Search

The evaluation for visual tracking is of utmost importance in computer vision. During the last two decades, several evaluation frameworks have been proposed and applied by a large amount of researchers, such as average central error, success rate, or Pascal score. It turns out that it is not easy to compare trackers fairly, precisely, and comprehensively with just only one evaluation index. Given the fact, a novel method for the evaluation of visual tracking algorithms is proposed in this paper, which combines both central error and Pascal score. Using this metric, an experimental validation was conducted finally and may serve as a reference for related research.

In this paper, we propose a topical object discovery method in commerical video. This method utilizes the objectness measure to generate the object candidates from the key-frames of the video. Then a sparse coding method is developed to discover the most topical object. Such a method can provide ranked results and therefore we can easily select the most topical object. The experimental validation on 10 videos shows that the sparse coding method performs better than existing topic mining methods.

In order to increase the robustness of space robot teleoperation system and good operational performance, the article design a set of haptic feedback system based on hand controller data glove and active vision system, which depend on the Pan-Tilt-Zoom (PTZ) camera and Kinect camera. It makes operators have the feeling of immersive. This system requires two operator cooperation, one processing Active Vision tracking and image processing, one controlling the movement of robot under the good perception environment. At the same time, Good interpersonal interface design to alleviate the pressure of the operator, in order to study the real space teleoperation scene, we use the software to set the delay system to make the operator to verify the performance of the system in the case of delay. The experiments show that no matter in the presence or absence of delay, the system completes the tasks at a high success rate.

In this paper, the spacecraft formation control and its stability problems are studied on the basis of the energy concept. The formation systems are viewed as a multi-mass point system with both generalized elastic deformation and rigid body movement, and certain potential fields interact with each other within the formation. Consequently, the stability of formation and coordination and the controller design problems are studied from the perspectives of energy. The symmetry in formation motion is studied, and the definition of formation stability and its corresponding criteria are presented based upon the notion of relative equilibrium. Then, the artificial potential method is explored to design the formation control law, and the stability of which is followed by utilizing the former criterions. The effectiveness of the proposed formation control approach is also demonstrated by numerical results.

This paper establishes a model of satellite mobile communication network end-to-end authentication and designs a distributed end-to-end authentication protocol for the model including initial authentication, authentication status inquire, and re-authentication. It also analyzes the safety of the protocol by the formal verification and makes performance analysis by simulation experiments.

In order to solve the adaptability problem of local tangent space alignment (LTSA) with potential higher-order information loss in manifolds, a novel algorithm is proposed to optimize the extraction of local neighborhood information. The algorithm is based on LTSA and ICA algorithms, which is called the IELTSA algorithm. By optimizing the extraction of the tangent vectors, the algorithm can improve dimension reduction in high-dimensional and unevenly distributed manifolds. The proposed algorithm is feasible in carrying out manifold learning, and the reconstruction error is no more than that of LTSA. Experiments show that IELTSA can be applied to changed-density 3D curves and face images targeted at lower dimensions, showing highest performance over LTSA and other improved methods based on LTSA, and achieving the highest recognition rate in lower-dimensional embedding. The algorithm can effectively reconstruct low-dimensional coordination in curves with changed-density and also shows adaptability in high-dimensional images targeted at lower dimensions.

The visual information fidelity (VIF) index gained widespread popularity as a tool to assess the quality of images and to evaluate the performance of image processing algorithms and systems. But VIF is not a map-based quality metric if its quality map is calculated by traditional sliding window approach. This map-based property is owned by the other quality metrics such as structural similarity (SSIM) and mean-squared error (MSE). In this article, we first construct a novel VIF quality map in pixel domain, which makes VIF become a Minkowski norm of its quality map. Furthermore, we deduce the gradient of VIF by taking the derivative of VIF index with respect to the reference image. The gradient of VIF is easy to calculate and has many useful applications. Experimental results show that the proposed quality map can provide useful guidance on how local image quality is similar to reference image.

This paper investigates the adaptive controller for the longitudinal dynamics of a generic hypersonic aircraft. The control-oriented model is adopted for design. The subsystem is transformed into the linearly parameterized form. Based on the parameter projection estimation, the dynamic inverse control is proposed via back-stepping. The dynamic surface method is employed to provide the derivative information of the virtual control. The proposed methodology addresses the issue of controller design with respect to parametric model uncertainty. Simulation results show that the proposed approach achieves good tracking performance in the presence of uncertain parameters.

Control of humanoid robot behavior with the mind begins a new era of robotics research. One of the critical issues in this research is how to acquire the brain signals with high quality which are correlated to humanoid robot behavior. In order to improve subjects’ concentration on their mental activities during tests, we develop a stimuli module in the Cerebot system, consisting of a Cerebus neural data acquisition system and a Kumotek robot with 20 degrees of freedom or a NAO robot with 25 degrees of freedom. We present the experimental procedures for acquiring brain signals of imagining humanoid robot walking behavior by using movies of robot walking or real robot walking activities. We record two groups of brain signals correlated to mental activities of six robot walking behavior. Finally, we present a demonstration of controlling the humanoid robot walking behavior using the phase coding mechanisms of the Delta rhythms.

We consider the problem of traffic sign recognition in image sequences. In many cases, image sequences of traffic signs can be collected from consecutive videos and these images have high correlation with each other. While traditional traffic sign recognition approaches focus on how to extract better features and design more powerful classifiers, most of these methods neglected this correlation. In this paper, we introduce the low-rank matrix recovery model to exploit the correlation among images with similar appearances to enhance feature representation. By recovering the underlying low-rank matrix from the original feature matrix consists of feature vectors of image sequences, we are able to attenuate the influence of corruption, such as noise and motion blur. Experiments are conducted on GTSRB dataset to evaluate our method, and noticeable performance gain is observed by using low-rank matrix recovered from original matrix. We obtain very impressive results on several super-class accuracy while get comparable performance with state-of-the-art results on global accuracy.

We propose a linear spatial pyramid matching using locality-constraint linear coding for SAR image classification based on MSTAR database. Recently, works have little consideration about targets’ randomly distributed poses when applying sparse coding in coding scheme. We do the preprocessing of pose estimation to generate over-complete codebook and therefore reduce reconstruction error. SIFT descriptors extracted from images are projected into its local-coordinate system by Locality-constrained linear coding instead of sparse coding. Locality constraint ensures similar patches will share similar codes. The codes are then pooled within each sub-region partitioned according to spatial pyramid and concatenated to form the final feature vectors. We use max-pooling which is more salient and robust to local translation. With linear SVM classifier, the proposed approach achieves better performance than traditional ScSPM method.

Learning from sensor data plays an important role in the field of robotic research, especially in dexterous robotic hand grasping. The manuscript puts efforts on learning from tactile dynamic process during robotic hand grasping. A piecewise linear dynamic systems and a group of models are presented, under the guidance of which, proper gesture according to different types of targets could then be selected to facilitate stable and accurate grasping. This is evaluated on the experimental testbed and shows promising results.

Image denoising is a traditional problem which has been tackled using a variety of conceptual frameworks and computational tools. Total variation-based methods have proven to be efficacious toward solving image noise removal problems. Its purpose is to remove unnecessary detail and achieve optimal performance in terms of mean squared error (MSE), a metric that has been widely criticized in the literature due to its poor performance as an image visual quality assessment. In this work, we use structural similarity (SSIM) index, a more accurate perceptual image measure, by incorporating it into the total variation framework. Specifically, the proposed optimization problem solves the problem of minimizing the total gradient norm of restored image and at the same time maximizing the SSIM index value between input and reconstructed images. Furthermore, a gradient descent algorithm is developed to solve this unconstrained minimization problem and attain SSIM-optimal reconstructed images. The image denoising experiment results clearly demonstrate that the proposed SSIM-optimal total variation algorithm achieves better SSIM performance and better perceptual quality than the corresponding MSE-optimal method.

Cognitive radio (CR) network can make an opportunistic access of spectrum licensed to a primary user (PU). The CR must perform spectrum sensing to detect active PU, thereby avoiding interfering with it. This chapter focuses on adaptively spectrum sensing, so that negative impacts to the performance of the CR network are minimized when CR users experience both stochastic data arrival and time-varying channel. Since the frequency of the spectrum sensing has a directly impact on system throughput and the probability of collision between the PU and CR user, the PU activity is modeled based on the characteristic analysis of the PU spectrum utilization. Based on that, an efficient adaptive sensing algorithm that takes into account the system stability, collision, and throughput is proposed. The CR users can make a balance between them by utilizing a “periodic control factor” which controls the adaptive adjustment of the spectrum sensing frequency. The simulation results indicate that the proposed algorithm has excellent performance on collision probability and throughput compared with conventional periodic spectrum sensing scheme. Meanwhile, it is shown that the proposed algorithm has low implementation complexity for practical applications.

LEO/MEO Multi-Layered Satellite Network (MLSN), consisting of low and medium earth orbit satellites, is capable of providing higher coverage and better service than most Single-Layered Satellite Network. Its performance, however, has been longly encumbered by obsolete routing protocols and algorithms. This paper takes the predictability of satellite movements into consideration, based on which a novel routing protocol—Predictable Satellite Network Routing Protocol (PSNRP), is proposed. In this protocol, all topology changes due to satellite movement are classified into predictable and unpredictable changes. This predictability assists to reduce the protocol overhead. The simulations show that except for obtaining better routing performance, PSNRP also successfully allocates calculation resources evenly among all nodes, separates user data from protocol control data, and achieves stronger robustness on undergoing satellite failures and link congestions.

This paper presents an experimental study on the dynamics and vibration control of a high-speed manipulator. Light weight and high-speed manipulators are flexible structures, vibration will be unavoidable due to motion of inertial components or uncertainty disturbance excitation. To solve this problem, input shaping feed forward controller is adopted to suppress vibration of a flexible smart manipulator. Also, multi-mode positive position feedback (PPF) controller is designed with piezoelectric actuator, for suppressing the lower amplitude vibration near the equilibrium point significantly. Especially, the experiment setup that includes the test-bed mechanism of a flexible planar parallel smart manipulator and the hardware and software structures of the control system are then developed. Experimental research is conducted to show that the adopted input shaping algorithm can substantially suppress the larger amplitude vibration, and the PPF controller can also damp out the lower amplitude vibration significantly. The experimental results demonstrate that the proposed controllers can suppress vibration effectively.

A novel image quality assessment method for remote sensing image is presented in the paper. Blur and noise are two common distortion factors that affect remote sensing image quality. Those two factors influence each other in both space and frequency domain. So it is difficult to objectively evaluate remote sensing image quality while exist these two kinds of distortion simultaneously. In the proposed method, the input image is first re-blurred by Gaussian blur kernels and also re-noised by white Gaussian noise. Then we measure the amount of mutual information loss before and after image filtering and noising. We take the VIF index as a measure of the information loss. The proposed method does not require reference image and can estimate distorted image with both blur and noise. Experimental results of the proposed method compared with other full-reference methods are presented. It is an accurate and reliable no-reference remote sensing image quality assessment method.

In this paper, we perform activity recognition using an inexpensive RGBD sensor (Microsoft Kinect). The main contribution of this paper is that the conventional STIPs feature are extracted from not only the RGB image, but also the depth image. To the best knowledge of the authors, there is no work on extracting STIPs feature from the depth image. In addition, the extracted feature are combined under the framework of locality-constrained linear coding framework and the resulting algorithm achieves better results than state-of-the-art on public dataset.

Standard particle swarm optimization (PSO) introduced in 2007, here called 2007-sPSO, is chosen as a starting algorithm in this paper. To solve the problems of the swarm's velocity slowing down towards zero and stagnant phenomena in the later evolutionary process of 2007-sPSO, elastic boundary for PSO (EBPSO) is proposed, where search space boundary is not fixed, but adapted to the condition whether the swarm is flying inside the current elastic search space or not. When some particles are stagnant, they are activated to speed up in the range of the current elastic boundary, and personal cognition is cleared. Experimental results show that EBPSO improves the optimization performance of 2007-sPSO, and performs better than comparison algorithms.

In this paper, the singularly perturbed systems are decomposed into slow and fast subsystems. An adaptive fuzzy controller is designed for slow subsystems to satisfy the tracking requirement. To alleviate the tracking error, the controller is constructed by T-S fuzzy model system since it has superior approximation performance than Mamdani system. As for fast subsystem, a fuzzy controller is developed to stabilize the fast states. To guarantee the stability of the SP systems, Lyapunov composite technique is proposed.

Traffic sign recognition is one of the hot issues on the modern driving assistance. In recent years, the method using Bag-of-Word (BOW) model for image recognition has gained its popularity upon its simplicity and efficiency. The conventional approach based on BOW requires nonlinear classifiers to get a good image recognition accuracy. Instead, a method called Locality-constrained Linear Coding(LLC) presents an effective strategy for coding, and only with a simple linear classifier could achieve a good effect. LLC uses uniform sampling for feature extraction, but allowing for features of traffic signs, the central vision information of the image is more important than the surroundings. Fortunately, log-polar mapping to preprocess image samples before coding is helpful for traffic sign recognition. In this paper, a combination method of log-polar mapping and LLC algorithm is presented to achieve a high image classification performance up to 97.3141% on speed limit sign in the GTSRB dataset.

This paper describes a system capable of detecting and counting people using the Kinect camera. Upon the assistance of the depth information, most false face detection can be effectively eliminated, and then a 3D data association is used for the link of tracks and detection results. Finally, the validated trajectory is used for counting the people who enters the region of interest. Experimental results show that the use of depth information strongly enhance the counting performance.

Recent research has advocated the use of sparse representation for tracking objects instead of the conventional histogram object representation models used in popular algorithms. In this paper we propose a new tracker. The core is that the tracking results is iteratively updated by gradually optimizing the sparsity and reconstruction error. The effectiveness of the proposed approach is demonstrated via comparative experiments.

Since there does not exist labelled samples during tracking period, most existing classification-based tracking approaches utilize a "self-learning" to online update the classifier. This often results in drift problems. Recently, semi-supervised learning attracts a lot of attentions and is incorporated into the tracking framework which collects unlabelled samples and use them to enhance the robustness of the classifier. In this paper, we develop a gradient semi-supervised learning approaches for this application. During the tracking period, the semi-supervised technology is used to online update the classifier. Experimental evaluations demonstrate the effectiveness of the proposed approach.

We address the problem of tracking relative translation in a leader-follower spacecraft formation architecture using Robust Integral of the Sign Error (RISE) based Neural Network (NN) technique. Based on the relative translational dynamic model of the spacecraft formation, RISE is introduced to approximate the dynamics of the follower as well as various practical disturbances. It is shown that the errors of the entire formation closed-loop are asymptotical stability (AS), which takes significant advantage over the typical Uniformly Upper Bounded (UUB) property of most NN controllers in high-precision formation tasks. Finally, numerical simulation is provided to verify the effectiveness of the proposed algorithm.

Different kinds of methods have been proposed in Chinese document classification, while high dimension of feature vector is one of the most significant limits in these methods. In this paper, an important difference is pointed out between Chinese document classification and English document classification. Then an efficient approach is proposed to reduce the dimension of feature vector in Chinese document classification using Genetic Algorithm. Through merely choosing the set of much more "important" features, the proposed method significantly reduces the number of Chinese feature words. Experiments combining with several relative studies show that the proposed method has great effect on dimension reduction with little loss in correctly classified rate.

Tracking appearance similar objects is very challenging. Conventional approaches often encounter "hijack" problem. That is to say, the tracking results for the smaller objects will be attracted to the larger one in the close vicinity. In this paper, we propose a decentralized particle filter approach for similar objects tracking. When the objects are close, the tracking results for the larger one will be masked and its influence will be eliminated. In principle, the tracker for the smaller object needs to be run two times, which increase the time costs. To tackle this, we construct the integral image for the mask region and dramatically decrease the calculation time of the evaluation of likelihood functions in the masked image. Experimental results show that the proposed approach effectively avoids "hijack" problems.

A discrete-time jump fuzzy system with two Markov chains is proposed to portray the asymmetric network characteristic of a class of nonlinear NCSs with random but bounded communication delays and packets dropout. The less conservative dual-mode-depend guaranteed cost controller is designed base on the model. The design approach can be cast into a set of nonlinear matrix inequalities (NMIs) solved by a homotopy- based iterative algorithm. Simulation examples are carried out to show the effectiveness of the proposed approaches.

Symmetry is an important characteristic of vehicles and has been frequently used for detection tasks by many researchers. However, existing results of vehicle tracking seldom used symmetry property. In this paper, we will utilize the detected symmetry feature to design a proposal distribution of particle filter for vehicle tracking. The resulting proposal distribution can be closer to the true posterior distribution. Experimental results show that the use of symmetry information will obtain better tracking performance than the conventional color histogram-based particle filters.

A novel neuro-identifier-based tracking control of uncertain nonlinear chaotic system is presented. The algorithm is divided into two contributions. First, a dynamic neural networks is used to identify the unknown chaos, then a dynamic adaptive state feedback controller based on neuro-identifier is derived to direct the unknown chaotic system into desired reference model trajectories. Moreover, the identification error and trajectory error is theoretically verified to be bounded and converge to zero Computer simulations are shown to demonstrate the effectiveness of this proposed methodology.

The disadvantages of large computing and complex discriminant function involved in classical SVM emerged when the scale of training data was larger. In this paper, a method for classification based on sparse sampling is proposed. A likelihood factor which can indicate the importance of sample is defined. According to the likelihood factor, non-important samples are cliped and misjudged samples are revised, this is called sparse sampling. Sparse sampling can reduce the number of the training samples and the number of the support vectors. So the improved classification method has advantages in reducing computational complexity and simplifying discriminant function.

In this paper, we first present a series of dynamic TS fuzzy subsystems to approximate a nonlinear singularly perturbed system. Then the reference model with same fuzzy sets is established. To make the states of the closed-loop system follow those of the reference model, a controller including of neuro-fuzzy adaptive and linear feedback term is designed. The linear feedback parameters can be solved by LMI approach. Adaptive term is used to compensate the uncertainty and alleviate the external disturbance. Lyapunov constitute techniques can prove the stability of the closed loop systems. The simulations results illustrate the effectiveness of this approach.

In this paper, a support vector machine (SVM) approach for automatic impulsive noise detection in corrupted image is proposed. Once the noises are detected, a filtering action based on regularization can be taken to restore the image. Experimental results show that the proposed SVM-based approach provides excellent performance with respect to various percentages of impulse noise.

A stable discrete-time adaptive tracking controller using neuro–fuzzy (NF) dynamic inversion is proposed for a robotic manipulator with its dynamics approximated by a dynamic T-S fuzzy model. NF dynamic inversion is used to compensate for the robot inverse dynamics. By assigning the dynamics of the Dynamic NF (DNF) system, the dynamic performance of the robot control system can be guaranteed in the initial control stage. The discrete-time adaptive control composed of NF dynamic inversion and NF variable structure control (NF-VSC) is developed to stabilize the closed-loop system and ensure the high-quality tracking. The system stability and the convergence of tracking errors are guaranteed and effectiveness of the proposed control approach. is verified.

This paper discusses the problems of control design and stability analysis of the networked control systems(NCSs) with random delays. The network-induced delays of the NCS are considered as interval variables governed by a Markov chain. Using the upper and lower bounds of the delays, a discrete-time Markovian jump system with norm-bounded uncertainties is presented to model the NCS. Based on this model, a state feedback controller can be constructed via a set of linear matrix inequalities. Simulations are given to illustrate the proposed results.

With output redefinition of flexible-link manipulators an adaptive controller for tip tracking is presented based on radial basis function network (RBFN) and fuzzy system. The uniformly asymptotical stability (UAS) of control system is guaranteed by the Lyapunov analysis and the adaptive laws including the centers and widths of Gaussian functions and coefficients of Takagi-Sugeno (TS) consequences can make the tracking error converge to zero. For comparison purpose, an RBFN controller with fixed centers and widths is also designed. The simulation results show that with similar performances the proposed controller can give smoother input torques than the conventional RBFN one.

A neuro-fuzzy (NF) hybrid position/force control with vibration suppression is developed in this paper for a space robot with flexible dual-arms handling a rigid object. An impedance force control algorithm is derived using force decomposition, and then singular perturbation method is used to construct the composite control, where an adaptive NF inference system is employed to approximate the inverse dynamics of the space robot. Finally, an example is employed to illustrate the validity of the proposed control scheme.