The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, a new image fusion algorithm based on fourth order partial differential equations and principal component analysis is introduced. This is for the first time fourth order partial differential equations brought into the context of image fusion. The proposed algorithm is as follows: First, fourth order partial differential equations are applied on each source image to obtain approximation...
In order to get high-resolution multispectral images, multispectral and panchromatic images are fused. The high frequency parts are fused by a fuzzy rule, low frequency parts fusion is performed by means of a weighted average. Experiments indicates that the fusion algorithm can obtain better results.
As two of the most commonly used image sensors in night-vision for military applications, infrared (IR) and visible light cameras have their own advantages and limitations due to the physical differences between the image formation processes. In this paper, a new multi-scale scheme for color image fusion is presented using EM algorithm and color transfer algorithm for IR and visible image. The color...
In this paper, a new multi-scale scheme for image fusion is presented using texture and edge information. The original images are decomposed into texture and edge maps by pyramid structures. The coefficients corresponding to the filtered texture and edge maps are solved by the singular value decomposition and the linear relationship between Gauss filter and Laws texture extract filter. The decomposed...
A pixel-level fusion approach is proposed to refine the resolution of urban multi-spectral images using the corresponding high-resolution panchromatic images. After the two images are decomposed by wavelet transform, three texture features are extracted from high-frequency detailed sub-images. Then a fuzzy fusion rule is used to merge wavelet coefficients from the two images according to the extracted...
An objective performance measure for image fusion considering region information is proposed. The measure not only reflects how much the pixel level information that fused image takes from the source image, but also considers the region features between source images and fused image. We conducted several simulations which show that our measure accords with subjective evaluations. Considering the robustness...
The proposed approach is for the fusion of urban multi-spectral images. Three extracted texture features are merged by a synthesizing fusion rule. Experimental results indicate that the proposed method performs well in both spectral information and spatial information.
A novel optimization-based method for designing wavelet filter banks in image fusion method is proposed. The filter bank design problem is formulated as a nonlinear optimization problem. The objective function of the optimization problem consists of both the performance metrics of the image fusion, such as the Root Mean Square Error (RMSE), and those of individual filters. The optimization problem...
Robot self-localization is one of the key problems to improve robot autonomous ability. In order to increase the localization precision of mobile robot, a self-localization algorithm based on odometry, single vision and laser radar is proposed. First, odometry estimated robotpsilas pose at every sampling time. At the same time, the angles between any two of the landmarks were measured by means of...
A new region based image fusion scheme is proposed. It is based on multiscale analysis. The low frequency band of the image multiscale representation is segmented into three kinds of regions by K-mean algorithm, which is used to determine the fusion rule and to achieve the multiscale representation of fusion result. The final image fusion result can be obtained by performing the inverse multiscale...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.