Multispectral images contain richer spectral signatures than easily available RGB images, for which they are promising to contribute to information perception. However, the relatively high cost of multispectral sensors and lower spatial resolution limit the widespread application of multispectral data, and existing reconstruction algorithms suffer from a lack of diverse training datasets and insufficient reconstruction accuracy. In response to these issues, this paper proposes a novel and robust multispectral reconstruction network from low-cost natural color RGB images based on free available satellite images with various land cover types. First, to supplement paired natural color RGB and multispectral images, the Houston hyperspectral dataset was used to train a convolutional neural network Model-TN for generating natural color RGB images from true color images combining CIE standard colorimetric system theory. Then, the EuroSAT multispectral satellite images for eight land cover types were selected to produce natural RGB using Model-TN as training image pairs, which were input into a residual network integrating channel attention mechanisms to train the multispectral images reconstruction model, Model-NM. Finally, the feasibility of the reconstructed multispectral images is verified through image classification and target detection. There is a small mean relative absolute error value of 0.0081 for generating natural color RGB images, which is 0.0397 for reconstructing multispectral images. Compared to RGB images, the accuracies of classification and detection using reconstructed multispectral images have improved by 16.67% and 3.09%, respectively. This study further reveals the potential of multispectral image reconstruction from natural color RGB images and its effectiveness in target detection, which promotes low-cost visual perception of intelligent unmanned systems.

In recent years, the UAV has become a convenient platform to obtain multi-angle reflectance observations and study bi-directional reflectance distribution function (BRDF) characteristics at a higher spatial resolution than satellite. However, only a few vegetation types were concerned in previous studies, leading to a lack of BRDF knowledge for various objects and preventing further recognition application. In this study, UAV-based multi-angle observations were collected for six typical natural and artificial targets including larch forest, grass, artificial turf, asphalt road, cement hut, and model plane. Firstly, fitting accuracy of directional reflectance was calculated, and then we analyzed the variance patterns of spectral and anisotropic indices along with spatial resolutions (i.e., 1-100 m). The results show that: (1) The RTLSR_C kernel-driven model is still applicable for UAV with fitting RMSEs of reflectance less than 0.05, showing multi-scale adaptability for both UAV and satellite; (2) For grass and artificial turf, the normalized difference vegetation index (NDVI) decreases as spatial resolution increases, and a significant change with view zenith angle can be observed with the minimum at the hotspot; (3) The anisotropic flat index (AFX) varies with ground types, light, shadows, and sample spatial homogeneity. Notably, there is a sudden change in AFX for larch forest at 5 m near canopy width. Similar NDVI and AFX values are found between grass and artificial turf. This study further reveals BRDF patterns for new target types at varying spatial scales, providing evidence for the applicability of the kernel-driven model at high spatial resolution and target camouflage.

The anisotropic reflectance characteristic (i.e., bidirectional reflectance distribution function (BRDF) effect) lays the foundation of quantitative remote sensing, while it is difficult to reconstruct at high spatial resolution due to near-nadir small-angle observations. Based on the traditional archetype inversion algorithm, this study explores and evaluates a two-step method considering vegetation structure clustering to retrieve fine-scale BRDF, using LESS simulated sufficient multiangle reflectances in forest scenes at multiple scales. First, full inversion of the kernel-driven model RTLSR_C was performed to investigate the BRDF feature at 1–50 m. Subsequently, the sensitivity of normalized difference vegetation index (NDVI) and anisotropic flat index (AFX) to forest structure was comprehensively analyzed. For reflectances at small view zenith angles (VZAs) of 0° and 15° close to Sentinel multispectral instrument (MSI) observations at 5, 10, and 25 m, forest structure cluster-based BRDF parameters were first retrieved based on accumulated intraclass reflectances, where prior BRDF information from 50-m LESS data and 500-m MODIS global representative sites were compared. Finally, cluster-based BRDF parameters were used as prior archetypes to retrieve pixel BRDF. Results show good fitting root mean square errors (RMSEs) for full inversion, with most average RMSEs below 0.05, and spectral and angular reflectance are sensitive to the fraction of vegetation cover (FVC), tree height, and crown length at 5 m and larger scales. In addition, the two-step method based on structure clustering yields a slightly higher BRDF inversion accuracy than that of the one-step method, and the traditional one-step archetype inversion algorithm demonstrates its simplicity and accuracy. This study provides new insights for fine-scale BRDF inversion.

With the development of uncrewed aerial vehicle (UAV) multiangle and multispectral observation, whether bi-directional reflectance distribution function (BRDF) models are applicable to high spatial resolution has become the focus of researchers. However, previous studies usually focus on soil-vegetation BRDF models, limited to certain natural types. In this study, UAV multispectral and multiangle observations were conducted over both natural and artificial targets, to investigate the heterogeneity and similarity among different targets. Five representative BRDF models were selected for inversion, including the Walthall model, the seven-parameter model with double-peak, the RossThick-LiSparseReciprocal-Chen (RTLSR_C) kernel-driven model, the Enhanced Rahman–Pinty–Verstraete (ERPV) model, and the Hemisphere Harmonics (HSH) basis model. To compare the ability of these models in capturing the optical scattering characteristics, observation data from different observation planes were used for fitting. The results show that: (1) The five selected BRDF models generally remain applicable at the UAV scale based on the fitting RMSEs. (2) When only the cross principal plane (CPP) data are used, the RTLSR_C model achieves the best inversion performance. When only the principal plane (PP) data are used, the ERPV model performs best. (3) The multispectral characteristics of the green camouflage net are most similar to that of the grassland.

Considering the simplicity of flight route planning, orthorectified images obtained from nadir observations are widely used in remote sensing. However, they are always insufficient to represent the anisotropic reflectance and three-dimensional (3D) structural information of objects. Therefore, multi-angle observation information can enhance target information and potentially improve the accuracy of target classification and recognition. In this study, we investigated the potential of anisotropic reflectance information in land cover classification. By employing the DJI P4M multispectral observation system, multi-angle multi-spectral reflectance images for five land cover types were captured at bare soil, concrete roads, grassland, apricot tree, and red broom cypress areas. Subsequently, the AFX-based BRDF archetypes model and the kernel-driven model were used to reconstruct the bidirectional reflectance distribution function (BRDF). Finally, land cover classification was performed using three types of machine learning algorithm considering different BRDF features and band combinations. The results indicate that, compared to nadir directional reflectance, multi-angle feature sets can improve the overall classification accuracy up to 24%. Compared to using single-band information, band combinations can also improve that up to 54%. The overall accuracy using the feature set of kernel-driven model parameters and nadir reflectance was also enhanced significantly, which can reach 86% using green-red-near infrared band combinations. This work demonstrates the contribution of multi-angle multi-spectral information to natural and artificial land cover classification.

Accurate target characterization extraction under overcast conditions is a great challenge for all-weather quantitative remote sensing. Although existing atmospheric correction methods based on optical scattering models can effectively mitigate image interference, their performance often depends on numerical simulations or idealized atmospheric assumptions, lacking systematic validation in real and complex environments. In this study, we assess the performance of a diffuse light correction (DLC) form of the Ross-Li kernel-driven BRDF model using multi-angular and multi-spectral reflectance data acquired by the DJI P4M platform over identical surfaces under both overcast and clear skies. Experimental results demonstrate that the model significantly suppresses the smoothing effect of anisotropic reflectance features near the hotspot, and the BRDF inversion accuracy are comparable to those obtained under clear-sky conditions with RMSEs less than 0.02 in average. This study validates the practicality and effectiveness of the improved kernel-driven model using field observations for the first time, providing critical data and theoretical insight for advancing all-weather operational remote sensing applications.