Moving object tracking is one of the key technologies in video surveillance. Mean shift algorithm fails to track the moving object in complicated environment. In this paper, a new strategy is proposed to improve the tracking ability of mean shift algorithm, in which the contrast between object and background along with similarity evaluation are applied for generating and updating object model. To eliminate the interference of the most similar features between tracking object and background, the coefficient ratio of the object to surrounding environment is first imported to generate the object model. To make sure the accuracy of updating object model, the effective way that combines similarity evaluation and Kalman filtering prediction is then applied for judge whether the tracking object is sheltered by other objects or background. The experimental results have shown that the proposed method can tack the moving object stably.
This paper presents a simple reactive terrain navigation strategy for a shape-shifting tracked mobile robot on environments consisting of flat surfaces, discrete climbable steps and slopes. The proposed navigation strategy employs the concept of fuzzy Terrain Traversability Index, where the ease of traversal is evaluated from a combination of geometric properties. In the two-layer fuzzy controller, the Terrain Traversability Index is first computed based on slope gradient and step height, of which data is obtained from an a priori information of its surroundings in the form of a 2.5D grid map, before combined with sonar sensory data to determine the overall traversability of the region. Using goal-enhancement on fuzzy sets prior to defuzzification, the fuzzy controller outputs a turn recommendation which is deemed most convenient for the mobile robot. The navigation algorithm has been implemented into a virtual agent and case studies. These studies have shown encouraging results of the ability of the mobile robot to select its path based on its perceived ease of traversing
The biomechanical analysis assists to provide evidences in the performance of the system used for stroke rehabilitation of lower and upper limb of human body. This could be done by providing a better understanding of human lower extremities movement through implementation of electromyography (EMG). As human body is a complex biomechanical machine, conducting analysis using only EMG is not sufficient in representing muscle coordination pattern for functional task (i.e. walking). For that, Genetic Algorithm (GA) is implemented in the selection process of best-fit mathematical model and its parameters used in conversion of EMG signal into estimated torque. Several experiments are conducted to validate the proposed method. The field of management and rehabilitation of motor disability is identified as one important application area. Based on relevant literature, the present paper asserts that scientific analysis of human movement patterns can materially affect patient treatment. It provides evidence that patient management and rehabilitation processes in central neurological disorders can be improved through EMG techniques. The use of electromyography for clinical planning in the treatment process of patients helps providing future directions in research, development and applications of scientific analysis of human movement.
This paper reviews and studies the state-of the-art of available maximum power point tracking (MPPT) algorithms. Due to the nature of the wind that is instantaneously changing, hence, there is only one optimal generator speed is desirable at one time that ensures the maximum energy is harvested from the available wind. Therefore, it is essential to include a controller that is able to track the maximum peak regardless of any wind speed. The available maximum power point tracking (MPPT) algorithms can be classified according to the control variable, namely with and without sensor, and also the technique used to locate the maximum peak. A comparison has been made on the performance of the selected MPPT algorithms on the basis of various speed responses and the ability to achieve the maximum energy yield. The tracking performance is performed by simulating wind energy system using MATLAB/Simulink simulation package. Besides that, a brief and critical discussion is made on the differences of available MPPT algorithms for wind energy system. Finally, a conclusion is drawn.
Among most conventional incineration systems, the fluidized bed combustor (FBC) had been described as one of the most advantageous by providing simple operation with ability to accommodate low quality fuel as biomass, sludge and MSW with high moisture; reduced auxiliary fuel use; reduced operating and maintenance costs. This could only be achieved if optimal operating parameters are determined. This paper presents the methods and part of the findings of an on-going research aimed at optimizing the operating parameters that gives lowest emissions in the combustion of a fluff refused-derived fuel (f-RDF) in pilot scale fluidized bed combustor. The method adopt includes - cold fluidization studies in rectangular model column to determine the fluidizing velocity of the inert bed material (silica sand), and the effects of increasing fluidizing numbers on the mixing behavior of bed and fuel. This is closely followed by combustion study in the pilot scale FBC.
