Intensity-hue-saturation Transformation Research Articles

On the use of the SOS metaheuristic algorithm in hybrid image fusion methods to achieve optimum spectral fidelity

ABSTRACTImage fusion aims to spatially enhance a low-resolution multispectral (MS) image by utilizing a high-resolution panchromatic (Pan) band. Various image fusion methodologies have been proposed with the aim to improve the spatial detail quality without deteriorating the colour content of the input MS image. Previous studies revealed the fact that there is no such thing as ‘the best image fusion method’ since all fusion methods cause either spectral distortion or spatial detail loss to some extent, which motivates the researchers to develop more advanced methods to keep the colour content while increasing the spatial detail quality. This study proposed to use the Symbiotic Organisms Search (SOS) metaheuristic algorithm in hybrid image fusion methods to achieve the optimum colour quality in the fused images. The SOS algorithm was used in two hybrid fusion approaches, one including the Intensity-Hue-Saturation (IHS) and Discrete Wavelet Transform (DWT) methods and the other one including the IHS and Discrete Wavelet Frame Transform (DWFT) methods. The results of the proposed methods were qualitatively and quantitatively compared in three test sites against those of eighteen widely-used image fusion methods. It was concluded that the proposed methods led to superior colour quality with both singlesensor and multisensor input images, regardless of the spatial resolution difference between the input images. The proposed methods were also found to be very successful in sharpening the images, despite the fact that their main purpose was to keep the colour content as much as possible.

Fusion of Visible and Infrared Images Based on IHS Transformation and Regional Variance Matching Degree

It is usually necessary to identify and extract specific characteristics by deriving an informative fused image from multiple images. An effective fusion algorithm was proposed by combining the intensity-hue-saturation (IHS) transformation and the regional variance matching degree (RVMD) in our study. Visible and thermal infrared images of wheat were used as the original data sources. After finishing the IHS transformation, a fusion rule was designed to produce the new component I. More specifically, the high frequency fusion rule was generated by the RVMD with a threshold of 0.5 and a 3 × 3 moving window, and the weighted average was used as the low frequency fusion rule. Experimental results show that the proposed algorithm can avoid producing color distortion in comparison with the IHS transformation, and additionally, it can also enhance the edge contrast and produce more obvious texture resolution. In addition, three quantitative indicators including entropy, standard deviation and average gradient were used to validate the proposed algorithm. The analysis results show that the values of three indicators are respectively 7.82, 63.93, 10.06, which are better than the results derived from the IHS transformation and regional variance fusion.

Investigation of Remote Sensing Image Fusion Strategy Applying PCA to Wavelet Packet Analysis Based on IHS Transform

Further exploration of wavelet packet analysis (WPA) in the area of image fusion has been a hot topic. It is a strategy to combine WPA with such other transforms as intensity–hue–saturation (IHS), principle component analysis (PCA) for image fusion between the panchromatic (PAN) and the multispectral (MS) image. The paper puts forward a distinct fusion method. Its main idea can be stated as three steps. Firstly, intensity component is derived from IHS model of the image after an MS image is transformed from RGB to IHS. Secondly, intensity component and a matched PAN image are decomposed by WPA at the second scale, respectively. The innovational concept with two aspects is applying PCA theory to merge wavelet packet coefficients. One is to detect edge and produce self-adaptive weighted ratios for low-frequency band. The other is to yield another weighted coefficients for high-frequency bands based on standard deviation. Lastly, the new intensity component created by implementing inverse WPA, matching with hue and saturation reserved, makes up a color composition. A fused image is produced when carrying out transformation from IHS to RGB for the composition. It turns out that the presented fusion strategy is effective with experiments.

An Improved Remote Sensing Image Fusion Algorithm Based on IHS Transformation

In remote sensing image processing, the traditional fusion algorithm is based on the Intensity-Hue-Saturation (IHS) transformation. This method does not take into account the texture or spectrum information, spatial resolution and statistical information of the photos adequately, which leads to spectrum distortion of the image. Although traditional solutions in such application combine manifold methods, the fusion procedure is rather complicated and not suitable for practical operation. In this paper, an improved IHS transformation fusion algorithm based on the local variance weighting scheme is proposed for remote sensing images. In our proposal, firstly, the local variance of the SPOT (which comes from French “Systeme Probatoire d`Observation dela Tarre” and means “earth observing system”) image is calculated by using different sliding windows. The optimal window size is then selected with the images being normalized with the optimal window local variance. Secondly, the power exponent is chosen as the mapping function, and the local variance is used to obtain the weight of the I component and match SPOT images. Then we obtain the I` component with the weight, the I component and the matched SPOT images. Finally, the final fusion image is obtained by the inverse Intensity-Hue-Saturation transformation of the I`, H and S components. The proposed algorithm has been tested and compared with some other image fusion methods well known in the literature. Simulation result indicates that the proposed algorithm could obtain a superior fused image based on quantitative fusion evaluation indices.

A Novel Hybrid Pan-Sharpen Method Using IHS Transform and Optimization

Intensity-hue-saturation (IHS) transform is the most commonly used method for image fusion purpose. Usually, the intensity image is replaced by Panchromatic (PAN) image, or the difference between PAN and intensity image is added to each bands of RGB images. Spatial structure information in the PAN image can be effectively injected into the fused multi-spectral (MS) images using IHS method. However, spectral distortion has become the typical factor deteriorating the quality of fused results. A hybrid image fusion method which integrates IHS and minimum mean-square-error (MMSE) was proposed to mitigate the spectral distortion phenomenon in this study. Firstly, IHS transform was used to derive the intensity image; secondly, the MMSE algorithm was used to fuse the histogram matched PAN image and intensity image; thirdly, optimization calculation was employed to derive the combination coefficients, and the new intensity image could be expressed as the combination of intensity image and PAN image. Fused MS images with high spatial resolution can be generated by inverse IHS transform. In numerical experiments, QuickBird images were used to evaluate the performance of the proposed algorithm. It was found that the spatial resolution was increased significantly; meanwhile, spectral distortion phenomenon was abated in the fusion results.

A Pan-Sharpening Method Based on Evolutionary Optimization and IHS Transformation

In many remote sensing applications, users usually prefer a multispectral image with both high spectral and high spatial information. This high quality image could be obtained by pan-sharpening techniques which fuse a high resolution panchromatic (PAN) image and a low resolution multispectral (MS) image. In this paper, we propose a new technique to do so based on the adaptive intensity-hue-saturation (IHS) transformation model and evolutionary optimization. The basic idea is to reconstruct the target image through a parameterized adaptive IHS transformation. An optimization objective is thus introduced by considering the relations between the fused image and the original PAN and MS images. The control parameters are optimized by an evolutionary algorithm. Experimental results show that our new approach is practical and performs much better than some state-of-the-art techniques according to the performance metrics.

Monitoring olive mills waste disposal areas in Crete using very high resolution satellite data

This paper evaluates the efficiency of different image analysis techniques applied to high resolution multispectral satellite data so as to identify olive oil waste disposal areas in the island of Crete where huge quantities of wastes are produced. For this purpose very high spatial resolution images including Pleiades, SPOT 6, QuickBird, WorldView-2 and GeoEye 1 have been exploited. The research included the application of the Normalised Difference Vegetation Index, Olive Oil Mill Waste Index as well as Principal Component Analysis. Moreover Intensity–Hue–Saturation transformation was carried out. Furthermore, unsupervised classification was performed for a variety of classes (5; 10 and 15) over the same area for two different periods. In addition, supervised linear constrained spectral un-mixing technique has been applied for the WorldView-2 image, to evaluate the potential use of sub-pixel analysis. Indeed, as it is demonstrated NDVI and OOMW indices may be used to enhance the exposure of disposal areas in high resolution satellite datasets, while the application of the PCA and HIS transformations seems to be able to further improve the results. Unsupervised classification techniques, with no ground truth data, can sufficiently work; however temporal changes of the disposal areas can affect the performance of the classifier. The use of spectral library was able to detect OOMW areas with a relatively high rate of success improving the results from the unsupervised classification. Finally, a COSMO-SkyMed radar image has been examined and fused with a hyperspectral EO-ALI image, indicating that such kind of datasets might be also explored for this purpose.

An Improved Image Fusion Algorithm Based on IHS and Wavelet Transform

A new improved image fusion algorithm is proposed for multi-spectral image (MUL) and the high-resolution panchromatic image (PAN) based on intensity-hue-saturation (IHS) transform combined with wavelet transformation (WT). Firstly, the multi-spectral image is transformed into the IHS space for getting the intensity component (I).Then the high-resolution panchromatic image and I were matched with histogram. Secondly, the PAN and I were decomposed respectively by WT and fused to obtain the new I by the inverse WT. Finally, the fusion image was obtained by inverse IHS transform. four evaluate indicators are defined in this paper. By experiment research, the results show that this new method can effectively improve the fusion effect.

An IHS Transform Fusion Method based on Adjustment to Wavelet Low-frequency Component and Its Application

Aim at the defects of IHS(Intensity-hue-saturation) and wavelet transform fusion methods,an IHS transform fusion method based on the adjustment to wavelet low-frequency component is proposed by uniting the two methods,feasibility and superiority of the proposed method are verified through IKONOS and QuickBird images.Firstly,IHS transform technology is used to extract intensity from the true color image;following,in order to improve spectral fidelity of the fused image,combining intensity with Pan image,more reasonable intensity is produced by using wavelet transform technology;meanwhile,an adjustment to wavelet low-frequency component is proposed and used to make high spatial frequency information gain of fused image better;finally,the true color fused image is obtained through IHS inverse transform.The study shows that the proposed method has the advantages of IHS and wavelet,the quality of its fused result is significantly improved.

A GIS and remote sensing based evaluation of groundwater potential zones in a hard rock terrain of Vaigai sub-basin, India

In this paper, remote sensing, geographic information systems (GIS) and fieldwork techniques were combined to study the groundwater conditions in Vaigai basin, Tamilnadu. Several digital image processing techniques, including standard color composites, intensity–hue–saturation transformation and decorrelation stretch were applied to map rock types. Remote sensing data were interpreted to produce lithological and lineament maps such as geology, geomorphology, soil hydrological group, land use/land cover and drainage map were prepared and analyzed using GIS Arc Map GIS Raster Calculator module as geomorphology × 12 + drainage × 9 + lineament × 5 + geology × 8 + land use × 2 + relief × 4. The final cumulative map generated by applying the above equation had weight values ranging from 0.315 to 4.515. The overall results demonstrate that the use of remote sensing and GIS provide potentially powerful tools to study groundwater resources and design a suitable exploration plan, the thematic maps for the study area.

A Remote Sensing Image Fusion Method Based on Wavelet Packet Transform

Remote sensing image fusion is becoming widely used in object recognition because of complementary nature of images from different sensors. The result of image fusion is a single image which is more suitable for human and machine perception or further image processing. In this paper, a new remote\|sensing image fusion method based on wavelet packet transform (WPT) to fusion a multi\|spectral image and a panchromatic image is studied. Firstly, the multi\|spectral image is transformed with PCA, and three principal components can be obtained. Secondly, the first principal component of the multi\|spectral image and panchromatic image are transformed with wavelet packet transform. Thirdly, their high\|frequency coefficients are combined efficiently, while the low\|frequency coefficients of the first principal component of the multi\|spectral image are preserved. Fourthly, the first principal component of the multi\|spectral image is transformed with inverse wavelet packet transform. Finally, the fusioned image is obtained by inverse PCAT. Visual result and statistical parameters indicate that the performance of our new method is efficient comparing with those of PCAT (principal component analysis Transform)\|based fusion method, IHST (Intensity\|Hue\|Saturation transform)\|based one, and WT (wavelet transform) \|based one. It not only enhances spatial detail information of the result image largely, but also preserves spectral information of the original multispectral image well.

Multi-spectral remote sensing image enhancement method based on PCA and IHS transformations

This paper introduces a new enhancement method for multi-spectral satellite remote sensing imagery, based on principal component analysis (PCA) and intensity-hue-saturation (IHS) transformations. The PCA and the IHS transformations are used to separate the spatial information of the multi-spectral image into the first principal component and the intensity component, respectively. The enhanced image is obtained by replacing the intensity component of the IHS transformation with the first principal component of the PCA transformation, and undertaking the inverse IHS transformation. The objective of the proposed method is to make greater use of the spatial and spectral information contained in the original multi-spectral image. On the basis of the visual and statistical analysis results of the experimental study, we can conclude that the proposed method is an ideal new way for multi-spectral image quality enhancement with little color distortion. It has potential advantages in image mapping optimization, object recognition, and weak information sharpening.

Multiple Input to Multiple Output Images Fusion Based on Turbo Iteration

This paper mainly addresses the problem of multipolar Synthetic Aperture Radar (SAR) and colorful optical images fusion by regarding them as multichannel images. Based on traditional wavelet-based and model-based fusion algorithms, the paper proposes a multi-channel image fusion algorithm based on a multi-multiturbo iterative method. Multi-multiframe is proposed to represent the original image information with multiple outputs from better information-separating viewpoints, and turbo iterative balances wavelet-based and model-based fusion. The approach is designed in this manner. First, Intensity-Hue-Saturation (IHS) transformation is applied to the SAR and optical images. Then, different fusion processes are used on corresponding components. Fusion based on multi-multi and turbo iterative is applied to the Intensity component whereas weighted fusion is applied to Hue and Saturation components. To get the final result, inverse IHS transformation is applied. Experimental results show that the proposed algorithm performs effectively in preserving useful complementary information between optical and SAR images.

Fusion of IKONOS Satellite Imagery Using IHS Transform and Local Variation

The intensity-hue-saturation (IHS) technique is a well-known merging approach for its computational efficiency and spatial definition holding. However, it results in color distortion particularly for the remote sensing images of IKONOS and QuickBird as some other fusion methods, such as principal component analysis, and Brovey transform. Although wavelet-based image fusion approaches can provide a better tradeoff between spatial and spectral quality, the fused images with these methods often have a spatial resolution that is less than that of the IHS-based algorithm. A remote sensing image fusion algorithm based on IHS transform and local variation and its modified approach with low computational complexity are proposed. Visual effect and quantity evaluation results show that the proposed simple algorithm outperforms the conventional image fusion methods in the spectral domain with the spatial quality similar to that of the undecimated wavelet transform-based scheme. The proposed modified method can obtain the similar spatial resolution of the merged image with the IHS-based fusion algorithm and the better spectral quality in the green vegetation areas.

Investigation of the Dual-Tree Complex and Shift-Invariant Discrete Wavelet Transforms on Quickbird Image Fusion

In the current survey, the performance of the shift-invariant discrete wavelet transform and dual-tree complex wavelet transform (DT-CWT) for Quickbird image fusion is investigated. For this purpose, a DT-CWT fusion algorithm is developed and implemented on high-resolution multispectral and panchromatic Quickbird images of Heraclion, Crete, Greece. In order to point out the effectiveness of the aforementioned transforms, the resulting imagery is visually (through photointerpretation) and computationally (through index computations) compared to fusion products derived by other commonly used methods, such as the intensity hue saturation transform (IHS), the discrete wavelet transform, and the crossbred wavelet and IHS transform. The DT-CWT has been proved to provide a complete and effective tool for Quickbird image fusion

An IHS-based change detection approach for assessment of urban expansion impact on arable land loss in China

China is experiencing a drastic loss of arable land as a result of the continuing process of rapid urbanization. This loss could have an adverse impact not only on China's sustainable development but also on the world food market. To provide a robust and economical tool for evaluating the impact of this process, we developed an IHS (Intensity, Hue, Saturation)-based approach for detecting the change from arable land to urban land by using Landsat TM and SPOT Pan images in different years. This approach takes full advantage of the colour distortion related to the changes in objects after IHS and reverse IHS transformation. Based on case studies in Guangzhou city and Nanyang city, choosing Landsat TM bands 7, 4, and 3 as the input RGB component and employing an exponential contrast stretch and a high-pass filter in SPOT Pan pre-processing led to the greatest change in detection accuracy.