Search

In this paper, a global connectivity control method for decentralized multi-robot systems is proposed. This method can achieve decentralized connectivity control of multi-robot network under disturbances, which has no effect on the objective flocking control. Based on the gradient between the connectivity and robot positions, the proposed connectivity control method can make each robot move along the desired gradient direction, so as to achieve the control of the global connectivity. Indeed, the flocking method based on the potential of attraction and repulsion can ensure that the distance between robots is stable within the desired range. Then the security of flocking and the stability of communication are guaranteed. It is proved in this paper that both connectivity and objective flocking control have no effect on the stability of each other, under the condition that both controllers are bounded. Therefore, the global connectivity and configuration of the system can achieve the desired states. In addition, a robust control method based on integral sliding mode is designed in this paper, which can counteract the external disturbance and ensure the ideal dynamics of multi-robot systems. Finally, several numerical simulations are given to validate the effectiveness of the proposed control methods.

In this paper, we propose a generation method of visually protected images and its application to privacy-preserving machine learning. Images generated by the proposed method hold the gradient direction information of the original images, but have no the information. Histogram-of-Oriented-Gradients (HOG) features are extracted from the protected images, and the features are applied to machine learning algorithms. In addition, the proposed generation method is an irreversible one, so there is no need to manage secret keys, unlike encryption methods. In an experiment, a face classification task is carried out under the use of a support vector machine algorithm with the HOG features to demonstrate the effectiveness of the proposed method.

The article offers a new method to detect brightness edges. It requires no image pre-smoothing and forms a contour image with minimum number of short lines. It is an analogue and, at the same time, an alternative to the widely known Canny border detection method. It differs from it by the method of calculating partial derivatives and by the choice of thresholds in the automatic mode. The processing time of one frame in the proposed method is 3 times less than in the Canny method.

Strawberry picking by machines confronts a complex environment where a targe may be sheltered by leaves or overlap with each other. Also, it is a challenge for machines to recognize mature strawberries among those in different maturity. This work presents a fast recognition method for elevated mature strawberries by the approach of deep learning. It uses an Ostu algorithm to separate targets from background and then the resulted effective image areas designated by the minimum external rectangular marking method are used to train CaffeNet for automatic target recognition. For comparison, we also design a SVM classifer that uses HOG gradient direction feature and H component of the color feature of the mature strawberries. The experimental results show that the average recognition rate of mature strawberries by CaffeNet can reach 95%, higher than that by SVM by 11%.

Weather has considerable influence on human behavior and activities. Weather-related disasters, in particular, can have a significant impact on societal functions, and the challenges they present need to be addressed. Weather forecasts help in minimizing the damage caused by a disaster by enabling us to make disaster management preparations beforehand. However, a disaster that occurs suddenly in a localized area is difficult to predict because existing forecasting systems are designed to make forecasts for a wide area. Therefore, a forecast system that can detect a sudden disaster in a small region is required. Pressure distribution measurements include information that is useful for forecasting the weather. Therefore, estimating the pressure distribution accurately is of considerable importance in increasing the accuracy of forecasting. One approach to estimating the pressure distribution involves using the gradient of pressure in a particular location. In this paper, we propose a system to estimate the pressure gradient using a pressure sensor array to enable the estimation of pressure distribution. The pressure difference measured by sensors is used to calculate the pressure gradient. For the evaluation of the proposed system, we built a prototype device consisting of 25 pressure sensors, and tested it in a wind tunnel and outdoors. The tests demonstrated the possibility of estimating the direction of the pressure gradient using our prototype device.

Robust facial representation approach is critical for face recognition. LDP is a more stable robust descriptor using gradient direction instead of intensity value. But it is less precise to treat the directional response values in the same way and it does not obtain enough information only considering fixed absolute values of the edge responses. we propose an adaptive local directional pattern (ALDP) feature descriptor for face recognition in this paper. Positive and negative edge directions are extracted to explore more valuable discriminant information in our ALDP. Based on Weber's law, an automatic threshold setting strategy is proposed to make the ALDP codes flexible and precise. The experiment results indicate our ALDP has higher recognition accuracy in comparison with traditional methods.

In this paper, we consider the problem of constrained fast source seeking using two nonholonomic wheeled robots with velocity limitations. To achieve maximum converging speed to the source, we propose a dual-module control approach. In the formation control module, we design the angular velocities of the two robots to keep them in a formation. In the source seeking module, a sliding-mode-like control algorithm is developed to generate the bounded linear velocities so that the moving directions of the two robots are aligned with the field gradient direction as quickly as possible. Only the instantaneous measurements of the field but not the gradients are used in the controller design. Compared to existing approaches, our method makes full use of the maximum velocity limitations of the nonholonomic robots to achieve fast overall converging speed using only two robots. Comparative simulation and experimental results are presented, demonstrating the superior performance of the proposed control strategy over the existing ones in terms of the seeking (converging) speed.

In this paper we suggest an approach to computational effective power line detection using the Integrated Vector Radon Transform (IVRT). The suggested IVRT-based approach uses gradient direction information. The experimental results show the effectiveness of the IVRT-based power line detection.

Depth image based rendering (DIBR) is one of the key techniques in converting the 2D videos into the stereoscopic 3D ones. Warping process is the major step in DIBR, which generates the virtual left and right views with a number of black disocclusion areas. The disocclusion filling process is the main task in DIBR. In this paper, an improved disocclusion filling approach is proposed, which is based on the texture and gradient analysis. Inpainting algorithm is applied first based on the background texture and depth information to repair the disocclusion areas, which can be effectively reduce the large sizes of the disocclusion areas. Then a new gradient direction template is proposed and applied to fill the left disocclusion areas. Experiments are conducted to compare with other disocclusion filling approaches. Our results are promising.

We proposed a simple and dynamic wavelet-based algorithm for enhancement of the satellite image sharpness or blurriness of a satellite image. Four set of methods are followed here (Denoising, Decomposing, Sharpness Estimation and Filtering). First Denoising is done on the input images and then it operates by initially decomposing the input image through a multilevel separable DWT. After this, the log-energies of the DWT sub bands are computed. A Scalar Index corresponding to the input image's sharpness is computed through the weighted average of the computed log-energies. Along with the Scalar Sharpness Index, a Block based algorithm is presented to determining the local perceived sharpness. This method is the simplest, fastest and accurate comparing to the currently best-performing techniques for the sharpness estimation. In this Paper A robust quantization-based image watermarking scheme, called the gradient direction watermarking (GDWM) is introduced for satellite enhanced image watermarking. In GDWM, the watermark bits are embedded by quantizing the angles of significant gradient vectors at multiple wavelet scales. To quantize the gradient direction, the DWT coefficients are modified based on the derived relationship between changes in the coefficients and the change in the gradient direction. This Watermarking technique is more robust for various sizes of watermark image. When compared to the existing watermarking techniques the proposed enhanced watermarking technique shows best results.

In this paper, we propose a new angle quantization index modulation (AQIM) method, called the difference AQIM (DAQIM) method. The proposed method aims to improve the watermarking performance against gain attacks. Unlike the original AQIM method [1], the DAQIM method quantizes the difference of the two angles instead of the angles themselves. The experimental results demonstrate that our proposed method outperforms both the AQIM and the gradient direction watermarking (GDWM) [2] methods in terms of document-to-watermark ratio (DWR).

In this paper, we consider the problem of removing jaggy artifacts from images. We consider the kernel regression framework and propose a reduced-rank quadratic adaptive method that adapts to the local gradient direction. The proposed technique is effective in shrinking isophote fluctuations, and the result is smooth edges. We observe that it is critical to differentiate jaggy artifacts from texture, junctions and corners, so that meaningful image structure is preserved. Here, we demonstrate that the spectrum of the local covariance matrix of gradients, also known as the structure tensor, is well suited for differentiation of jaggy artifacts from image structure, and we incorporate this into the kernel regression framework. Results show the efficacy of the approach. Namely, that the method is effective in reducing jaggy artifacts without blurring meaningful image structure.

An algorithm based on oriented centroid for image matching is designed. The main contribution lies in providing a stable feature direction of pixels called oriented centroid which takes place of the main gradient direction of the traditional SIFT (Scale Invariant Feature Transform) algorithm. The computation cost required to calculate the oriented centroid based feature direction is much less than that required to estimated the main gradient direction, leading to the considerable improvement of the algorithm's real-time performance. Experimental results verify that the algorithm does not lose performance in terms of robustness and accuracy compared with the standard SIFT algorithm.

Face alignment aims to fit a deformable landmark-based mesh to a facial image so that all facial features can be located accurately. In discriminative face alignment, an alignment score function, which is treated as the appearance model, is learned such that moving along its gradient direction can improve the alignment. This paper proposes a new face model named “Optimal Gradient Pursuit Model”, where the objective is to minimize the angle between the gradient direction and the vector pointing toward the ground-truth shape parameter. We formulate an iterative approach to solve this minimization problem. With extensive experiments in generic face alignment, we show that our model improves the alignment accuracy and speed compared to the state-of-the-art discriminative face alignment approach.

The essence of traditional ANN algorithm is to transfer the input-output problem of a group sample into a nonlinear programming problem. And it is a learning method to use iteration to work out weight problem along the negative gradient direction, but its convergence rate is slow and it is easy to fall into local minimum. Previously, there are many improved methods to solve the above-mentioned drawbacks by modifying the searching step size but there are few modified ANN algorithms by modifying the searching direction. In this paper, by studying the characteristics of the search direction of ANN Algorithm, there raises a new search direction, then an improved ANN algorithm based on the change of search direction is formed. The convergence rate of this new algorithm is much faster than the traditional ANN algorithm.

This paper presents a capacitive liquid level sensor with four electrodes. By detecting the level changes of liquid filled in a cylindrical vessel, not only liquid level information can be measured unrelated to gradient of the vessel, but also gradient status of the vessel can be evaluated at the same time. For this purpose, a new sensor with four electrodes sticked on inside wall of the cylindrical vessel has been designed and a novel measurement method different from conventional one is developed. Experimental results prove that this sensor can be used to detect the liquid level information and the gradient status of the vessel such as it is vertical or gradient, moreover, detailed gradient direction and gradient angle of the vessel on the gradient direction can be estimated if the vessel is gradient.

This paper presents a multi-agent algorithm to address the source-seeking problem in which the task is to locate the source of some signal (e.g., a radio transmitter, a location of chemical contamination, etc.). This algorithm is based on the formation control work of another researcher in which they designed a control structure to stabilize a group of non-holonomic vehicles to a circular formation and also to move that formation by changing the location of its center. The source-seeking algorithm builds on these results by providing an outer-loop control law to move this circular formation towards a source. The resulting control law depends only on direct measurements of the signal to calculate an approximate gradient direction which is then used to steer the formation. Under certain assumptions about the spatial propagation of the signal this algorithm causes the center of the agents' formation to asymptotically converge to the location of the source.

In this paper a fast face location method based on gradient distributions is presented. This method can locate face with certain rotation, or light variation or with glasses or beard in the image. It begins with vertical location by use of vertical integral projection on the two-valued image of the original image, and then proceeds with horizontal location according to the distributions of gradient direction. Experiments have proved this method fast and efficient.

The existing iris location algorithms are of low executing speed and poor robustness. In order to improve the accuracy of iris location, an iris location algorithm based on gradient direction information is proposed according to both the ring structural characteristics of iris and the gray distribution features of eye image in this paper. Experiments shows that the algorithm is effective and can improve the speed and accuracy of iris location.

Mammography is the standard examination method for the early detection of breast cancer. In the last decade, computer assisted detection systems have been developed that assist the physician in the detection of suspicious regions in mammograms. However, recent clinical studies indicate that state of the art CAD systems might have a negative impact on the accuracy of screening mammography. Therefore, besides additional clinical studies, better evaluations of state of the art detection approaches are necessary. In this contribution three methods for the detection of spiculated masses in mammograms are evaluated and compared. All three of them are based on gradient orientation images. To detect masses, the methods use circular neighbourhoods with different sizes around a single pixel. The number of orientations in every neighbourhood is used by every method in different ways to form a result. The main contribution is the first fair comparison of the performance of different detection approaches for spiculated masses. Furthermore, a novel gradient direction analysis is introduced. The analysis is an extension to the three approaches, which increases the performance for one of the three approaches.

The capsule endoscopy approved by U.S. FDA in 2001 has been widely used to detect the diseases in human gastrointestinal tract. However, the contrast of the images produced by this small device is often low due to some reasons. In this paper, we propose a new adaptive diffusion algorithm to enhance the capsule endoscopy images. Based on the behavior analysis of the anisotropic diffusion and the characteristics of the capsule endoscopy images, we design two conduction functions in edge direction and gradient direction respectively to enhance capsule endoscopy images. Experimental results on real capsule endoscopy images show that this new adaptive diffusion outperforms the original anisotropic diffusion so as to help the doctors to diagnose.

Selection of suitable thresholds for edgel detection is discussed. An analysis of the variation in gradient direction is performed to estimate the probability density function of gradient direction as a function of image signal-to-noise ratio. A direction band about the mean of the PDF is determined on the basis of the minimum acceptable fraction of the cumulative neighborhood gradient magnitudes due to those gradients which have directions within the band. The proposed algorithm thus bases edgel detection on the distribution of local gradient direction rather than merely the magnitude response. Corners and small-radius curves are accommodated by permitting multiple histogram peaks with attendant reduction in both the minimum cumulative response fraction required and the direction bandwidth. >

Although direct volume rendering is a powerful tool for visualizing complex structures within volume data, the size and complexity of the parameter space controlling the rendering process makes generating an informative rendering challenging. In particular, the specification of the transfer function-the mapping from data values to renderable optical properties-is frequently a time consuming and unintuitive task. Ideally, the data being visualized should itself suggest an appropriate transfer function that brings out the features of interest without obscuring them with elements of little importance. We demonstrate that this is possible for a large class of scalar volume data, namely that where the regions of interest are the boundaries between different materials. A transfer function which makes boundaries readily visible can be generated from the relationship between three quantities: the data value and its first and second directional derivatives along the gradient direction. A data structure we term the histogram volume captures the relationship between these quantities throughout the volume in a position independent, computationally efficient fashion. We describe the theoretical importance of the quantities measured by the histogram volume, the implementation issues in its calculation, and a method for semiautomatic transfer function generation through its analysis. We conclude with results of the method on both idealized synthetic data as well as real world datasets.

This work is aimed at the extraction of vascular structures and the formation of high level structural entities, i.e. vascular branches. The proposed approach is based on a string matching technique to associate contour lines. The lines are encoded using the direction of lines and the gradient direction. The measure of similarity between strings is performed using Wagner and Fischer's (1974) algorithm. A first step realizes a two string matching to associate contour lines. It is then extended to three string matching to form triplets (including the centerlines and contour lines).