We propose an information fusion algorithm—common matrix approach-based edge detection—for edge detection in multispectral images based on a tensor projection approach. In order to merge the edge information situated on different spectral bands, the concept of the common matrix approach is enhanced for each band to project a tensor of gradients onto a derived basis. Once a single-gradient map is acquired from the tensor, a smart thinning and thresholding methodology is utilized at the edge extraction stage in terms of getting rid of spots and discontinuous edge pixels. Upon inspecting the experiments’ results on datasets including the Computer Vision Laboratory at Columbia University, Scene, scanning electron microscopy using the energy-dispersive x-ray microanalysis, and particular hyperspectral remote sensing datasets, it is observed that the proposed method achieves pleasing results in terms of subjective and objective measures in comparison to some recently proposed edge detectors on multispectral and hyperspectral images.
Change detection with background subtraction process remains to be an unresolved issue and attracts research interest due to challenges encountered on static and dynamic scenes. The key challenge is about how to update dynamically changing backgrounds from frames with an adaptive and self-regulated feedback mechanism. In order to achieve this, we present an effective change detection algorithm for pixelwise changes. A sliding window approach combined with dynamic control of update parameters is introduced for updating background frames, which we called sliding window-based change detection. Comprehensive experiments on related test videos show that the integrated algorithm yields good objective and subjective performance by overcoming illumination variations, camera jitters, and intermittent object motions. It is argued that the obtained method makes a fair alternative in most types of foreground extraction scenarios; unlike case-specific methods, which normally fail for their nonconsidered scenarios.