection

  • Apr 23, 2010
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Dong-Su Lee +3
  • Research Article
  • Citations4

PMMWMatcher: Weakly Supervised Feature Matching With Descriptor Enhancement for Passive Millimeter-Wave Images

  • Jan 01, 2024
  • IEEE Transactions on Instrumentation and Measurement
  • Hao Yang +5
  • Conference Article
  • Citations1

Research on Image Fusion for Visual and PMMW Images Using NSCT and Region Detection

  • Jan 01, 2013
  • Tang Shi +3
  • Research Article
  • Citations35

Automatic image segmentation for concealed object detection using the expectation-maximization algorithm

  • May 06, 2010
  • Optics Express
  • Dong-Su Lee +3
  • Research Article
  • Citations4

Image Fusion of PMMW and Optical Images for Concealed Object Detection

  • Jan 01, 2021
  • Journal of Physics: Conference Series
  • Lu Zhang +2
  • Conference Article
  • Citations22

Evaluation of a passive millimeter-wave (PMMW) imager for wire detection in degraded visual conditions

  • May 01, 2009
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Roger Appleby +2
  • Research Article
  • Citations1

An Iterative Method Combining Fuzzy Fusion and Fisher Vectors for Concealed Object Detection in Passive Millimeter-Wave Imaging

  • Jan 01, 2025
  • IEEE Transactions on Instrumentation and Measurement
  • Bo Fang +7
  • Research Article
  • Citations23

A Multi-Thresholding Method Based on Otsu’s Algorithm for the Detection of Concealed Threats in Passive Millimeter-Wave Images

  • May 27, 2019
  • Frequenz
  • Hakan Işıker +1
  • Research Article
  • Citations83

Passive millimeter-wave imaging with compressive sensing

  • Sep 14, 2012
  • Optical Engineering
  • Nachappa Gopalsami +7
  • Research Article
  • Citations1

Design of Ka-band Linear Tapered Slot Antennas Based on Substrate Integrated Waveguide Feed

  • Mar 19, 2020
  • 电子与信息学报
  • Honggang Hao +3
  • Conference Article

Research on Compressive Super-Resolution Algorithm Based on Pre-classification Learning for Passive Millimeter Wave Images

  • Dec 07, 2013
  • Zhuli Cao +3
  • Research Article
  • Citations33

Segmentation of Concealed Objects in Passive Millimeter-Wave Images Based on the Gaussian Mixture Model

  • Feb 17, 2015
  • Journal of Infrared, Millimeter, and Terahertz Waves
  • Wangyang Yu +2
  • Book Chapter
  • Citations1

Passive Millimeter-Wave Imaging Technology for Concealed Contraband Detection

  • Jan 01, 2018
  • Jing-Hui Qiu +3
  • Conference Article
  • Citations1

Concealed Object Detection Performance of Polarimetric Passive Millimeter-Wave Imaging

  • Aug 12, 2022
  • Xun Tian +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.