Aiming at the problem that traditional target tracking algorithms cannot detect and track specific targets in the real environment(such as airports) due to the given initial frame target position,this article proposes...
详细信息
Aiming at the problem that traditional target tracking algorithms cannot detect and track specific targets in the real environment(such as airports) due to the given initial frame target position,this article proposes a target tracking algorithm that combines improved Grid-based Motion Statistics(GMS) matching algorithm and correlation filtering tracking *** of all,for the problem that GMS cannot adapt to the detection of specific targets in realistic monitoring environment,a template size expansion method is proposed to disperse the centrally gathered feature points and Random Sample Consensus(RANSAC) is introduced to remove outliers in the center of similar ***,the initial template of the tracking algorithm is the target detected by the improved GMS method,and it is used to extract features to train the correlation filter to determine the target position of the video ***,two groups of comparative experiments show that not only the improved GMS algorithm has better target detection performance,but also the fusion algorithm has better reliability and robustness for target tracking.
This paper studies the optimal operating strategy of high-speed trains to reduce the total energy consumption in fixed time. Optimization of train running trajectory and efficient utilization of regenerative energy ar...
详细信息
This paper studies the optimal operating strategy of high-speed trains to reduce the total energy consumption in fixed time. Optimization of train running trajectory and efficient utilization of regenerative energy are two effective methods for energy-efficient operation. Based on the analysis of dynamic model of high-speed trains, this paper proposes a Genetic algorithm-Particle Swarm Optimization（GA-PSO） fusion algorithm in the pursuit of a sequence of speed codes at each end of subsection, which shares the same geographical data, to minimize the energy consumption. First, we formulate a two-objective dynamic model with energy consumption and operating time. Second, we design a combined algorithm with real number encoding to obtain the optimal solution. Then, we conduct the proposed optimization method under an actual route condition to verify the effectiveness. The simulation results show that the proposed operating strategy saves 22.81% more than the minimum time strategy and 4.22% than the global optimization on energy consumption. Finally, the situation involving interval speed limit is simulated with proposed method. The results demonstrate that optimal train trajectory saves 6.76% more than the normal train control strategy.
As an important component of the future HumanC-omputer Interface,Automatic Speech Recognition is designed for the purpose of realizing identification recognition and natural language comprehension by means of human **...
详细信息
As an important component of the future HumanC-omputer Interface,Automatic Speech Recognition is designed for the purpose of realizing identification recognition and natural language comprehension by means of human *** recognition technology has acquired significant achievements with some successful popularity and ***'s Via Voice system,for instance,has good performances when the vocabulary pool is small and when the noise is *** its performance will be greatly degraded when used in real application *** future applications of the humancomputer interaction,such as in a car,at airport,or live interviews,higher requirements for robust systems will be needed,therefore we need to explore new *** highly effective by most researchers,the combination of visual features of lip motion with vocal features can raise the recognition rate of the automatic speech system,and make it more robust and more adaptable to real *** focuses on the recognition methods and speech and visual fusion algorithm,which aims to attract more researchers to be interested and concerned in this area of research.
Image fusion is becoming one of the hottest techniques in image processing. Many image fusion methods have been developed in a number of applications. This paper mainly discusses the structures of image fusion process...
详细信息
ISBN:
(纸本)078038248X
Image fusion is becoming one of the hottest techniques in image processing. Many image fusion methods have been developed in a number of applications. This paper mainly discusses the structures of image fusion process, which is classified as hierarchical fusion structure, overall fusion structure, and arbitrary fusion structure. And the effects of such image fusion structures on the performances of image fusion are analyzed. In the experiment, a typical hyperspectral image data set is fused using the same wavelet transform based image fusion technique, but applying different fusion structures. The differences among their fused images are analyzed. The experimental results testify the theoretical analysis that the performances of image fusion techniques are related not only to the fusion algorithm, but also to the fusion structures, and different image fusion structures that produces different fusion performance even using the same image fusion method.
Pyroelectric infrared（PIR） sensor is low–cost, low-power small component commonly used only to trigger alarm in presence of humans or moving objects. PIR sensors are widely used as a simple, but reliable. In this p...
详细信息
Pyroelectric infrared（PIR） sensor is low–cost, low-power small component commonly used only to trigger alarm in presence of humans or moving objects. PIR sensors are widely used as a simple, but reliable. In this paper, we present a novel pyroelectric sensor node, feature extraction method and human pyroelectric information fusion method to identify direction of multi-human motion, number of people passing and distance between the PIR sensor and people in an array of pyroelectric sensors. The pyroelectric sensor node is composed of two kinds of pyroelectric sensor modules. Each module has different function, so we can fuse the different function to accurately track human target. The approach has low computational requirement, so it is well-suited for limited-resources devices. Through the experiment, we can get the correct detection rate of the direction and number of people is more than 100%, the correct identification rate of the path is more than 78%.
In social networks, maximizing influence is an important research direction. However, traditional influence maximization algorithms often overlook the attribute information of nodes and the heterogeneity of networks, ...
详细信息
暂无评论