Infrared polarization image fusion integrates intensity and polarization information, producing a fused image that enhances visibility and captures crucial details. However, in complex environments, polarization imaging is susceptible to noise interference. Existing fusion methods typically use the infrared intensity (S0) and degree of linear polarization (DoLP) images for fusion but fail to consider the noise interference, leading to reduced performance. To cope with this problem, we propose a fusion method based on polarization salient prior, which extends DoLP by angle of polarization (AoP) and introduces polarization distance (PD) to obtain salient target features. Moreover, according to the distribution difference between S0 and DoLP features, we construct a fusion network based on attention-guided filtering, utilizing cross-attention to generate filter kernels for fusion. The quantitative and qualitative experimental results validate the effectiveness of our approach. Compared with other fusion methods, our method can effectively suppress noise interference and preserve salient target features.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1364/OE.492954 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Individual differences elucidate the perceptual benefits associated with robust temporal fine-structure processing.
Proc Natl Acad Sci U S A
January 2025
Department of Communication Science and Disorders, University of Pittsburgh, Pittsburgh, PA 15213.
The auditory system is unique among sensory systems in its ability to phase lock to and precisely follow very fast cycle-by-cycle fluctuations in the phase of sound-driven cochlear vibrations. Yet, the perceptual role of this temporal fine structure (TFS) code is debated. This fundamental gap is attributable to our inability to experimentally manipulate TFS cues without altering other perceptually relevant cues.
View Article and Find Full Text PDFCurcumin/kaolin composite for advanced latent fingerprint imaging with fluorescence quantification.
Analyst
January 2025
Questrom School of Business, Boston University, Boston, MA, 02215, USA.
Latent fingerprints (LFPs) are invisible impressions that need to be developed before being used for criminal investigation; however, existing fingerprint visualization techniques face challenges, such as complex preparation and poor contrast. To advance practical fingerprint detection, green-emissive micron-sized curcumin/kaolin composites were synthesized a facile and cost-effective one-step physical cross-linking method, which exhibited unprecedented performance in developing diversified marks, including LFPs, knuckle prints, palm prints, and footprints, with clear three-level details on various substrates. Notably, the powders successfully developed LFPs that were aged for 30 days and even up to 100 days, meeting the stringent requirements for comprehensive forensic application.
View Article and Find Full Text PDFSeq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems.
Sci Rep
January 2025
School of Mines, China University of Mining and Technology, Xuzhou, China.
In coal mining operations, the stable operation of hydraulic supports is crucial for ensuring mine safety. However, the nonlinear, non-stationary characteristics and noise interference in hydraulic support pressure data pose significant challenges for anomaly detection and fault diagnosis. This study proposes an anomaly detection and failure identification method based on Gated Recurrent Unit Autoencoder (GRU-AE), aimed at achieving anomaly detection in hydraulic support pressure data and equipment failure early warning.
View Article and Find Full Text PDFA improved group quantum key distribution protocol with multi-party collaboration.
Sci Rep
January 2025
Faculty of Computer and Control Engineering, Qiqihar University, Qiqihar, 161000, China.
The rapid advancement of quantum key distribution technology in recent years has spurred significant innovation within the field. Nevertheless, a crucial yet frequently underexplored challenge involves the comprehensive evaluation of security quantum state modulation. To address this issue, we propose a novel framework for quantum group key distribution.
View Article and Find Full Text PDFElectrochemical Self-Sacrificial Label Conversion Coupled with DNA Framework Nanomachine Mediated Serotonin Sensing with Highly Minimized Background Noise.
Anal Chem
January 2025
School of Chemistry and Materials Science, Jiangsu Normal University, Xuzhou, Jiangsu 221116, China.
Conventional solid/liquid electrochemical interfaces typically encounter challenges with impeded mass transport for poor electrochemical quantification due to the intricate pathways of reactants from the bulk solution. To address this issue, this work reports an innovative approach integrating a target-activated DNA framework nanomachine with electrochemically driven metal-organic framework (MOF) conversion for self-sacrificial biosensing. The presence of the target biomarker serotonin initiates the DNA framework nanomachine by an entropy-driven circuit to form a cross-linked nanostructure and subsequently release the Fe-MOF probe.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!