• Home
  • Search
  • PMMWMatcher: Weakly Supervised Feature Matching With Descriptor Enhancement for Passive Millimeter-Wave Images
  • Cite Icon4
  • https://doi.org/10.1109/tim.2024.3395309Copy DOI Icon

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

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

Concealed object detection in passive millimeter-wave (PMMW) image has achieved significant progress. Using the limited information in 2-D PMMW images, however, some intractable cases cannot be handled, such as the objects with grayscale values close to the human body. Mining 3-D structures of concealed objects is beneficial to improve the performance and robustness of the detection. In this article, we dedicate to establish the accurate correspondence between PMMW images, which is an essential step in 3-D reconstruction. Such a task is especially challenging for textureless PMMW images with large noise. To this end, we introduce PMMWMatcher, a weakly supervised feature matcher that only leverages the camera pose as supervision, to promote the quality of current descriptors and establish the correspondence in a learnable manner. Concretely, we boost the representation of descriptors with self- and cross-attention. Then, we introduce a novel local-to-global searching strategy that comprehensively exploits the epipolar constraint between image pairs derived from the camera poses. Such a strategy effectively improves the robustness of descriptors for local feature matching in real scenes. Finally, we design a matching module to adaptively set up more accurate correspondence through deep reinforcement learning (RL) than the handcrafted methods. The experimental results show that PMMWMatcher can achieve a further enhancement in matching performance, with a +3.6% improvement in homography accuracy based on the existing PMMW feature points. The proposed method can be easily embedded in the existing keypoint detection pipelines, exhibiting great flexibility in practical applications.

Similar Papers
  • Research Article
  • Citations29

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

  • Aug 01, 2023
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Hao Yang +5
  • 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

Image Fusion of PMMW and Optical Images for Concealed Object Detection

  • Jan 01, 2021
  • Journal of Physics: Conference Series
  • Lu Zhang +2
  • Conference Article
  • Citations1

Concealed Object Detection Performance of Polarimetric Passive Millimeter-Wave Imaging

  • Aug 12, 2022
  • Xun Tian +2
  • Research Article
  • Citations35

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

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

PMMWPoint: Weakly Supervised Dense Keypoint Detection and Description for Passive Millimeter-Wave Image Matching

  • Jan 01, 2024
  • IEEE Transactions on Instrumentation and Measurement
  • Hao Yang +4
  • 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

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
  • Conference Article
  • Citations4

The millimeter-wave ISAR imaging of concealed objects

  • Aug 01, 2011
  • Harun Cetinkaya +6
  • Conference Article
  • Citations6

InP-HEMT MMICs for passive millimeter-wave imaging sensors

  • May 01, 2008
  • M Sato +8
  • Conference Article
  • Citations5

A millimeter-wave image denoising method based on adaptive sparse representation

  • Oct 01, 2011
  • Qiao Zhang +3
  • Research Article
  • Citations2

Indoor Passive Millimeter-Wave Imaging for Concealed Object Detection

  • Sep 18, 2013
  • Advanced Materials Research
  • Shou Long Dong +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.