Xu Tao¹, Qiang Xiao², Zhaoqi Jin², Hao Li^1,*

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-18, 2026, DOI:10.32604/cmc.2025.070790 - 09 December 2025

Abstract Image fusion technology aims to generate a more informative single image by integrating complementary information from multi-modal images. Despite the significant progress of deep learning-based fusion methods, existing algorithms are often limited to single or dual-dimensional feature interactions, thus struggling to fully exploit the profound complementarity between multi-modal images. To address this, this paper proposes a parallel multi-dimensional complementary fusion network, termed PMCFusion, for the task of infrared and visible image fusion. The core of this method is its unique parallel three-branch fusion module, PTFM, which pioneers the parallel synergistic perception and efficient integration of… More >

Guofeng Han, Chenxi Luo, Xin Liu, Yuanyuan Li, Yuling Cheng, Shuai Huang, Dan Huang^*

Frontiers in Heat and Mass Transfer, Vol.23, No.6, pp. 1981-1999, 2025, DOI:10.32604/fhmt.2025.074593 - 31 December 2025

Abstract Bananas are highly perishable after harvest, and processing them into dried products is a crucial approach to reducing losses and adding their economic values. To address the inefficiency and prolonged duration of traditional hot air drying (HAD) and the quality inconsistency associated with single infrared drying (IRD), this study proposed a novel hot air-infrared combined drying (HAD-IRD) strategy. The effects of HAD, IRD, and HAD-IRD on the drying kinetics, color, rehydration capacity, moisture diffusion mechanism, and sensory quality of banana slices were systematically investigated. The parameters of the combined drying process were optimized using an L₉(3³)… More >

Yang Liu¹, Biao Chen¹, Xin Liu², Chenxi Luo², Shihui Xiao^2,*

Frontiers in Heat and Mass Transfer, Vol.23, No.6, pp. 2127-2146, 2025, DOI:10.32604/fhmt.2025.070973 - 31 December 2025

Abstract This study evaluated corn kernel drying performance and quality changes using hot air drying (HAD) and infrared drying (ID) across temperatures ranging from 55°C to 80°C. Optimal drying parameters were determined by using the entropy weight method, with drying time, specific energy consumption, damage rate, fatty acids, starch, polyphenols, and flavonoids as indicators. Results demonstrated that ID significantly outperformed HAD, achieving drying times up to 20% shorter and reducing specific energy consumption and kernel damage by up to 79.3% and 66.7%, respectively, while also better preserving quality attributes. Both methods exhibited drying profiles characterized by More >

Tianzhe Jiao, Yuming Chen, Xiaoyue Feng, Chaopeng Guo, Jie Song^*

CMC-Computers, Materials & Continua, Vol.85, No.2, pp. 2681-2700, 2025, DOI:10.32604/cmc.2025.069235 - 23 September 2025

Abstract Visible-infrared object detection leverages the day-night stable object perception capability of infrared images to enhance detection robustness in low-light environments by fusing the complementary information of visible and infrared images. However, the inherent differences in the imaging mechanisms of visible and infrared modalities make effective cross-modal fusion challenging. Furthermore, constrained by the physical characteristics of sensors and thermal diffusion effects, infrared images generally suffer from blurred object contours and missing details, making it difficult to extract object features effectively. To address these issues, we propose an infrared-visible image fusion network that realizes multimodal information fusion… More >

Konstantin Busov^1,*, Nikolay Mazheiko¹, Leonid Plotnikov², Boris Zhilkin²

Frontiers in Heat and Mass Transfer, Vol.23, No.4, pp. 1203-1214, 2025, DOI:10.32604/fhmt.2025.067598 - 29 August 2025

Abstract Experimental research into the boiling-up of a free jet of superheated water discharging through a short cylindrical nozzle with sharp inlet and outlet edges into the atmosphere has been carried out. The change in the shape of a liquid jet has been traced through changes in thermodynamic parameters (temperature, pressure) along the saturation line in both the visible range and the infrared spectrum. The flow shapes corresponding to various modes of boiling-up have been identified. With thermal-imaging diagnostics, heterogeneities in the spray plume of a superheated liquid jet have been recorded and temperature distributions have More >

Chongyang Wang¹, Qiongyan Li¹, Shu Liu², Pengle Cheng^1,*, Ying Huang³

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 5157-5176, 2025, DOI:10.32604/cmc.2025.067367 - 30 July 2025

Abstract With rapid urbanization, fires pose significant challenges in urban governance. Traditional fire detection methods often struggle to detect smoke in complex urban scenes due to environmental interferences and variations in viewing angles. This study proposes a novel multimodal smoke detection method that fuses infrared and visible imagery using a transformer-based deep learning model. By capturing both thermal and visual cues, our approach significantly enhances the accuracy and robustness of smoke detection in business parks scenes. We first established a dual-view dataset comprising infrared and visible light videos, implemented an innovative image feature fusion strategy, and More >

Siqi Zhang, Shengda Pan^*

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 4655-4676, 2025, DOI:10.32604/cmc.2025.064864 - 30 July 2025

Abstract Infrared images typically exhibit diverse backgrounds, each potentially containing noise and target-like interference elements. In complex backgrounds, infrared small targets are prone to be submerged by background noise due to their low pixel proportion and limited available features, leading to detection failure. To address this problem, this paper proposes an Attention Shift-Invariant Cross-Evolutionary Feature Fusion Network (ASCFNet) tailored for the detection of infrared weak and small targets. The network architecture first designs a Multidimensional Lightweight Pixel-level Attention Module (MLPA), which alleviates the issue of small-target feature suppression during deep network propagation by combining channel reshaping,… More >

Mengke Tang¹, Yong Gan^2,*, Yifan Zhang¹, Xinxin Gan³

CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 2699-2716, 2025, DOI:10.32604/cmc.2025.064541 - 03 July 2025

Abstract Infrared imaging technology has been widely adopted in various fields, such as military reconnaissance, medical diagnosis, and security monitoring, due to its excellent ability to penetrate smoke and fog. However, the prevalent low resolution of infrared images severely limits the accurate interpretation of their contents. In addition, deploying super-resolution models on resource-constrained devices faces significant challenges. To address these issues, this study proposes a lightweight super-resolution network for infrared images based on an adaptive attention mechanism. The network’s dynamic weighting module automatically adjusts the weights of the attention and non-attention branch outputs based on the… More >

Kezhen Xie^1,2, Syed Mohd Zahid Syed Zainal Ariffin^1,*, Muhammad Izzad Ramli¹

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 997-1011, 2025, DOI:10.32604/cmc.2025.063469 - 09 June 2025

Abstract Infrared and visible image fusion technology integrates the thermal radiation information of infrared images with the texture details of visible images to generate more informative fused images. However, existing methods often fail to distinguish salient objects from background regions, leading to detail suppression in salient regions due to global fusion strategies. This study presents a mask-guided latent low-rank representation fusion method to address this issue. First, the GrabCut algorithm is employed to extract a saliency mask, distinguishing salient regions from background regions. Then, latent low-rank representation (LatLRR) is applied to extract deep image features, enhancing More >

Junfeng Lin¹, Jialin Ma^1,*, Wei Chen^1,2, Hao Wang¹, Weiguo Ding¹, Mingyao Tang¹

CMC-Computers, Materials & Continua, Vol.84, No.1, pp. 1013-1029, 2025, DOI:10.32604/cmc.2025.062895 - 09 June 2025

Abstract The cross-modal person re-identification task aims to match visible and infrared images of the same individual. The main challenges in this field arise from significant modality differences between individuals and the lack of high-quality cross-modal correspondence methods. Existing approaches often attempt to establish modality correspondence by extracting shared features across different modalities. However, these methods tend to focus on local information extraction and fail to fully leverage the global identity information in the cross-modal features, resulting in limited correspondence accuracy and suboptimal matching performance. To address this issue, we propose a quadratic graph matching method… More >