Multispectral Fusion Research Articles

Unsupervised Hyperspectral and Multispectral Image Blind Fusion Based on Deep Tucker Decomposition Network With Spatial-Spectral Manifold Learning.

Hyperspectral image (HSI) and multispectral image (MSI) fusion aims to generate high spectral and spatial resolution hyperspectral image (HR-HSI) by fusing high-resolution multispectral image (HR-MSI) and low-resolution hyperspectral image (LR-HSI). However, existing fusion methods encounter challenges such as unknown degradation parameters, and incomplete exploitation of the correlation between high-dimensional structures and deep image features. To overcome these issues, in this article, an unsupervised blind fusion method for LR-HSI and HR-MSI based on Tucker decomposition and spatial-spectral manifold learning (DTDNML) is proposed. We design a novel deep Tucker decomposition network that maps LR-HSI and HR-MSI into a consistent feature space, achieving reconstruction through decoders with shared parameters. To better exploit and fuse spatial-spectral features in the data, we design a core tensor fusion network (CTFN) that incorporates a spatial-spectral attention mechanism for aligning and fusing features at different scales. Furthermore, to enhance the capacity to capture global information, a Laplacian-based spatial-spectral manifold constraint is introduced in shared-decoders. Sufficient experiments have validated that this method enhances the accuracy and efficiency of hyperspectral and multispectral fusion on different remote sensing datasets. The source code is available at https://github.com/Shawn-H-Wang/DTDNML.

Evolutionary computation-based self-supervised learning for image processing: a big data-driven approach to feature extraction and fusion for multispectral object detection

The image object recognition and detection technology are widely used in many scenarios. In recent years, big data has become increasingly abundant, and big data-driven artificial intelligence models have attracted more and more attention. Evolutionary computation has also provided a powerful driving force for the optimization and improvement of deep learning models. In this paper, we propose an image object detection method based on self-supervised and data-driven learning. Differ from other methods, our approach stands out due to its innovative use of multispectral data fusion and evolutionary computation for model optimization. Specifically, our method uniquely combines visible light images and infrared images to detect and identify image targets. Firstly, we utilize a self-supervised learning method and the AutoEncoder model to perform high-dimensional feature extraction on the two types of images. Secondly, we fuse the extracted features from the visible light and infrared images to detect and identify objects. Thirdly, we introduce a model parameter optimization method using evolutionary learning algorithms to enhance model performance. Validation on public datasets shows that our method achieves comparable or superior performance to existing methods.

GF-4 high-resolution texture and FY-4A multispectral data fusion: Two case studies for enhancing early convective cloud detection

Early detection of convective clouds is vital for minimizing hazardous impacts. Forecasting convective initiation (CI) using current multispectral geostationary meteorological satellites is often challenged by high false-alarm rates and missed detections caused by limited resolution. In contrast, high-resolution earth observation satellites offer more detailed texture information, improving early detection capabilities. The authors propose a novel methodology that integrates the advanced features of China's latest-generation satellites, Gaofen-4 (GF-4) and Fengyun-4A (FY-4A). This fusion method retains GF's high-resolution details and FY-4A's multispectral information. Two cases from different observational scenarios and weather conditions under GF-4's staring mode were carried out to compare the CI forecast results based on fused data and solely on FY-4A data. The fused data demonstrated superior performance in detecting smaller-scale convective clouds, enabling earlier forecasting with a lead time of 15–30 minutes, and more accurate location identification. Integrating high-resolution earth observation satellites into early convective cloud detection provides valuable insights for forecasters and decision-makers, particularly given the current resolution limitations of geostationary meteorological satellites.摘要对流云的早期探测对于降低天气致灾风险至关重要. 当前静止气象卫星受其分辨率的限制, 在预测对流初生 (CI) 时仍存在较高的虚警率和漏报率. 对比而言, 高分辨率的地球观测卫星能够提供更丰富的纹理细节, 有助于提升对流云早期探测的能力. 作者提出了一种创新性的方法, 融合GF-4的高分辨率细节和FY-4A的多光谱信息, 以优化对流云的早期识别和预测. 通过对GF-4凝视模式下两种不同天气条件和观测场景的案例分析, 融合数据在探测更小尺度的对流云方面具有明显优势, 一定程度解决漏报难题, 另一方面能够将对流初生的可探测时间提前, 更精确表现对流爆发位置和更准确刻画对流发展过程. 在当前静止气象卫星分辨率受限的条件下, 这种高分辨率地球观测卫星数据的融合应用能够为气象预报员和决策者提供更有价值的观测视角.

Rapid discriminant analysis for the origin of specialty yam based on multispectral data fusion strategies

In order to achieve rapid and effective identification of Hebei yam, a qualitative discrimination model was constructed based on near infrared (NIR), mid infrared (MIR), and microscopic Raman spectra in combination with individual spectra and multispectral data fusion strategies. The results showed that the gray wolf optimizer-support vector machine (GWO-SVM) model constructed by mid-level fusion using the three feature spectra performed the best in distinguishing the geographic origin of the yam, with a prediction accuracy of 100.00% in both the training set and the test set, and an F1 score of 1.00. The results indicated that due to spectral complementarity, NIR, MIR and Raman combined with feature-level fusion can be used as a powerful, non-destructive, fast and feasible tool for geographic origin classification and brand protection of Hebei yam. This work is expected to be a potential method for origin identification analysis and quality monitoring in the food and pharmaceutical industries.

Multi-spectral image fusion for moving object detection

This study delves into the problem of moving object detection in infrared and visible images. While existing approaches primarily focus on single-task detection using single-spectral image data, such as thermal infrared or visible images, they often ignore the differences between different spectral images and the interconnectedness of related tasks such as image fusion and segmentation. To tackle these problems, we present a novel multi-spectral image fusion network with quality and semantic awareness for moving object detection (MOD), particularly in scenarios where ground truth labels for both infrared and visible images are unavailable. Our approach fuses multi-spectral images, incorporating additional subtasks in the image fusion to obtain content and quality perception of infrared and visible images. In addition, we design a novel residual global perception module (RGPM) and multi-spectral fusion loss, which can capture more hidden features and contextual information across various scales. This enhanced capability leads to more precise detection and tracking of moving objects, particularly in challenging situations involving occlusions and dynamic backgrounds. Compared with single-spectral moving object detection optimization, the hurdles of utilizing deep learning for multi-spectral image fusion, e.g., without ground truth labels and harmful noise, are significantly mitigated. Extensive quantitative and qualitative comparative experiments demonstrate its effectiveness, robustness, and superior performance compared to contemporary methods. Concisely, the proposed fusion representation learning has gained 44.2%,31.2%,36.3%,41.6%,5.3%,31.2%,76.2% on EI, SF, DF, AG, MI, SD and Nabf metrics compared with the best competitors.

Recognition of small water bodies under complex terrain based on SAR and optical image fusion algorithm

Understanding the spatial and temporal distribution of small water bodies is essential for managing water resources, crafting conservation policies, and preserving watershed ecosystems and biodiversity. However, existing studies often rely on a single remote sensing data source (optical or microwave), focusing on large-scale, flat areas and lacking comprehensive monitoring of small water bodies in complex terrain. Therefore, considering the complementary advantages of multisource remote sensing (multispectral and SAR), this paper proposes a multispectral and SAR fusion algorithm, named Multispectral and SAR Fusion algorithm (MASF), to better capture the remote sensing characteristics of small water bodies in complex areas. Based on this, a dataset containing spectral, texture, and geometric features is constructed, and multi-scale segmentation and random forest algorithms are applied for identification of small water bodies in complex terrain. The results demonstrate that the proposed fusion algorithm MASF exhibits minimal spectral distortion (SAM < 3.5, ERGAS <21, RMSE <0.01) and robust spatial feature enhancement (PSNR >40, SSIM >0.999, CC > 0.99). The Overall Accuracy (OA) and Kappa coefficients for both experimental areas surpassed 0.9. For rivers and reservoirs, both Producer's Accuracy (PA) and User's Accuracy (UA) exceeded 0.9. The UA for agricultural ponds exceeded 0.8. Comparative analysis with three other types of water-related data products shows that the freshwater identification results in this study have certain advantages in local small water bodies. Our research holds significant implications for the utilization of water resources in mountainous areas, prevention and control of floods and floods, as well as the development of aquaculture industry.

Deep learning model based on molecular spectra to determine chlorpyrifos residues in corn oil

This study presents a novel molecular spectroscopy depth fusion strategy for rapid detection of residual chlorpyrifos in corn oil. Raman and Fourier transform near-infrared (FT-NIR) spectrometers were employed to collect contaminated corn oil sample spectra. The multi-spectral fusion enhances spectral features, improving data reliability and outcomes. The research employed low and mid-level fusion strategies alongside a one-dimensional convolutional neural network (1D-CNN) for modeling. The mid-level data fusion model outperformed the low-level model, achieving a relative percent deviation (RPD) of 11.6517 and a prediction coefficient of determination (RP2) of 0.9874. The results indicate that the mid-level fusion strategy is suitable for multivariate model calibration of Raman and FT-NIR, providing a rapid detection method for pesticide residues in edible oils. This study offers a method reference for fusion strategies in molecular spectroscopy and expands the application scope of deep learning in spectroscopy.

Residual spatial fusion network for RGB-thermal semantic segmentation

Semantic segmentation plays an important role in widespread applications such as autonomous driving and robotic sensing. This work focuses on RGB-Thermal (RGB-T) semantic segmentation, since RGB images are easily affected by lighting conditions, e.g., darkness, and thermal images are robust to the night scenario as a compensating modality. However, existing works either simply fuse RGB-T images or adopt the encoder with the same backbone for the two modalities, neglecting the semantic difference under varying lighting conditions. Therefore, we present a Residual Spatial Fusion Network (RSFNet) for RGB-T semantic segmentation. Specifically, RSFNet employs an asymmetric encoder to learn the compensating features of RGB and thermal images. To fuse the dual-modality features, it generates pseudo-labels by adopting the saliency detection skill to supervise feature learning, and develops the Residual Spatial Fusion (RSF) module with structural re-parameterization to learn more promising features by spatially fusing the cross-modality features. RSF adopts a hierarchical feature fusion to aggregate multi-level features, and applies the spatial weights with the residual connection to adaptively control the multi-spectral feature fusion by the confidence gate. Extensive experiments were carried out on two benchmarks, i.e., MFNet database and PST900 database. The results have shown the state-of-the-art segmentation performance of our method, which strikes a good balance between accuracy and speed.

Selection of suitable fusional band combination from Sentinel-2A and UAV imagery for agricultural applications

ABSTRACT This study explores the fusion of Sentinel-2A (S2) and different bands of UAV imagery (Blue, Green, Red and Panchromatic (PAN)) to enhance spatial and spectral information for crop health monitoring. It assesses the quality of fused images, accuracy of the classified fused images and statistical analysis between the fused and S2 vegetation indices. Various fusion techniques are examined to select an optimal combination of bands. The quality of the fused images is evaluated using image quality assessment metrics and classification employs the Random Forest algorithm, assessing accuracy with metrics like F-score and Kappa Coefficient. Statistical analysis involves comparing vegetation indices from fused and S2 imagery. Notably, the fusion of UAV Green and Red bands with S2 imagery, using BT and PCA techniques, emerges as an effective combination for plant-level agricultural health monitoring. This research contributes to advancing precision agriculture techniques by leveraging multispectral imaging fusion for enhanced crop monitoring and management.

Non-destructive discrimination of honey origin based on multispectral information fusion technology

Accurate discrimination of honey origin is of significant importance for safeguarding consumer rights and promoting the sustainable development of apiculture. Spectroscopic techniques, as rapid, efficient, and non-destructive detection methods, have been widely applied in honey research. However, studies often focus on a single analytical technique, limiting the acquisition of comprehensive chemical information and hindering improvements in discrimination accuracy. Data fusion, an information processing technique that enhances test results' accuracy by integrating data from multiple devices, holds vast potential for various applications. Therefore, this study employed data fusion technology to investigate 142 honey samples from five different origins by combining Fourier Transform Mid-Infrared Spectroscopy (FT-MIR) and Raman spectroscopy. Discrimination models based on single-spectral and multispectral Probabilistic Neural Networks (PNN) and Support Vector Machines (SVM) were established using data-level and feature-level fusion strategies. Compared to single-spectral methods, multispectral data fusion significantly improved the geospatial traceability discrimination performance of the models. Particularly, the feature-level fusion strategy demonstrated significant discrimination effectiveness for honey origin. By optimizing the optimal SVM model with the Particle Swarm Optimization (PSO) algorithm, the final test accuracy reached 95.28 %, representing an 11.4 % increase over the best single-spectrum model's test accuracy. Therefore, the establishment of a PSO-SVM discrimination model using feature-level fusion technology enables rapid discrimination of honey origin, providing a reliable and stable method for non-destructive honey origin discrimination.

Monitoring Snow Cover in Typical Forested Areas Using a Multi-Spectral Feature Fusion Approach

Accurate snow cover monitoring is greatly significant for research on the hydrology model and regional climate variation, especially in Northeast China where forests cover almost forty percent of the total area. However, effectively monitoring snow cover under the forest canopy is still challenging with either in situ or remote sensing observations. The global SNOWMAP algorithm pertinent to the fixed normalized difference snow index (NDSI) threshold is, therefore, no longer applicable in a typical forested region of Northeast China. In order to achieve the goal of improving the accuracy of monitoring snow cover in areas with forest, utilizing MOD09GA and MOD13A1 products, a new approach of snow mapping was developed in this study, and it exploits the fusion and coupling of spectral features by integrating and analyzing the normalized difference forest snow index (NDFSI), the normalized difference vegetation index (NDVI), and the NDSI index. Then, Landsat 8 OLI images of high resolution were used to evaluate snow cover mapping precision. The experimental results indicated that the NDFSI index combined with the NDVI index showed great potential for extracting the snow cover distribution in forested regions. Compared with the snow distribution obtained from the Landsat 8 images, the average bias and FAR (false alarm ratio) values of snow cover mapping obtained by this algorithm were 1.23 and 13.54%, which were reduced by 1.98 and 29.36%, respectively. The overall accuracy of 81.31% was reached, which is improved by 20.19%. Thus, the snow classification scheme combining multiple spectral features from MODIS data works effectively in improving the precision of automatic snow cover mapping in typical forested areas of Northeast China, which provides essential support and significant perspectives for the next step of establishing a runoff model and rationally regulating forest water resources.

Scanning Micro X-ray Fluorescence and Multispectral Imaging Fusion: A Case Study on Postage Stamps.

Scanning micrο X-ray fluorescence (μ-XRF) and multispectral imaging (MSI) were applied to study philately stamps, selected for their small size and intricate structures. The μ-XRF measurements were accomplished using the M6 Jetstream Bruker scanner under optimized conditions for spatial resolution, while the MSI measurements were performed employing the XpeCAM-X02 camera. The datasets were acquired asynchronously. Elemental distribution maps can be extracted from the μ-XRF dataset, while chemical distribution maps can be obtained from the analysis of the multispectral dataset. The objective of the present work is the fusion of the datasets from the two spectral imaging modalities. An algorithmic co-registration of the two datasets is applied as a first step, aiming to align the multispectral and μ-XRF images and to adapt to the pixel sizes, as small as a few tens of micrometers. The dataset fusion is accomplished by applying k-means clustering of the multispectral dataset, attributing a representative spectrum to each pixel, and defining the multispectral clusters. Subsequently, the μ-XRF dataset within a specific multispectral cluster is analyzed by evaluating the mean XRF spectrum and performing k-means sub-clustering of the μ-XRF dataset, allowing the differentiation of areas with variable elemental composition within the multispectral cluster. The data fusion approach proves its validity and strength in the context of philately stamps. We demonstrate that the fusion of two spectral imaging modalities enhances their analytical capabilities significantly. The spectral analysis of pixels within clusters can provide more information than analyzing the same pixels as part of the entire dataset.

UAV-Based Wetland Monitoring: Multispectral and Lidar Fusion with Random Forest Classification

As sea levels rise and temperatures increase, vegetation communities in tropical and sub-tropical coastal areas will be stressed; some will migrate northward and inland. The transition from coastal marshes and scrub–shrubs to woody mangroves is a fundamental change to coastal community structure and species composition. However, this transition will likely be episodic, complicating monitoring efforts, as mangrove advances are countered by dieback from increasingly impactful storms. Coastal habitat monitoring has traditionally been conducted through satellite and ground-based surveys. Here we investigate the use of UAV-LiDAR (unoccupied aerial vehicle–light detection and ranging) and multispectral photogrammetry to study a Florida coastal wetland. These data have higher resolution than satellite-derived data and are cheaper and faster to collect compared to crewed aircraft or ground surveys. We detected significant canopy change in the period between our survey (2020–2022) and a previous survey (2015), including loss at the scale of individual buttonwood trees (Conocarpus erectus), a woody mangrove associate. The UAV-derived data were collected to investigate the utility of simplified processing and data inputs for habitat classification and were validated with standard metrics and additional ground truth. UAV surveys combined with machine learning can streamline coastal habitat monitoring, facilitating repeat surveys to assess the effects of climate change and other change agents.

A dual-branch neural network for crop disease recognition by integrating frequency domain and spatial domain information

Crop diseases severely affect crop yield and quality, and accurate identification of crop diseases is crucial for disease management. Although deep neural networks have made progress in the task of crop disease identification, the complex environment of crop diseases, including background interference, morphological differences, and scale variations, has led to limited accuracy in disease recognition. To address these issues, this study proposes a dual-branch deep neural network for crop disease identification, integrating both frequency domain and spatial domain information. The frequency branch takes frequency domain information as input to extract rich crop disease frequency component features, while the deformable attention Transformer branch excels in representing global features and selectively focusing on local features of crop diseases. A new fusion method, Multi-Spectral Channel Attention Fusion (MSAF), is adopted to better integrate crop disease frequency and spatial features. Additionally, an improved bias loss function (cv_bias) is proposed to optimize the dual-branch network model, achieving an accuracy of 96.7 % on the test dataset, which is 2.0 % higher than the existing state-of-the-art deformable attention Transformer model. With only 14 M model parameters, this study's model provides an effective method for future applications in complex environment.

MineCam: Application of Combined Remote Sensing and Machine Learning for Segmentation and Change Detection of Mining Areas Enabling Multi-Purpose Monitoring

Our study addresses the need for universal monitoring solutions given the diverse environmental impacts of surface mining operations. We present a solution combining remote sensing and machine learning techniques, utilizing a dataset of over 2000 satellite images annotated with ten distinct labels indicating mining area components. We tested various approaches to develop comprehensive yet universal machine learning models for mining area segmentation. This involved considering different types of mines, raw materials, and geographical locations. We evaluated multiple satellite data set combinations to determine optimal outcomes. The results suggest that radar and multispectral data fusion did not significantly improve the models’ performance, and the addition of further channels led to the degradation of the metrics. Despite variations in mine type or extracted material, the models’ effectiveness remained within an Intersection over Union value range of 0.65–0.75. Further, in this research, we conducted a detailed visual analysis of the models’ outcomes to identify areas requiring additional attention, contributing to the discourse on effective mining area monitoring and management methodologies. The visual examination of models’ outputs provides insights for future model enhancement and highlights unique segmentation challenges within mining areas.

Assessing the Efficacy of Pixel-Level Fusion Techniques for Ultra-High-Resolution Imagery: A Case Study of BJ-3A.

Beijing Satellite 3 is a high-performance optical remote sensing satellite with a spatial resolution of 0.3-0.5 m. It can provide timely and independent ultra-high-resolution spatial big data and comprehensive spatial information application services. At present, there is no relevant research on the fusion method of BJ-3A satellite images. In many applications, high-resolution panchromatic images alone are insufficient. Therefore, it is necessary to fuse them with multispectral images that contain spectral color information. Currently, there is a lack of research on the fusion method of BJ-3A satellite images. This article explores six traditional pixel-level fusion methods (HPF, HCS, wavelet, modified-IHS, PC, and Brovey) for fusing the panchromatic image and multispectral image of the BJ-3A satellite. The fusion results were analyzed qualitatively from two aspects: spatial detail enhancement capability and spectral fidelity. Five indicators, namely mean, standard deviation, entropy, correlation coefficient, and average gradient, were used for quantitative analysis. Finally, the fusion results were comprehensively evaluated from three aspects: spectral curves of ground objects, absolute error figure, and object-oriented classification effects. The findings of the research suggest that the fusion method known as HPF is the optimum and appropriate technique for fusing panchromatic and multispectral images obtained from BJ-3A. These results can be utilized as a guide for the implementation of BJ-3A panchromatic and multispectral data fusion in real-world scenarios.

Multi-spectral fusion and self-attention mechanisms for Gentiana origin identification via near-infrared spectroscopy

Gentiana is rich in Gentiopicroside and strychnine acid with medicinal value. However, the active ingredients of Gentiana from different origins are different, so identifying Gentian's origin is significant. Currently, neural networks such as CNN and GRU are widely used for spectral data analysis, but the modeling effect is easily affected by the spectral preprocessing method, and the long region and many features of spectral data make it difficult for CNN models to capture the long-term dependence of spectra, while GRU modeling has a large number of parameters, high computational complexity, and low efficiency. Therefore, a Gentian Root Data Fusion Module (GL) for sequence data is proposed to achieve the fusion between spectral data under different pre-processing by assigning weights to multiple pre-processing data and all features of pre-processing data respectively, making full use of the advantages of different pre-processing methods. Aiming at the characteristics of the long spectral data region, the joint architecture of convolutional neural network (CNN) and gated neural network (GRU) is adopted to achieve the extraction of features and the capture of long-term dependencies, while reducing the model complexity. Finally, GL is integrated with CNN and GRU to craft the advanced collaborative framework known as CCRN. The experimental findings demonstrate that CCRN outperforms CNN + GRU, CNN, PLS-DA, and SVM in terms of accuracy and loss function performance. Notably, CCRN exhibits superior Accuracy, Recall, and F1-score, surpassing the CNN + GRU model by 2.4 %, 2.1 %, and 2.1 %, respectively. These results validate the efficacy of the GL module in seamlessly integrating various preprocessing methods. In addition, the model CCRN still performs best when tested on public datasets, proving that CCRN has good Portability and scalability.

Deep saliency detection-based pedestrian detection with multispectral multi-scale features fusion network

In recent years, there has been increased interest in multispectral pedestrian detection using visible and infrared image pairs. This is due to the complementary visual information provided by these modalities, which enhances the robustness and reliability of pedestrian detection systems. However, current research in multispectral pedestrian detection faces the challenge of effectively integrating different modalities to reduce miss rates in the system. This article presents an improved method for multispectral pedestrian detection. The method utilises a saliency detection technique to modify the infrared image and obtain an infrared-enhanced map with clear pedestrian features. Subsequently, a multiscale image features fusion network is designed to efficiently fuse visible and IR-enhanced maps. Finally, the fusion network is supervised by three loss functions for illumination perception, light intensity, and texture information in conjunction with the light perception sub-network. The experimental results demonstrate that the proposed method improves the logarithmic mean miss rate for the three main subgroups (all day, day and night) to 3.12%, 3.06%, and 4.13% respectively, at “reasonable” settings. This is an improvement over the traditional method, which achieved rates of 3.11%, 2.77%, and 2.56% respectively, thus demonstrating the effectiveness of the proposed method.

Hyperspectral Image Fusion via a Novel Generalized Tensor Nuclear Norm Regularization.

Recently, low-rank tensor regularization has received more and more attention in hyperspectral and multispectral fusion (HMF). However, these methods often suffer from inflexible low-rank tensor definition and are highly sensitive to the permutation of tensor modes, which hinder their performance. To tackle this problem, we propose a novel generalized tensor nuclear norm (GTNN)-based approach for the HMF. First, we define a novel GTNN by extending the existing third-mode-based tensor nuclear norm (TNN) to arbitrary mode, which conducts the Fourier transform on an arbitrary single mode and then computes the TNN for each mode. In this way, we can not only capture more extensive correlations for the three modes of a tensor, and also omit the adverse effect of permutation of tensor modes. To utilize the correlations among spectral bands, the high-resolution hyperspectral image (HSI) is approximated as low-rank spectral basis multiplication by coefficients, and we estimate the spectral basis by conducting singular-value decomposition (SVD) on HSI. Then, the coefficients are estimated by addressing the proposed GTNN regularized optimization. In specific, to exploit the non-local similarities of the HSI, we first cluster the patches of the coefficient into a 3-D, which contains spatial, spectral, and non-local modes. Since the collected tensor contains the strong non-local spatial-spectral similarities of the HSI, the proposed low-rank tensor regularization is imposed on these collected tensors, which fully model the non-local self-similarities. Fusion experiments on both simulated and real datasets prove the advantages of this approach. The code is available at https://github.com/renweidian/GTNN.

Multiscale Cross-Modal Homogeneity Enhancement and Confidence-Aware Fusion for Multispectral Pedestrian Detection

Multispectral pedestrian detection has shown many advantages in a variety of environments, particularly poor illumination conditions, by leveraging visible-thermal modalities. However, in-depth insight into distinguishing the complementary content of multimodal data and exploring the extent of multimodal feature fusion is still lacking. In this paper, we propose a novel multispectral pedestrian detector with multiscale cross-modal homogeneity enhancement and confidence-aware feature fusion. RGB and thermal streams are constructed to extract features and generate candidate proposals. During feature extraction, multiscale cross-modal homogeneity enhancement is proposed to enhance single-modal features using the separated homogeneous features via modal interactions. Homogeneity features encode the semantic information of the scene and are extracted from the RGB-thermal pairs by employing a channel attention mechanism. Proposals from two modalities are united to obtain multimodal proposals. Then, confidence measurement fusion is proposed to achieve multispectral feature fusion in each proposal by measuring the internal confidence of each modality and the interaction confidence between modalities. In addition, a confidence transfer loss function is designed to focus more on hard-to-detect samples during training. Experimental results on two challenging datasets demonstrate that the proposed method achieves better performance compared to existing methods.