Moving object detection is usually used in gray image, and the color image should be converted to gray images to achieve detection. However, the color object can’t be described by simple gray information completely. ...
详细信息
ISBN:
(纸本)9781479947249
Moving object detection is usually used in gray image, and the color image should be converted to gray images to achieve detection. However, the color object can’t be described by simple gray information completely. In order to achieve automatic color moving object detection, the method based on automatic color clustering is especially proposed. Because the difference between adjacent pixels in an image is very small, the initial cluster center can be moved in the maximum distance. The proposed method can reduce the number of iterations and quicken convergence speed, meanwhile determine the number of color cluster and the location of the color object automatically. The proposed algorithm is validated in the actual system, experimental results show that the proposed method can automatically achieve color clustering for color image, while detect color objects.
As an important research field of intelligent Transport system(ITS),Unmanned Ground Vehicles(UGV)can lessen traffic accidents and relieve traffic congestion by high intelligence,thereby improving the efficiency of the...
详细信息
ISBN:
(纸本)9789881563842
As an important research field of intelligent Transport system(ITS),Unmanned Ground Vehicles(UGV)can lessen traffic accidents and relieve traffic congestion by high intelligence,thereby improving the efficiency of the entire *** and more complex urban traffic environment forces UGV to perceive a lot of environmental information,and the Geographic Information system(GIS)has strong capabilities of storage and management for geographic ***,a new method for constructing GIS database is proposed in this paper,which combines the characteristics of urban traffic and needs for perceiving the environment of UGV,to assist UGV in moving in the urban traffic environment ***,Google Earth is used to create the city ***,an urban road network model is proposed and the GIS database of urban traffic environment is constructed based on the ***,the GIS database is used to achieve the least-time route based on improved Dijkstra ***,the GIS database can provide the attributive information of roads in the real vehicle experiment,which guides UGV to perceive the environment *** have shown that the proposed GIS database performs well in assisting UGV to move autonomously in the urban traffic environment.
In order to provide more decision-making information and improve the effects of probabilistic forecasting, a novel wind power probabilistic forecasting approach based on Markov chain model of variation is proposed in ...
详细信息
In order to provide more decision-making information and improve the effects of probabilistic forecasting, a novel wind power probabilistic forecasting approach based on Markov chain model of variation is proposed in this paper. The transition probabilities matrix of Markov chain model is built from the variations of historical wind power data to compute probability distributions and deterministic wind generation at future moments. Refined state space is built because the value of variation is much smaller than wind generation, which could improve the prediction accuracy. The effectiveness and higher accuracy of proposed approach are proved by actual data from wind farm.
Aiming at the chiller process variables cannot be strictly obey the Gauss distribution,and the large number of variables between the serious correlation,this paper describes a fault detection method to detect the faul...
详细信息
ISBN:
(纸本)9781479970186
Aiming at the chiller process variables cannot be strictly obey the Gauss distribution,and the large number of variables between the serious correlation,this paper describes a fault detection method to detect the faults of *** Component Analysis(ICA) approach is used to extract the correlation of variables of chiller and reduce the dimension of measured data.A ICA-based method model is built to determine the thresholds of statistics and calculate statistics I2 and SPE,which are used to check if a fault occurs in *** method is validated using the laboratory data from ASHRAE RP-1043 and compared with Principle Component Analysis(PCA).Results show that the ICA-based method has better fault detection performance of *** has very good sensitivity for early fault and can effectively reduce the false alarm rate.
Scene recognition is a significant topic in computer vision, and Deep Boltzmann Machines (DBM) is a state-of-the-art deep learning model which has been widely applied in object and hand written digit recognition. Howe...
详细信息
ISBN:
(纸本)9781479970995
Scene recognition is a significant topic in computer vision, and Deep Boltzmann Machines (DBM) is a state-of-the-art deep learning model which has been widely applied in object and hand written digit recognition. However, when the DBM is used in scene recognition, it is difficult to handle large images due to its computational complexity. In this paper, we present a deep learning method based on Convolutional Neural Networks (CNN) and DBM for scene image recognition. First, in order to categorize large images, the CNN is utilized to preprocess images for dimensional reduction. Then, regarding the preprocessed images as the input of the visible layer, the DBM model is trained using Contrastive Divergence (CD) algorithm. Finally, after extracting features by the DBM, the softmax regression is employed to perform scene recognition tasks. Since the CNN can reduce effectively image size, the proposed method can improve the computational efficiency and becomes more suitable for large image recognition. Experimental evaluations using SIFT Flow dataset and fifteen-scene dataset demonstrate that the proposed method can obtain promising results.
For the problem that it is difficult to evaluate overall control effects when tuning PID controller parameter,this paper propose an evaluation method tuning PID controller parameter which is based on Fluent and comput...
详细信息
ISBN:
(纸本)9781479970186
For the problem that it is difficult to evaluate overall control effects when tuning PID controller parameter,this paper propose an evaluation method tuning PID controller parameter which is based on Fluent and computer aided *** method uses Fluent to emulate controlled object,and Fluent UDF to conduct the unsteady closed-loop control,achieving evaluation for PID controller parameter *** northern platform in one of the station of the Line 5 in Beijing for example,the results show that the method can be effectively evaluate the control effects in different control parameters.
This paper addresses the robust semi-global coordinated tracking problem of multiple-input multiple-output (MIMO) multi-agent systems with input saturation and communication noise. A distributed observer-based coordin...
详细信息
ISBN:
(纸本)9781479978878
This paper addresses the robust semi-global coordinated tracking problem of multiple-input multiple-output (MIMO) multi-agent systems with input saturation and communication noise. A distributed observer-based coordinated tracking protocol is constructed by combining a novel parameterized low-and-high feedback technique with the high-gain observers design approach. It is shown that, under the assumptions that each agent is asymptotically null-controllable with bounded controls and the network is connected, semi-global consensus tracking or semi-global swarm tracking can be attained for left-invertible and minimal-phase systems.
Similar to other major electrical apparatuses, the reliability and stability of the dc network is becoming the most important issue when using the voltage-source-converter-based multiterminal dc (VSC-MTDC) system for ...
详细信息
Considering two disadvantages in traditional gravity matching aided inertial navigation system,low matching accuracy and error accumulation,we propose an improved gravity matching algorithm and aided method for inerti...
详细信息
ISBN:
(纸本)9789881563842
Considering two disadvantages in traditional gravity matching aided inertial navigation system,low matching accuracy and error accumulation,we propose an improved gravity matching algorithm and aided method for inertial navigation *** of using the sequence sampling,the single point sampling is applied to improve the structure of proposed algorithm,enhancing the matching speed and *** the aided navigation system method,we use combination of Sage-Husa adaptive filter and strong-tracked Kalman filter to make further optimal estimation of the matching *** results show the effectiveness of the real-time ICCP algorithm and the combined filter *** to the traditional methods,proposed method provides higher matching and navigation accuracy.
Analysis and design of simulation scenario, design and application of scenario system are problems needed to be solved in the development and performance verification of simulation system. Consequently, a standardized...
详细信息
ISBN:
(纸本)9781479947249
Analysis and design of simulation scenario, design and application of scenario system are problems needed to be solved in the development and performance verification of simulation system. Consequently, a standardized development method for developing scenario based on a kind of combat information simulation system is proposed in this paper. Firstly, according to the requirements for generation of scenario which are decided by simulation system, the combining of military conceptual model and the entity oriented modeling method(EATI method) is used to build scenario structure model accurately and without distortion. Secondly, description of content and realizing form for scenario are constrained and standardized by extensible markup language(XML). Finally, a visualized and flexible scenario system model is built based on former theory analysis, which is independent of simulation system. This paper not only solves the problem existed in scenario and scenario system, but also implements rapid development of scenario, which provides important theory guiding meaning.
暂无评论