As a leading cause of loss functional movement, stroke often makes it difficult for patients to walk. Interventions aid motor recovery in should be carried out as matter urgency. However, muscle activity the knee is usually too weak generate overt movements, which poses challenge early post-stroke rehabilitation training. Although electromyography (EMG)-controlled exoskeletons have potential solve this problem, most existing robotic devices centers are expensive, technologically complex, and...

Summary The fuzzy model predictive control (FMPC) problem is studied for a class of discrete‐time Takagi‐Sugeno (T‐S) systems with hard constraints. In order to improve the network utilization as well reduce transmission burden and avoid data collisions, novel event‐triggering–based try‐once‐discard (TOD) protocol developed networks between sensors controller. Moreover, due practical difficulties in obtaining measurements, dynamic output‐feedback method introduced replace traditional state...

In this study, the time‐varying formation control problem for second‐order discrete‐time multi‐agent systems is investigated, where both non‐uniform communication time‐delays and switching topology are taken into account. A linear protocol developed based on neighbouring relative position velocity information. Using state transformation method properties of stochastic matrix, feasibility condition given sufficient conditions to accomplish established. An unmanned aerial vehicles (UAVs)...

Spherical buoys serve as water surface markers, and their location information can help unmanned vessels (USVs) identify navigation channel boundaries, avoid dangerous areas, improve accuracy. However, due to the presence of disturbances such reflections, obstruction, changes in illumination for spherical on surface, using binocular vision positioning encounters difficulties matching. To address this, this paper proposes a monocular vision-based localization method elliptical fitting. First,...

Object recognition is fundamental to some high-level computer vision tasks such as image segmentation, object tracking and behavior analysis. The main objective of answer whether a specified exists in given image, so extracting representative features from images training right classifier become the key techniques this area. In paper, we use convolutional neural network model learn RGB-D dataset which are then linear SVM classify objects. As number not big enough retrain deep with high...

Bipartite antagonistic time-varying formation tracking problems for multi-agent systems with one dynamic leader is investigated in this paper, where the followers track while achieving a pre-defined formation, and group of tracks another at opposite position to origin. The competitive interactions among external input are both taken into consideration. A distributed bipartite protocol constructed by using neighboring state information. Sufficient conditions system achieve given. An approach...

In this paper, we present a novel vision-based human motion capture system, which employs two simultaneously running Kinects to scan the same subject in order improve stability. First causes of noise and unstability single Kinect system is analyzed. Then introduce very simple but effective method calibrate Kinects. As Kinect's depth sensing based on emission an infrared pattern, should be placed with 180° angle each other reduce interference errors caused by overlapping fields view. Two...

Time-varying formation tracking control problems for multi-UAV systems are investigated in this paper, where a leader with dynamic input is considered. A discrete-time protocol based on sliding mode method presented. Using Lyapunov stability approach, sufficient conditions system to realize the desired given and quasi-sliding band expressed. An experiment seven UAVs via Gazebo simulator performed verify effectiveness of protocol.

Classification of high-resolution remote sensing images is a challenging problem. Bag-of-words (BOW) based classification algorithms have obtained good performances in recent years. However, how the procedures BOW framework affect result still an open question. We present three visualization to reconstruct from BOW. After visualization, we can see what computer actually “sees” image feature. also analyze framework, namely, descriptor extraction and histogram generation, detail. It found that...

In this paper, we address the antenna array design problem at low signal-to-noise ratio (SNR). The Cramér-Rao bound (CRB) is most commonly used criterion to solve optimization due its computing simplicity and tightness in asymptotical region. However, there exists a threshold SNR which estimation variance significantly deviates from CRB. case, CRB no longer tight bound. To issue, propose use of Barankin Bound (BB) on source location intensity astrometry photometry problems as an alternative...

Automatic detection of salient object from a static image is highly active area computer vision research. In this paper, we propose an effective region-contrast based solution for saliency estimation which involves three phases. First, abstract into perceptually homogeneous regions to better capture structural information the input image. Next, kinds region contrast measures, i.e., global distinctness, compactness, and center prior, are evaluated integrated together by means two-layer...

Time-varying formation tracking control problems for multi-agent systems with second-order nonlinear dynamics are investigated in this paper, where a leader unknown dynamic input is considered. By utilizing sliding mode approach, distributed controller on the basis of neighboring state information designed. Based Lyapunov stability theory, sufficient conditions realization predefined summarized. A numerical simulation six agents performed to demonstrate effectiveness proposed protocol.

Real-time object tracking is a critical task in many computer vision applications. So far, conventional algorithms have been developed for real-time tracking, and most of them are based on visual recognition. Unfortunately, these could easily fail some specific circumstances when used individually. It often an effective approach to fuse the multi information different sensors, or solve mentioned problem. In this paper, simple but algorithm that fuses camera laser range finder proposed, which...

Edge detection plays an important role in many advanced robot applications. Sometimes the boundaries of objects should be extracted. This paper proposes edge algorithm that combining both color and depth data. Firstly, Canny operator is applied to image extract initial edges. Then color-edges are optimized using information eliminate non-boundary The depth-edges also remove edges caused by missing regions. At last, fused together forming final extraction. Comparative experiments demonstrate...

Time-varying formation problem for discrete-time multi-agent systems with double-integrator dynamics is investigated in this article, where the transmission delays and switching topology are discussed. The time-delay can be nonuniform graph of not required to include a spanning tree all time. A time-varying defined; corresponding vector reference function given. Based on neighboring states, linear protocol presented. Using state transformation method properties stochastic matrix, sufficient...