The regularized alternating least squares (ALS) is a widely used method for computing the CP decomposition of tensors. Existing convergence analyses for the regularized ALS are limited to first-order stationary points. In this work, we study its second-order convergence and prove that, with random initialization, the regularized ALS almost surely avoids strict saddle points. These results provide stronger theoretical guarantees for the effectiveness of regularized ALS in practical tensor approximation tasks.

Recently, principal skewness analysis (PSA) has been introduced into the domain of feature extraction. It is equivalent to the skewness version of Fast independent component analysis (FastICA). Unlike FastICA, PSA does not require all sample points when searching for the projection directions, making it faster. However, for the data of dimension$L$, PSA needs to calculate the eigenvectors of$L$tensors, each of size$L\times L\times L$. When$L$is large, PSA still requires significant computational time to find all projection directions. In this letter, we find that the$(m+1)$th projection direction in PSA can be obtained by calculating the eigenvector of a tensor of size$(L-m)\times (L-m)\times (L-m)$. Furthermore, we propose a fast version of PSA (FastPSA) that is mathematically equivalent to PSA. The experimental results demonstrate that FastPSA has lower computational complexity than PSA.

Abstract Multi‐graph matching (MGM), which aims to find correspondences among multiple graphs, is an extension of conventional two‐graph matching. Existing MGM methods fall into two categories: pairwise based and tensor based. Pairwise‐based methods consider similarities between every two features; while tensor‐based methods consider the overall similarity among all features, offering much more flexibility similarity measurements and less information loss, but at the cost of exorbitant computational demands. Here, a fresh perspective on MGM task is delivered, that is, matching based on any k features. It enables the consideration of more complex affinity relationship beyond pairwise while keeping computational demands within a manageable threshold. Furthermore, a factorization technique for the k ‐wise global affinity matrix is proposed, significantly reducing space complexity. This approach unifies existing MGM methods and inspires future research focusing on k ‐wise affinity relationship, showcasing both theoretical and practical advancements in the field. Experiments on synthetic and real‐world datasets demonstrate the superiority of our method.

Vision-language models have demonstrated impressive capabilities in associating images and text by pretraining on extensive image-text paired data. The paradigm of continual pretraining followed by fine-tuning has become prevailing for boosting performance in domain-specific tasks under constrained computation resources. Benefiting from the superior generalization abilities of foundation models, the demands for computational resources and extensive data corpora have been significantly reduced. Nonetheless, it is crucial to tailor the model for the characteristics of downstream tasks to mitigate the misalignment between the pretraining pretext tasks and actual applications of interest. In this study, we utilize a CLIP-based model that has been continually pretrained on the 5 million image-text dataset in the remote sensing field as the foundation model, focusing on cross-modal image-text retrieval tasks. We introduce an efficient framework called remote sensing image-text retrieval fine-grained fine-tuning (RSITR-FFT), which refines the feature space by introducing fine-grained word-region alignment and incorporating consistency constraint regularization terms in the learning objectives. The fine-grained alignment aims for precise word-region correspondence beyond classical global-level image-text matching, while the consistency regularization encourages geometric coherence between the image and text modalities. Remarkably, our method achieves observable performance improvements while requiring far fewer fine-tuning samples—about 10 000, in contrast to the 400 million and 5 million samples used during the CLIP’s initial pretraining and GeoRSCLIP’s continual pretraining stages, respectively. We perform quantitative evaluation on RSICD, NWPU-Captions, and UCM-Captions datasets to demonstrate the effectiveness of RSITR-FFT. We further showcase its realistic application on the high-resolution remote sensing imagery through the qualitative visualization experiments on the FAIR1M-1.0 dataset. The code and models are available athttps://github.com/d1x1u/RSITR-FFT.

Independent component analysis (ICA) is one of the widely used techniques in remote sensing feature extraction. When selecting high-order statistics (HOS) as non-Gaussian metric, the determination of independent components (ICs) can be attributed to calculating the eigenpairs of HOS tensors of the mixed data. However, previous algorithms can only obtain approximate solutions for eigenpairs, and the accuracy of ICs may be unavoidably affected. Recently, a homotopy-based tensor eigenpairs (HTE) method that can obtain accurate solutions has been proposed. In this letter, we introduce it into the ICA field and further propose a modified version, termed modified HTE (MHTE). MHTE incorporates the concept of the projected Hessian matrix into HTE, which can further improve the accuracy of ICs and also intellectually determine the number of ICs. Experiments with both simulated image and remote sensing image demonstrate that it is more accurate and parameter adaptive than other compared feature extraction algorithms.

The hierarchical constrained energy minimization (hCEM) algorithm, published in TGRS, has received more attentions in the field of hyperspectral target detection since publication. Using the classical constrained energy minimization (CEM) detector as the basic unit, it designs a hierarchical structure to gradually suppress the background and to enhance the target detection performance. The authors claimed that the convergence of the hCEM algorithm can be theoretically guaranteed by analyzing the realtionship between different layers of the hierarchical output. However, after some investigations, we found that the key formula presented in the paper is theoretically defective. This implies that the theoretical results do not hold and the convergence of the algorithm cannot be ensured.

It has been proved that the determination of independent components (ICs) in the independent component analysis (ICA) can be attributed to calculating the eigenpairs of high-order statistical tensors of the data. However, previous works can only obtain approximate solutions, which may affect the accuracy of the ICs. In addition, the number of ICs would need to be set manually. Recently, an algorithm based on semidefinite programming (SDP) has been proposed, which utilizes the first-order gradient information of the Lagrangian function and can obtain all the accurate real eigenpairs. In this article, for the first time, we introduce this into the ICA field, which tends to further improve the accuracy of the ICs. Note that the number of eigenpairs of symmetric tensors is usually larger than the number of ICs, indicating that the results directly obtained by SDP are redundant. Thus, in practice, it is necessary to introduce second-order derivative information to identify local extremum solutions. Therefore, originating from the SDP method, we present a new modified version, called modified SDP (MSDP), which incorporates the concept of the projected Hessian matrix into SDP and, thus, can intellectually exclude redundant ICs and select true ICs. Some cases that have been tested in the experiments demonstrate its effectiveness. Experiments on the image/sound blind separation and real multi/hyperspectral image also show its superiority in improving the accuracy of ICs and automatically determining the number of ICs. In addition, the results on hyperspectral simulation and real data also demonstrate that MSDP is also capable of dealing with cases, where the number of features is less than the number of ICs.

In recent years, deep learning has been successfully applied in the field of synthetic aperture radar (SAR) image object detection. However, unlike ships and tanks targets, the oil tank targets in SAR image are usually dense and compact with more overlaps and discrete scattering centers, which greatly increases the difficulty of extracting location and structural parameters. Most of the existing methods transfer the methods suitable for natural image to the SAR image field, without considering the unique characteristics of SAR image. Therefore, in this article, we propose an improved model based on the end-to-end transformer network, which is the first model introducing transformer network to 3-D detection of oil tank targets from single SAR image. We input the incidence angle into the transformer model as a priori token. Then, we propose a feature description operator (FDO) based on the scattering centers that are used as an aid to improve the precision of predictions. In addition, we also propose a cylinder IOU as a more suitable evaluation metric for 3-D detection of oil tank. Finally, we evaluate our model on an SAR image dataset that contains SAR images from RADARSAT-2, TerraSAR-X, and GF-3 with different incidence angles. Our experiments demonstrate that our proposed model achieves the AP of 77.6% compared with 60.8% of baseline, which proves the effectiveness of the introduction of observation conditions, cylinder IOU loss (CI Loss), and the FDO based on the scattering centers in our model and is appealing for 3-D detection of oil tank.

Target detection is always an important topic in the field of hyper/multispectral remote sensing image processing. At present, target detection algorithms in this field are generally limited to processing single-temporal remote sensing data, and they cannot obtain satisfactory results when the spectra of target and background are similar to each other. Recently, a target detection algorithm called filter tensor analysis (FTA), which is specially designed for multitemporal remote sensing data, has been reported and has achieved better detection results in many cases than the traditional single-temporal methods. However, FTA can only extract one target of interest at a time, and it cannot work when there are multiple targets of interest in the image. Therefore, considering that the matrix form of the FTA method is similar to that of the constrained energy minimization (CEM) model, it naturally comes to us that we can combine the tensor filter in FTA and the multiple target constraints to detect multiple targets by fully exploiting the time-series information in multitemporal data. To be specific, through: 1) adding the “output to one” constraints to the multiple targets in FTA; 2) applying linear/nonlinear function to the outputs of FTA for the multiple targets; and 3) modifying the autocorrelation matrix in FTA, four multitarget detection algorithms for multitemporal remote sensing data are proposed in this article. Experiments with simulation data and real data both show the effectiveness and superiority of the proposed methods.

Recently, the volume-gradient-based band selection (VGBS) method has attracted more and more attention in the field of band selection. It is a ranking-based unsupervised algorithm which applies the sequential backward selection strategy to successively remove the most abundant band. The key finding of VGBS is that the band redundancy corresponds to the volume gradient matrix with respect to hyperspectral images. However, we have found that VGBS requires to update the gradient matrix after each band removal, which includes the calculation of the matrix inverse, determinant, and multiplication, and thus is time-consuming when the number of bands is large. In this letter, we first find that the norm of the row of the gradient matrix has a one-to-one correspondence to the diagonal element of the covariance matrix of the image. Further, we develop a recursive formula to calculate the inverse of the covariance matrix. The experimental results show the effectiveness of the method, i.e., we can reduce the computational complexity of VGBS with an order of magnitude.

As one of the most important algorithms in target detection, constrained energy minimization (CEM) has been widely used and developed in recent years. However, it is easy to verify that the target detection result of CEM varies with the data origin, which is apparently unreasonable since the distribution of the target of interest is objective and, therefore, unrelated to the selection of data origin. The clever eye (CE) algorithm tries to solve this problem by adding the data origin as a new variable from the perspective of the filter output energy. However, due to the nonconvexity of the objective function, CE can only obtain locally optimal solutions by using the gradient ascent method. In this article, we find a striking conclusion that there exists an analytical solution for CE that corresponds to the solution of a linear equation and further prove that all the solutions of the linear equation are globally optimal.

Translation matching is one of the most fundamental problems in the field of image matching, and the normalized cross-power spectrum (NCPS)-based methods have achieved great success regarding this problem. However, when the images to be matched are seriously corrupted by noise, most current NCPS-based methods cannot obtain satisfactory results. Besides, the 2-D phase extraction of the NCPS, which is required in most NCPS-based methods, may cause an additional error to the final result. In this article, we proposed the concept of autocorrelated NCPS (ANCPS) that is theoretically proved to be able to significantly alleviate the influence of noise and developed a new method based on it. Furthermore, by utilizing the property of equal phase interval of ANCPS, the 2-D phase extraction problem is also naturally avoided in our method. The experiments with simulated and real data demonstrate that the presented method has a better performance in both accuracy and antinoise performance compared with state-of-the-art methods.

Endmember determination is a key step of spectral unmixing, which decomposes a mixed pixel into endmembers and corresponding fractional abundances for hyperspectral imagery. So far, convex geometry-based endmember determination methods have attracted much attention due to their clear physical meaning and light computational burden. Recently, a Fast Gram Determinant-based Algorithm (FGDA) has been proposed as an efficient endmember determination method for hyperspectral imagery. In this letter, we further implement the derivation of endmember score index (ESI) defined in FGDA. From the algebra and geometric view, we find interestingly that the ESI is actually the height of a new vertex to the hyperplane or simplex linear spanned by previously found endmembers (base), and essentially the FGDA is equivalent to the Automatic Target Generation Process (ATGP) when their initial condition is the same.

Principal skewness analysis (PSA) has been introduced for feature extraction in hyperspectral imagery. As a thirdorder generalization of principal component analysis (PCA), its solution of searching for the local maximum skewness direction is transformed into the problem of calculating the eigenpairs (the eigenvalues and the corresponding eigenvectors) of a coskewness tensor. By combining a fixed-point method with an orthogonal constraint, the new eigenpairs are prevented from converging to the same previously determined maxima. However, in general, the eigenvectors of the supersymmetric tensor are not inherently orthogonal, which implies that the results obtained by the search strategy used in PSA may unavoidably deviate from the actual eigenpairs. In this paper, we propose a new nonorthogonal search strategy to so lve this problem and the new algorithm is named nonorthogonal principal skewness analysis (NPSA). The contribution of NPSA lies in the finding that the search space of the eigenvector to be determined can be enlarged by using the orthogonal complement of the Kronecker product of the previous eigenvector with itself, instead of its orthogonal complement space. We also give a detailed theoretical proof on why we can obtain the more accurate eigenpairs through the new search strategy by comparison with PSA. In addition, after some algebraic derivations, the complexity of the presented algorithm is also greatly reduced. Experiments with both simulated data and real multi/hyperspectral imagery demonstrate its validity in feature extraction.

For numerous applications in image registration, sub-pixel translation estimation is a fundamental task, and increasing attention has been given to methods based on image phase information. However, we have found that none of these methods is universal. In other words, for any one of these methods, we can always find some image pairs which will not be well matched. In this paper, by introducing the cyclic shift matrix (CSM), we present a new model for the translation matching problem and derive a least squares solution for the model. In addition, by repeatedly applying the CSM to the matching image, an iterative CSM method is proposed to further improve the matching accuracy. Furthermore, we show that the traditional phase-based matching algorithms can only achieve an exact solution when there is a cyclic shift relationship between the images to be matched. The proposed method is evaluated using simulated and real images and demonstrates a better performance in both accuracy and robustness compared with the state-of-the-art methods.

In[1], the affiliation for the authors was incorrect in the first footnote. It should be as follows.

Non-negative matrix factorization (NMF) has been widely used in mixture analysis for hyperspectral remote sensing. When used for spectral unmixing analysis, however, it has two main shortcomings: (1) since the dimensionality of hyperspectral data is usually very large, NMF tends to suffer from large computational complexity for the popular multiplicative iteration rule; (2) NMF is sensitive to noise (outliers), and thus the corrupted data will make the results of NMF meaningless. Although principal component analysis (PCA) can be used to mitigate these two problems, the transformed data will contain negative numbers, hindering the direct use of the multiplicative iteration rule of NMF. In this paper, we analyze the impact of PCA on NMF, and find that multiplicative NMF can also be applicable to data after principal component transformation. Based on this conclusion, we present a method to perform NMF in the principal component space, named ‘principal component NMF’ (PCNMF). Experimental results show that PCNMF is both accurate and time-saving.

Simplex volume is the most commonly used parameter for endmember extraction. However, when outliers exist in the image, the maximum-volume-criterion (MVC)-based methods tend to extract them as endmembers. Those outlier endmembers could be either physically meaningless or not representative enough for prevalent land covers. This is the biggest bottleneck preventing MVC-based methods from being extended from theoretical analysis to practical applications. This is mainly due to the limitation of the simplex volume formula itself, which is only determined by simplex vertices and completely ignoring the statistics of the data cloud. Usually, the simplex with vertices containing outliers has a larger volume than the one with vertices only containing true endmembers; thus, outliers are more favorably extracted as endmembers. Usually, the outliers are distributed in the direction of low information content. When extracted endmembers contain outliers, the overall information content (OIC) of the data cloud projected onto the endmember subspace will be definitely reduced. Motivated by this fact, we present the concept of statistical volume and develop a new endmember extraction method, which is named statistical volume analysis (SVA). The algorithm simultaneously utilizes the geometrical property of the simplex and the statistical characteristic of the projected data in the endmember subspace. Therefore, SVA not only can find a simplex with a large volume but also can get a large OIC of the projected data. Experiments with both simulated and real data show that SVA can compete with state-of-the-art methods in extracting endmembers of prevalent land covers. Moreover, it is capable of avoiding extracting outliers as endmembers.

Principal skewness analysis (PSA) has been introduced to the remote sensing community recently, which is equivalent to fast independent component analysis (FastICA) when skewness is considered as a non-Gaussian index. However, similar to FastICA, PSA also has the nonconvergence problem in searching for optimal projection directions. In this letter, we propose a new iteration strategy to alleviate PSA's nonconvergence problem, and we name this new version of PSA as momentum PSA (MPSA). MPSA still adopts the same fixed-point algorithm as PSA does. Different from PSA, the (k + 1)th result in the iteration process of MPSA not only depends on the kth iteration result but also is related to the (k - 1)th iteration. Experiments conducted for both simulated data and real-world hyperspectral image demonstrate that MPSA has an obvious advantage over PSA in convergence performance and computational speed.

Band selection (BS) plays an important role in the dimensionality reduction of hyperspectral data. However, as to the existing BS methods, few are specially designed for target detection. In this letter, we combine the target detection and BS process together and put forward a new BS method for target detection, named least absolute shrinkage and selection operator (LASSO)-based BS (LBS). Interestingly, by using a linear regression model with L1 regularization (LASSO model), LBS transforms the discrete BS problem into the continuous optimization problem, which cannot only avoid the complicated subset selection process but also evaluate the importance of all the bands simultaneously. The experiments on real hyperspectral data demonstrate that LBS is a very effective BS method for target detection.

How to find the representative bands is a key issue in band selection for hyperspectral data. Very often, unsupervised band selection is associated with data clustering, and the cluster centers (or exemplars) are considered ideal representatives. However, partitioning the bands into clusters may be very time-consuming and affected by the distribution of the data points. In this letter, we propose a new band selection method, i.e., exemplar component analysis (ECA), aiming at selecting the exemplars of bands. Interestingly, ECA does not involve actual clustering. Instead, it prioritizes the bands according to their exemplar score, which is an easy-to-compute indicator defined in this letter measuring the possibility of bands to be exemplars. As a result, ECA is of high efficiency and immune to distribution structures of the data. The experiments on real hyperspectral data set demonstrate that ECA is an effective and efficient band selection method.

The linear mixture model (LMM) plays a crucial role in the spectral unmixing of hyperspectral data. Under the assumption of LMM, the solution with the minimum reconstruction error is considered to be the ideal endmember. However, for practical hyperspectral data sets, endmembers that enclose all the pixels are physically meaningless due to the effect of noise. Therefore, in many cases, it is not sufficient to consider only the reconstruction error, some constraints (for instance, volume constraint) need to be added to the endmembers. The two terms can be considered as serving two forces: minimizing the reconstruction error forces the endmembers to move outward and thus enlarges the volume of the simplex while the endmember constraint acts in the opposite direction by driving the endmembers to move inward so as to constrain the volume to be smaller. Many existing methods obtain their solution just by balancing the two contradictory forces. The solution acquired in this way can not only minimize the reconstruction error but also be physically meaningful. Interestingly, we find, in this paper, that the two forces are not completely contradictory with each other, and the reconstruction error can be further reduced without changing the volume of the simplex. And more interestingly, our method can further optimize the solution provided by all the endmember extraction methods (both endmember selection methods and endmember generation methods). After optimization, the final endmembers outperform the initial solution in terms of reconstruction error as well as accuracy. The experiments on simulated and real hyperspectral data verify the validation of our method.

In this letter, we present a new feature extraction approach based on third-order statistics (coskewness tensor) called principal skewness analysis (PSA). PSA is the natural extension of principal components analysis from second-order statistics to third-order statistics. The result of PSA is equivalent to that of FastICA when skewness is considered as a non-Gaussian index. Similar to FastICA, PSA also applies the fixed-point method to search the skewness extreme directions. However, when calculating the new projected direction in each iteration, PSA only requires a coskewness tensor, whereas FastICA requires all the pixels to be involved. Therefore, PSA has an advantage over FastICA in speed.

Target detection has recently drawn considerable interest in hyperspectral image processing. People tend to exclude corrupted or badly damaged bands before applying the target detection algorithm to the data for better detection results. In this letter, it is proved that adding any band independent of the original image, even a noisy band, would be always beneficial to the performance of constrained energy minimization in terms of output energy. Finally, several tests are conducted to further justify our viewpoint.

In the field of endmember extraction, most methods involve calculating the volume of simplex in high-dimensional space. Two different simplex volume formulas are used in these methods. One requires dimensionality reduction (DR); therefore, it may result in loss of the information of targets classes with a low priori probability, such as that used in N-FINDR. The other one, which is based on Gram determinant, avoids DR but is time consuming. In this letter, we explain a recursion rule of the calculation for the second simplex volume. Based on that rule, this letter presents a fast endmember extraction algorithm named as Fast Gram Determinant based Algorithm (FGDA). The theoretical analysis and experiments on both simulated and real hyperspectral data demonstrate that, compared to other volume-based methods, FGDA can greatly reduce the computational complexity of endmember extraction.

In this paper, a subtle relationship is found between the volume of a subsimplex and the volume gradient of a simplex with respect to hyperspectral images. By using this relationship, we propose an efficient band selection method, namely, the volume-gradient-based band selection (VGBS) method. The VGBS method is an unsupervised method, which tries to remove the most redundant band successively. Interestingly, the VGBS method can find the most redundant band based only on the gradient of volume instead of calculating the volumes of all subsimplexes. Experiments on simulated and real hyperspectral data verify the efficiency of the proposed method.

This letter presents a new endmember generation method, which is called the geometric optimization model (GOM). The algorithm exploits the following fact: anL-dimensional (L-D) simplex can be divided intoL+ 1L-D smaller simplexes by any point within the simplex, and the sum of the volumes of theL+ 1 smaller simplexes is equal to the volume of the simplex. Based on this geometrical property, we propose a new objective function for endmember generation, whose variable only includes the mixing matrix. As a result, all the problems caused by the abundance matrix can be avoided. Experiments using both simulated and real hyperspectral data show that the GOM is effective in searching the optimal solution.

This letter proposes a small target detection method for the hyperspectral image based on higher order statistics. This method first calculates the coskewness tensor of the hyperspectral image, followed by the orthogonal decomposition using higher order singular value decomposition. The obtained singular vectors are then used to perform the orthogonal transform to the centralized image. Compared to the popular blind source separation techniques, the presented method keeps clear of nonconvergence. Experiments with a real hyperspectral image show that the interested small target will be presented in the first few bands (even in the first band) very clearly after the transformation.

Remote sensing of shallow waters may produce images characterized by limited image coverage, strong uneven background, and high noise/speckle levels, which contribute to the challenges of extracting spatial information. To better assess the submerged aquatic vegetation (SAV) habitat of coastal Pinellas County, Florida, USA, using Hyperion images, two operational image optimization algorithms, vertical radiance correction (VRadCor) for destripe and spectral recognition spatial smooth hyperspectral filter (SRSSHF) for denoise, were modified for use in the shallow coastal waters and then compared to other methods. The VRadCor compresses the cross-track radiance abnormity addressing both the along-track cambering effect with low frequency and the stripe effect with high frequency by estimating both the additive and the multiplicative correction factors. The experimental results show that VRadCor more effectively removes stripes from Hyperion images in comparison to other traditional algorithms. Application of SRSSHF, a special adaptive filter model that compresses the noise by using both spectral and spatial features, was effective for denoising for inner patch areas while retaining (or enhancing) subtle edges between different patches. The use of VRadCor and SRSSHF significantly improves the quality of images of coastal waters while retaining the spectral features of water/SAV. The optimization of the images may lead to improved feature classification or increased accuracy for parameter extraction.

Reflectance of typical artificial surfaces, such as road and roof is usually believed to be invariant in a short period of time due to their physical and chemical stability. To examine its variability, reflectance of asphalt, concrete, walkway slab, asphalt roof paper and color plate is measured using dual-beam method. A preprocessing procedure is performed to remove possible errors caused by non-target factors. Measurement results show that reflectance of these targets are relatively stable when sun elevation condition is large and change rapidly when sun elevation is close to 0 °. This result provides useful information about reflectance variation of typical urban surfaces under changing field condition and may benefit reflectance modeling studies on similar targets.

Measurement of polarized properties of the skylight from the ground is one of an effective means of investigating the optical and physical parameters. A new system to measure the natural skylight polarized radiance distribution has been developed. The system is based on the field spectrometer Analytical Spectral Devices (ASD) with a dichroic linear polarizing filter. With this system sequences of radiance data were obtained which can be determined the linear polarization components of the skylight. The ground-based measurements are compared with simulations based on semi-empirical Rayleigh model.

* This paper is funded by the National Natural Sciences Foundation of China(40202031), and the Key Innovation Projection of CAS(KZCX3-SW-338-1) † State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications, CAS. P. O. Box 9718, Beijing 100101, China. Tel: +86-10-60892893, Email: [email protected] ‡ Shaoxing Bureau of Land and Resources, No.108 Longshanhoujie, Shaoxing 312000, P. R. China. Tel:+86-575-5128397, Email:[email protected] § China Telecom Beijing Research Institute, Guanhua Bldg., Rm. 118, Xizhimenneidajie, Beijing 100035, China. Email: [email protected] ** Image Information Base Group, Research and Development Headquarters, NTT Data Corporation, Japan †† State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, Tel: 13810380409, Email: [email protected], Abstract-A low-frequency but complex cross-track radiometric variation is found in OMIS hyperspectral images, which can't be corrected well by the general tool as CTIC in ENVI. Therefore a new correction method named as VRadCor is suggested in this paper, and good effect is obtained in some verification examples both for OMIS and HYMAP. It shows that VRadCor adequately considers and uses the spectral features of hyperspectral image on the base of some reasonable supposes. Therefore it can keep the spectral shape well after correction. And furthermore, it can not only obtain both the multiplicative and additive correction factors, but also provide a possibility to locate the optimized base spectra for correcting reference. A contrast between VRadCor and CTIC is also suggested.