A feature refinement and adaptive generative adversarial network for thermal infrared image colorization.

Colorizing thermal infrared images poses a significant challenge as current methods struggle with issues such as unrealistic color saturation and limited texture. To address these challenges, we propose the Feature Refinement and Adaptive Generative Adversarial Network (FRAGAN). Our approach enhances the detailed, semantic, and contextual capabilities of image coloring by combining multi-level interactions that integrate the lost detailed information from the encoding stage with the semantic information from the decoding stage. Additionally, we introduce the Residual Feature Refinement Module (RFRM) to improve both the accuracy and generalization ability of the model, thereby elevating the quality of colorization results. The Feature Adaptation Module (FAM) is employed to mitigate sub-region information loss during downsampling. Furthermore, we introduce the Trinity Attention Module (TAM) to accurately capture the spatial and channel-wise interaction features of local semantic information. Extensive experimentation on the KAIST dataset and the FLIR dataset demonstrates the superiority of our proposed FRAGAN methodology, surpassing both the performance metrics and visual quality of current state-of-the-art methods. The colorized images generated by our proposed FRAGAN exhibit enhanced clarity and realism. Our code and models are available at GitHub.

A Low-Illumination Enhancement Method Based on Structural Layer and Detail Layer.

Low-illumination image enhancement technology is a topic of interest in the field of image processing. However, while improving image brightness, it is difficult to effectively maintain the texture and details of the image, and the quality of the image cannot be guaranteed. In order to solve this problem, this paper proposed a low-illumination enhancement method based on structural and detail layers. Firstly, we designed an SRetinex-Net model. The network is mainly divided into two parts: a decomposition module and an enhancement module. Second, the decomposition module mainly adopts the SU-Net structure, which is an unsupervised network that decomposes the input image into a structural layer image and detail layer image. Afterward, the enhancement module mainly adopts the SDE-Net structure, which is divided into two branches: the SDE-S branch and the SDE-D branch. The SDE-S branch mainly enhances and adjusts the brightness of the structural layer image through Ehnet and Adnet to prevent insufficient or overexposed brightness enhancement in the image. The SDE-D branch is mainly denoised and enhanced with textural details through a denoising module. This network structure can greatly reduce computational costs. Moreover, we also improved the total variation optimization model as a mixed loss function and added structural metrics and textural metrics as variables on the basis of the original loss function, which can well separate the structure edge and texture edge. Numerous experiments have shown that our structure has a more significant impact on the brightness and detail preservation of image restoration.

Contour Information-Guided Multi-Scale Feature Detection Method for Visible-Infrared Pedestrian Detection.

Infrared pedestrian target detection is affected by factors such as the low resolution and contrast of infrared pedestrian images, as well as the complexity of the background and the presence of multiple targets occluding each other, resulting in indistinct target features. To address these issues, this paper proposes a method to enhance the accuracy of pedestrian target detection by employing contour information to guide multi-scale feature detection. This involves analyzing the shapes and edges of the targets in infrared images at different scales to more accurately identify and differentiate them from the background and other targets. First, we propose a preprocessing method to suppress background interference and extract color information from visible images. Second, we propose an information fusion residual block combining a U-shaped structure and residual connection to form a feature extraction network. Then, we propose an attention mechanism based on a contour information-guided approach to guide the network to extract the depth features of pedestrian targets. Finally, we use the clustering method of mIoU to generate anchor frame sizes applicable to the KAIST pedestrian dataset and propose a hybrid loss function to enhance the network's adaptability to pedestrian targets. The extensive experimental results show that the method proposed in this paper outperforms other comparative algorithms in pedestrian detection, proving its superiority.

Improved Thermal Infrared Image Super-Resolution Reconstruction Method Base on Multimodal Sensor Fusion.

When traditional super-resolution reconstruction methods are applied to infrared thermal images, they often ignore the problem of poor image quality caused by the imaging mechanism, which makes it difficult to obtain high-quality reconstruction results even with the training of simulated degraded inverse processes. To address these issues, we proposed a thermal infrared image super-resolution reconstruction method based on multimodal sensor fusion, aiming to enhance the resolution of thermal infrared images and rely on multimodal sensor information to reconstruct high-frequency details in the images, thereby overcoming the limitations of imaging mechanisms. First, we designed a novel super-resolution reconstruction network, which consisted of primary feature encoding, super-resolution reconstruction, and high-frequency detail fusion subnetwork, to enhance the resolution of thermal infrared images and rely on multimodal sensor information to reconstruct high-frequency details in the images, thereby overcoming limitations of imaging mechanisms. We designed hierarchical dilated distillation modules and a cross-attention transformation module to extract and transmit image features, enhancing the network's ability to express complex patterns. Then, we proposed a hybrid loss function to guide the network in extracting salient features from thermal infrared images and reference images while maintaining accurate thermal information. Finally, we proposed a learning strategy to ensure the high-quality super-resolution reconstruction performance of the network, even in the absence of reference images. Extensive experimental results show that the proposed method exhibits superior reconstruction image quality compared to other contrastive methods, demonstrating its effectiveness.

Research on Nickel Material Trade Redistribution Strategy Based on the Maximum Entropy Principle.

In the double carbon background, riding the wind of new energy vehicles and the battery high nickelization, nickel resources rise along with the trend. In recent years, due to the influence of geopolitical conflicts and emergencies, as well as the speculation and control of international capital with its advantages and rules, the world may face price and security supply risks to a certain extent. Therefore, to obtain the most objective trade redistribution strategy, this paper first constructs the nickel material trade network, identifies the core trading countries and the main trade relations of nickel material trade, and finds that the flow of nickel material mainly occurred between a few countries. On this basis, a trade redistribution model is constructed based on the maximum entropy principle. Taking Indonesia, the largest exporter, and the largest trade relationship (Indonesia exports to China) as examples, the nickel material redistribution between countries when different supply risks occur are simulated. The results can provide an important reference for national resource recovery after the risk of the nickel trade.

The Long-Term Effect of a Nine Amino-Acid Antimicrobial Peptide AS-hepc3(48-56) Against Pseudomonas aeruginosa With No Detectable Resistance.

The emergence of multidrug-resistant (MDR) pathogens has become a global public health crisis. Among them, MDR Pseudomonas aeruginosa is the main cause of nosocomial infections and deaths. Antimicrobial peptides (AMPs) are considered as competitive drug candidates to address this threat. In the study, we characterized two AMPs (AS-hepc3(41-71) and AS-hepc3(48-56)) that had potent activity against 5 new clinical isolates of MDR P. aeruginosa. Both AMPs destroyed the integrity of the cell membrane, induced leakage of intracellular components, and ultimately led to cell death. A long-term comparative study on the bacterial resistance treated with AS-hepc3(41-71), AS-hepc3(48-56) and 12 commonly used antibiotics showed that P. aeruginosa quickly developed resistance to the nine antibiotics tested (including aztreonam, ceftazidime, cefepime, imipenem, meropenem, ciprofloxacin, levofloxacin, gentamicin, and piperacillin) as early as 12 days after 150 days of successive culture generations. The initial effective concentration of 9 antibiotics against P. aeruginosa was greatly increased to a different high level at 150 days, however, both AS-hepc3(41-71) and AS-hepc3(48-56) maintained their initial MIC unchangeable through 150 days, indicating that P. aeruginosa did not produce any significant resistance to both AMPs. Furthermore, AS-hepc3(48-56) did not show any toxic effect on mammalian cells in vitro and mice in vivo. AS-hepc3(48-56) had a therapeutic effect on MDR P. aeruginosa infection using a mouse lung infection model and could effectively increase the survival rate of mice by inhibiting bacterial proliferation and attenuating lung inflammation. Taken together, the short peptide AS-hepc3(48-56) would be a promising agent for clinical treatment of MDR P. aeruginosa infections.

An effector caspase Sp-caspase first identified in mud crab Scylla paramamosain exhibiting immune response and cell apoptosis.

Apoptosis plays a key role in the immune defense against pathogen infection, and caspase is one of the most important protease enzyme families, which could initiate and execute apoptosis. Among crustaceans, several caspase genes have been reported. However, caspase in mud crab Scylla paramamosain, have not been identified yet. Here, in the present study, we characterized a new caspase, named as Sp-caspase, from S. paramamosain. The full-length cDNA sequence of Sp-caspase contained 966 bp open reading frame, encoding 322 amino acids, and its molecular weight was 36 kDa. This gene has three conserved domains of the caspase family, a prodomain, a large subunit P20 and a small subunit P10. Phylogenetic analysis showed that Sp-caspase was clustered into an effector caspase group. Sp-caspase mainly distributed in midgut, hepatopancreas, hemocytes and female ovaries, and the transcript was significantly regulated in different tissues after being challenged with Vibrio parahaemolyticus, Vibrio alginolyticus or LPS. After infection with V. alginolyticus, the apoptosis rate of hemocytes notably increased, while the mRNA level of Sp-caspase and hydrolysis activity of caspase 3/7 significantly decreased. Furthermore, in vitro assays showed that the recombinant protein tSp-caspase (deletion of Sp-caspase prodomain) could efficiently recognize and cleave human caspase 3/7 substrate Ac-DEVD-pNA, functioning as an effector caspase. Meanwhile, heterologous expression of Sp-caspase in several cell lines (HEK293T cells, HeLa cells and HighFive cells) could specifically induce cell apoptosis. Taken together, these data demonstrated that Sp-caspase could perform apoptosis as an effector caspase. In addition, it might be a negative regulator of hemocytes apoptosis under pathogen infection, which would contribute to homeostasis and immune defense of hemocytes in S. paramamosain.