Amr Hussein Yousef

High-Speed Image Registration Algorithm with Subpixel Accuracy

A new, fast and computationally efficient lateral subpixel shift registration algorithm is presented. It is limited to register images that differ by small subpixel shifts otherwise its performance degrades. This algorithm significantly improves the performance of the single-step discrete Fourier transform approach proposed by Guizar-Sicairos and can be applied efficiently on large dimension images. It reduces the dimension of Fourier transform of the cross correlation matrix and reduces the discrete Fourier transform (DFT) matrix multiplications to speed up the registration process. Simulations show that our algorithm reduces computation time and memory requirements without sacricing the accuracy associated with the usual FFT approach accuracy.

Mathematical model development of super-resolution image Wiener restoration

In super-resolution (SR), a set of degraded low-resolution (LR) images are used to reconstruct a higher-resolution image that suffers from acquisition degradations. One way to boost SR images visual quality is to use restoration filters to remove reconstructed images artifacts. We propose an efficient method to optimally allocate the LR pixels on the high-resolution grid and introduce a mathematical derivation of a stochastic Wiener filter. It relies on the continuous-discrete-continuous model and is constrained by the periodic and nonperiodic interrelationships between the different frequency components of the proposed SR system. We analyze an end-to-end model and formulate the Wiener filter as a function of the parameters associated with the proposed SR system such as image gathering and display response indices, system average signal-to-noise ratio, and inter-subpixel shifts between the LR images. Simulation and experimental results demonstrate that the derived Wiener filter with the optimal allocation of LR images results in sharper reconstruction. When compared with other SR techniques, our approach outperforms them in both quality and computational time.

On the restoration of the microscanned images captured from unmanned airborne vehicles

Unmanned Airborne Vehicles (UAVs) during flight capture a set of images that have slightly different looks of the scene. These images often contain a sufficient overlapped area between them and subpixel shifts of random fractions that allows for constructing a high resolution image within the overlapped area. The high resolution image may have a poor visual quality due to the degradations during acquisition and display processes such as blurring caused by the system optics or aliasing due to sampling. A technique referred to as the microscanning is an effective method for reducing aliasing and increasing spatial resolution. By moving the field of view (FOV) on the detector array with predetermined sub-pixel shifts, both aliasing reduction and resolution improvement are realized with increasing effective spatial sampling periods. In this paper we introduce the idea of the microscanning in UAV captured images. Based on the continuous-discrete-continuous (CDC) model, a Wiener restoration filter is used to restore the visually poor quality image to a super resolution (SR) image.

Super-resolution reconstruction of images captured from airborne unmanned vehicles

Super-resolution (SR) reconstruction refers to the process of combining a sequence of under-sampled and degraded low-resolution (LR) images in order to produce a single high-resolution (HR) image. The LR input images are assumed to have slightly different views of the same scene. In the broad sense, super-resolution techniques attempt to improve spatial resolution by incorporating into the final HR result the additional new details that are revealed in each LR image. This can be the case of the images captured from unmanned aerial vehicles (UAVs). These images must have sufficient overlap to produce an HR image. Additionally, information about the UAV altitude and attitude-rotational parameters yaw, pitch, and roll-that allows us to relate the different images to a common coordinate system is also needed. This extra information can be used to get an SR image of the overlapping area common to all these images. In this paper, we define a metric to determine if there is enough overlap between a set of frames that would allow SR reconstruction. When this overlap exists, we use the set of registered data to reconstruct an SR image.

Highway traffic segmentation using super-resolution and Gaussian mixture model

One benefit of employing computer vision techniques to extract individual vehicles from a highway traffic scene is the abundance of networked, traffic surveillance cameras that may be leveraged as the input video. However, the acquisition sensors that are monitoring the highway traffic will have very limited quality. Additionally, video streams are heavily compressed, causing noise and, in some cases, visible artifacts to be introduced into the video. Further challenges are presented by external environmental and weather conditions, such as rain, fog, and snow, that cause video blurring or noise. The resulting output of a segmentation algorithm yields poorer results, with many vehicles undetected or partially detected. Our goal is to extract individual vehicles from a highway traffic scenes using super-resolution and the utilization of Gaussian mixture model algorithm (GMM). We used a speeded-up enhanced stochastic Wiener filter for SR reconstruction and restoration. It can be used to remove artifacts and enhance the visual quality of the reconstructed images and can be implemented efficiently in the frequency domain. The filter derivation depends on the continuous-discrete-continuous (CDC) model that represents most of the degradations encountered during the image-gathering and image-display processes. Then, we use GMM followed by the clustering of individual vehicles. Individual vehicles are detected from the segmented scene through the use of a series of morphological operations, followed by two-dimensional connected component labeling. We evaluate our hybrid approach quantitatively in the segmentation of the extracted vehicles.

Shoreline extraction from light detection and ranging digital elevation model data and aerial images

Abstract. There is an increased demand for understanding the accurate position of the shorelines. The automatic extraction of shorelines utilizing the digital elevation models (DEMs) obtained from light detection and ranging (LiDAR), aerial images, and multispectral images has become very promising. In this article, we develop two innovative algorithms that can effectively extract shorelines depending on the available data sources. The first is a multistep morphological technique that works on LiDAR DEM with respect to a tidal datum, whereas the second depends on the availability of training data to extract shorelines from LiDAR DEM fused with aerial images. Unlike similar techniques, the morphological approach detects and eliminates the outliers that result from waves, etc., by means of an anomaly test with neighborhood constraints. Additionally, it eliminates docks, bridges, and fishing piers along the extracted shorelines by means of Hough transform. The second approach extracts the shoreline by means of color space conversion of the aerial images and the support vector machines classifier to segment the fused data into water and land. We perform Monte-Carlo simulations to estimate the confidence interval for the error in shoreline position. Compared with other relevant techniques in literature, the proposed methods offer better accuracy in shoreline extraction.

Fast stochastic Wiener filter for superresolution image restoration with information theoretic visual quality assessment

Super-resolution (SR) refers to reconstructing a single high resolution (HR) image from a set of subsampled, blurred and noisy low resolution (LR) images. The reconstructed image suffers from degradations such as blur, aliasing, photo-detector noise and registration and fusion error. Wiener filter can be used to remove artifacts and enhance the visual quality of the reconstructed images. In this paper, we introduce a new fast stochasticWiener filter for SR reconstruction and restoration that can be implemented efficiently in the frequency domain. Our derivation depends on the continuous-discrete-continuous (CDC) model that represents most of the degradations encountered during the image-gathering and image-display processes. We incorporate a new parameter that accounts for LR images registration and fusion errors. Also, we speeded up the performance of the filter by constraining it to work on small patches of the images. Beside this, we introduce two figures of merits: information rate and maximum realizable fidelity, which can be used to assess the visual quality of the resultant images. Simulations and experimental results demonstrate that the derived Wiener filter that can be implemented efficiently in the frequency domain can reduce aliasing, blurring, and noise and result in a sharper reconstructed image. Also, Quantitative assessment using the proposed figures coincides with the visual qualitative assessment. Finally, we evaluate our filter against other SR techniques and its results were very competitive.

Performance analysis of different plasmonic metallic nanoparticles using for ultra-sensitive optical sensor

In this paper we introduce a nanosensor that able to detect optical wave using plasmonic nanoparticles of different metallic materials. Electro-optical material is used to control the refractive index of the surrounding plasmonic nanoparticles medium. A half width full maximum of the absorbed light is also calculated for five different nanoparticles. The nanoparticles are in spherical shape and could be gold, silver, aluminum, copper, or vanadium dioxide. We simulate the proposed structure using finite difference time domain method, FDTD, and calculate the refractive index sensitivity of each nanoparticle material. We noted that, the gold nanoparticles gives the best sensitivity. In additional, FWHM and the absorbance of gold nanoparticles are also given for different refractive index of the electro-optical material from 1.1 to 1.9 with step 0.2.

Image registration under symmetric conditions: novel approach

Registering the 2D images is one of the important pre-processing steps in many computer vision applications like 3D reconstruction, building panoramic images. Contemporary registration algorithm like SIFT (Scale Invariant Feature transform) was not quite success in registering the images under symmetric conditions and under poor illuminations using DoF (Difference of Gaussian) features. In this paper, we introduced a novel approach for registering the images under symmetric conditions.

An improved algorithm for pedestrian detection

In this paper we present a technique to detect pedestrian. Histogram of gradients (HOG) and Haar wavelets with the aid of support vector machines (SVM) and AdaBoost classifiers show good identification performance on different objects classification including pedestrians. We propose a new shape descriptor derived from the intra-relationship between gradient orientations in a way similar to the HOG. The proposed descriptor is a two 2-D grid of orientation similarities measured at different offsets. The gradient magnitudes and phases derived from a sliding window with different scales and sizes are used to construct two 2-D symmetric grids. The first grid measures the co-occurence of the phases while the other one measures the corresponding percentage of gradient magnitudes for the measured orientation similarity. Since the resultant matrices will be symmetric, the feature vector is formed by concatenating the upper diagonal grid coefficients collected in a raster way. Classification is done using SVM classifier with radial basis kernel. Experimental results show improved performance compared to the current state-of-art techniques.