• Home
  • Search
  • PMMWPoint: Weakly Supervised Dense Keypoint Detection and Description for Passive Millimeter-Wave Image Matching
  • Cite Icon4
  • https://doi.org/10.1109/tim.2023.3343790Copy DOI Icon

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

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

Passive millimeter-wave (PMMW) imager has become a common device for detecting concealed objects in security screening. However, the current detection methods rely primarily on 2-D information, which is inefficient for objects with similar grayscale values to the human body. Exploiting the 3-D features of the objects will be conducive to tackling this challenge, where image matching is generally the first step before performing the 3-D reconstruction. However, the existing matching methods struggle to produce reliable keypoints in textureless and noisy PMMW images, since they mainly focus on texture regions with distinct features, such as corners and lines. To tackle this challenge, we present a weakly supervised framework to learn keypoints in PMMW images, named as PMMWPoint. Specifically, we first pretrain a diffusion model on unlabeled PMMW images in an unsupervised manner for better modeling the intricate characteristics of PMMW images. Then we employ a few labeled keypoints as guidance for network to detect keypoints from textureless regions. To compensate for the sparsity of manual labeling, a self-paced keypoint augmentation (SPKA) strategy is introduced to progressively increase the quantity and quality of ground-truth labels during training. In addition, we propose an improved contrastive loss for better descriptor learning by integrating the information from detection and description branches. Extensive experiments prove the superiority of PMMWPoint in producing dense and accurate keypoints, which deliver a notable improvement of +4.8% and +1.2% in homography accuracy over unsupervised baselines for PMMW and Hpatches datasets, respectively. Through our investigation, our work represents the first effort to address the problem of PMMW image matching.

Similar Papers
  • Conference Article
  • Citations5

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

  • Oct 01, 2011
  • Qiao Zhang +3
  • 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
  • Citations1

Improving Image Matching Accuracy with Keypoint Features and Feature Fusion

  • Nov 12, 2021
  • Tongyu Lu
  • Research Article
  • Citations12

Fast image matching via multi-scale Gaussian mutation pigeon-inspired optimization for low cost quadrotor

  • Oct 02, 2017
  • Aircraft Engineering and Aerospace Technology
  • Shanjun Chen +1
  • Research Article
  • Citations1

IMPROVED ALGORITHM OF NONLINEAR EXTRAPOLATION IN FREQUENCY SPACE AND ITS APPLICATION IN PASSIVE MILLIMETER-WAVE IMAGE ENHANCEMENT

  • Nov 25, 2009
  • JOURNAL OF INFRARED AND MILLIMETER WAVES
  • Yue-Lin Deng +2
  • Conference Article
  • Citations5

Polarimetric Passive Millimeter-Wave Imaging of Surface Vessels

  • Jul 17, 2022
  • Yayun Cheng +2
  • Book Chapter
  • Citations3

Image Matching based on Curvilinear Regions

  • Jun 01, 2007
  • J Perez +4
  • PDF
  • Research Article
  • Citations6

An Emergency Georeferencing Framework for GF-4 Imagery Based on GCP Prediction and Dynamic RPC Refinement

  • Oct 17, 2017
  • Remote Sensing
  • Pengfei Li +4
  • Research Article

High-resolution 96-GHz (3 mm) passive millimeter-wave imaging system and the effect of scanning resolution on images

  • Oct 27, 2022
  • Journal of Applied Remote Sensing
  • Alp Oral Salman +1
  • Conference Article

Passive millimetre wave imaging and absorption from exhaust gases

  • May 24, 1999
  • N.A Salmon
  • Conference Article
  • Citations4

Image fusion of visual and millimeter wave images for concealed object detection

  • Sep 01, 2009
  • Hyoung Lee +4
  • Conference Article
  • Citations26

<title>A passive millimeter-wave imaging system for concealed weapons and explosives detection (Invited Paper)</title>

  • May 19, 2005
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Vladimir G Kolinko +8
  • Book Chapter
  • Citations3

Image Background Matching for Identifying Suspects

  • May 01, 2020
  • Paul Fogg +2
  • Conference Article
  • Citations17

Real-time wide-field-of-view passive millimeter-wave imaging

  • Jul 25, 2002
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Christopher A Martin +3
  • Conference Article
  • Citations1

Research on 3mm Band Alternating Current Radiometric Imaging

  • Sep 01, 2006
  • Guangfeng Zhang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.