A deep learning algorithm for Gaussian noise removal from both grayscale and color images is developed. As opposed to most existing discriminative methods that train a specific model for each noise level, the proposed method can handle a wide range of noise levels using only two trained models, one for low noise levels and the other for high noise levels. In the proposed algorithm, the training process consists of three successive steps. In the first step, a classifier is trained to classify the noisy and clean images. In the second step, a denoiser network aims to remove the noise in the image features that are extracted by the trained classifier. Finally, a decoder is utilized to map back the denoised images features into images pixels. To evaluate the performance of the model, the Berkeley segmentation dataset of 68 images (BSDS68) and 12 widely used images are used, and the denoising performance for additive white Gaussian noise is compared with several state-of-the-art methods in terms of peak signal-to-noise ratio (PSNR) and visual quality. For grayscale image denoising of BSDS68, our method gives the highest PSNR on all noise levels (significant mean improvement of 0.99). For color image denoising of BSDS68, except for one low noise level, the proposed method gives the highest PSNR on all other noise levels (mean improvement of 0.3).
The search for effective noise removal algorithms is still a real challenge in the field of image processing. An efficient image denoising method is proposed for images that are corrupted by salt-and-pepper noise. Salt-and-pepper noise takes either the minimum or maximum intensity, so the proposed method restores the image by processing the pixels whose values are either 0 or 255 (assuming an 8-bit/pixel image). For low levels of noise corruption (less than or equal to 50% noise density), the method employs the modified mean filter (MMF), while for heavy noise corruption, noisy pixels values are replaced by the weighted average of the MMF and the total variation of corrupted pixels, which is minimized using convex optimization. Two fuzzy systems are used to determine the weights for taking average. To evaluate the performance of the algorithm, several test images with different noise levels are restored, and the results are quantitatively measured by peak signal-to-noise ratio and mean absolute error. The results show that the proposed scheme gives considerable noise suppression up to a noise density of 90%, while almost completely maintaining edges and fine details of the original image.
Satellites are subject to harsh lighting conditions which make visual inspection difficult. Automated systems
which detect changes in the appearance of a satellite can generate false positives in the presence of intense
shadows and specular reflections. This paper presents a new algorithm which can detect visual changes to a
satellite in the presence of these lighting conditions. The position and orientation of the satellite with respect to
the camera, or pose, is estimated using a new algorithm. Unlike many other pose estimation algorithms which
attempt to reduce image reprojection error, this algorithm minimizes the sum of the weighted 3-dimensional
error of the points in the image. Each inspection image is compared to many different views of the satellite, so
that pose may be estimated regardless of which side of the satellite is facing the camera. The features in the
image used to generate the pose estimate are chosen automatically using the scale-invariant feature transform.
It is assumed that a good 3-dimensional model of the satellite was recorded prior to launch. Once the pose
between the camera and the satellite have been estimated, the expected appearance of the satellite under the
current lighting conditions is generated using a raytracing system and the 3-dimensional model. Finally, this
estimate is compared with the image obtained from the camera. The ability of the algorithm to detect changes
in the external appearance of satellites was evaluated using several test images exhibiting varying lighting and
pose conditions. The test images included images containing shadows and bright specular reflections.
In order to maintain space situational awareness, it is necessary to maintain surveillance of objects in Earth orbit.
A system of space-based imaging sensors could make much more detailed inspections of the existing resident
space objects (RSOs). However, in order to preserve bandwidth, it is desirable to send the groundstation only a
subset of all images which are taken by the inspection system. This paper presents a change detection algorithm
which can detect changes in the appearance of an RSO. A new inspection image is compared to a previously taken
base image. In each image, the translation vector and rotation matrix between the camera and the RSO, or pose,
is slightly different. Assuming that the points making up each image of the RSO are within a single plane, it is
possible to generate a planar homography which is a linear mapping between the two images. The homography
is used to estimate the rotation and translation between the camera coordinate systems. This knowledge can be
used to warp the inspection image so that it appears as though it was taken from the same coordinate system
as the base image. Finally, basic morphological image processing and image thresholding techniques are used to
perform change detection. The algorithm was evaluated by applying it to raytraced inspection images exhibiting
varying lighting and pose conditions. Simulation results show that the algorithm can reliably detect damage to
the RSO or the rendezvous of a suspicious object.
In this paper we propose the use of the genetic algorithm (GA) as a tool to solve multi-objective optimization problems in flexure jointed hexapods. Using the concept of heuristic mutation, a modified GA-based multi-objective optimization technique is proposed and the passive parameters' optimization problems in a flexure jointed hexapod system are solved. The passive parameters found include the spring and the damping parameters in each strut of the hexapod. The results produced by this new approach are compared to those produced by other practical selection techniques, proving that this technique is more flexible. Thus, the genetic algorithm can be used as a reliable numerical optimization tool in such problems.
When using a Gough-Stewart Platform (GSP) for a vibration isolation or precision motion task, the geometry of that GSP is often chosen on an ad hoc basis. This can result in a number of problems: singularities or poor conditioning; inability to produce desired motions or forces; high dynamic coupling between axes; poor fault tolerance. This paper will show that the class of orthogonal GSPs has a number of useful properties. Denoting the mapping from Cartesian payload velocities to strut velocities as a 6x6 matrix M, orthogonal GSPs are those where either the rows or columns of M are orthogonal. In other words, either MMT or MTM are diagonal matrices. This paper will derive the properties of orthogonal GSPs wherein MMT is diagonal. In particular, it will first discuss the possible geometries that yield orthogonal GSPs. This will make it clear when these geometries are appropriate for a desired application. By re-arranging the rows and columns of M, a block diagonal form is found. Based on this block diagonal form, methods of designing Stewart platforms meeting desired position and force specifications are derived.
A hexapod strut at the University of Wyoming currently exhibits high resonant modes at 3 kHz and above. To reduce these resonant peaks, the current aluminum rod of one of the struts was redesigned. A graphite/epoxy granularly filled composite tube was designed and incorporated into the strut. Reduction in the resonant peaks of up to 32 dB’s was achieved. Six of the above mentioned composite tubes were fabricated and incorporated into the hexapod. Testing showed considerable improvement in overall damping for the hexapod.
Stabilized platforms are required for two needs: (1) isolating vibrating machinery from a precision bus, and (2) quieting and precisely pointing a payload attached to a noisy, coarsely pointed bus. The early technology was based on platforms with simple passive struts, distributed in some geometry between the bus and the payload. Passive isolators have since improved. Also, active struts have augmented and sometimes replaced passive struts. To date, most research in this field has been concentrated on developing struts, so strut technology is becoming relatively mature. However, several struts are needed to support the payload, so the complex interactions between struts is critical, especially when performing pointing and tracking. Pertinent issues include: supporting the payload; making the struts function in unison in as many axes as possible; fault tolerance; control over a large range of bandwidth, stroke and load. Efforts at different sites are continuing relatively independently and, so far, very little attention has been given to developing optimization methods for matching platform design to applications. In this presentation, we will discuss the state-of-the-art platforms developed to deal with specific applications and present an overview of the performance characteristics of these different platforms. Using these models, we formulate various applications, and problems arising from these applications, that are not addressed by the existing technology. These problems deal with the geometry of the platform, control, DOF, and fault tolerance concerns.
Over-constrained parallel manipulators can be used for fault tolerance. This paper derives the differential kinematics and static force model for a general over-constrained rigid multibody system. The result shows that the redundant constraints result in constrained active joints and redundant internal force. By incorporating these constraints, general methods for overcoming stuck legs or even the complete loss of legs are derived. The Stewart platform special case is studied as an example, and the relationship between its forward Jacobian and its inverse Jacobian is also found.
Vibration isolation and precision pointing problems using hexapods have been separately investigated by several groups of researchers. Since many applications require simultaneous vibration isolation and precision pointing (e.g., telescopes, laser communication, and laser weapons), it is particularly useful to do both with a single device. A simultaneous control scheme is developed in this paper using acceleration feedback to provide high-frequency vibration isolation, while Cartesian pointing feedback provides low-frequency pointing. The compensation is divided by frequency because pointing sensors often have a low bandwidth, while acceleration sensors often have a poor low-frequency response. Methods for unifying these finite bandwidth joint and Cartesian controls to perform simultaneous pointing and vibration isolation on a single platform are developed and verified. Experiments on the University of Wyoming hexapods show that this scheme provides a viable control bandwidth.
A technique for selecting one camera viewpoint from m viewpoints containing zero mean Gaussian errors is presented. The procedure consists of a two stage analysis. First, the joint entropy of each viewpoint is found. The viewpoint with minimum entropy possesses the greatest possible lower bound reliability of meeting any quadratic specification of the pose error. Hence it is the best pose algorithm to select without further analysis. To guarantee a minimum reliability, a second stage of analysis is necessary. Methods of calculating reliability bounds for a given quadratic specification are explained. The reliability calculations require three orders of magnitude less computations than the alternative, Monte Carlo simulations. On the other hand, reliability analysis requires an order of magnitude more computations than entropy analysis. The concepts are simulated using a visual pose measurement system developed by NASA. The results indicate that entropy is very effective for selecting pose algorithms, and the reliability greatest lower bound is close to the actual reliability.