Targets grouping is the basis of second-level information fusion,which can effectively assist commanders to make *** aerial targets grouping algorithm only takes the radar acquisition data at the current time as the o...
详细信息
Targets grouping is the basis of second-level information fusion,which can effectively assist commanders to make *** aerial targets grouping algorithm only takes the radar acquisition data at the current time as the object and cannot update the clustering results automatically.A grouping method combining dynamic time warping(DTW) and the algorithm Density-Based Spatial Clustering of Applications with Noise(DBSCAN) is *** DTW distance of each attribute historical time-series data is used to measure the similarity between ***,an improved DBSCAN algorithm is used for *** simulation results show that the method has better grouping effect and can automatically cluster regularly.
A mount of recent researches on scene parsing and semantic labeling, while few focus on obtaining joint semantic motion labeling. In this paper, we propose an approach to infer both the object class and motion status ...
详细信息
ISBN:
(纸本)9781509024100
A mount of recent researches on scene parsing and semantic labeling, while few focus on obtaining joint semantic motion labeling. In this paper, we propose an approach to infer both the object class and motion status for each pixel of images. First, we extract and match sparse image features to estimate ego-motion between two consecutive stereo images, the result of feature points grouping is used to segment moving object in U-disparity map. Second, a Fully Convolutional Neural Network is employed for semantic segmentation. Moreover, semantic cues are utilized to remove pixels have no potential to be moved in motion mask. Finally, we use a fully connected CRF to integrate motion into semantic segmentation. To validate the effectiveness of the proposed algorithm, we present experimental results with KITTI stereo images that contain moving objects.
The research of image deblurring plays an important role in the digital image *** order to reduce image blurring problems,a content constraint loss(CCL) function in the generative adversarial network(GAN)is *** SS...
详细信息
The research of image deblurring plays an important role in the digital image *** order to reduce image blurring problems,a content constraint loss(CCL) function in the generative adversarial network(GAN)is *** SSIM loss and the perceptual loss constitute the CCL function,which makes the trained generative model *** CCL function as the content constraint loss component and the adversarial loss component constitute the total *** total loss is optimized by the iterative training to further improve the stability of the network model,and the image blurring will be *** the test experiment of the open source image dataset MNIST,CIFAR10/100 and CELEBA,the CCL function is used as the content constraint loss component of the generative adversarial network,the effect of image deblurring has obvious promotion in the structural similarity measure and visual appearance.
Comparing to the commonly used hydraulic three-axial shaking tables, multi-degree of freedom shaking systems implemented by Stewart platform have the merits of being portable, easy to install and with high load capaci...
详细信息
Comparing to the commonly used hydraulic three-axial shaking tables, multi-degree of freedom shaking systems implemented by Stewart platform have the merits of being portable, easy to install and with high load capacity, but are not well studied because of the inherent nonlinearity and strong coupling of Stewart platform. In order to replicate multi-degree of freedom road acceleration spectrum on Stewart platform, analysis of the system was carried out. Firstly, the system structure was introduced and the linearized platform kinematic equations, at the equilibrium position, were inducted. The models of actuators that drive the platform were simplified and the principles of three variable controller(TVC) were deduced briefly. Finally, MATLAB-Adams co-simulation environment was built to perform multi-degree of freedom road acceleration spectrum replication with TVC. The results show that it can reproduce high accuracy multi-degree of freedom road acceleration spectrum with TVC on Stewart platform.
A multi-bandwidth based tracking algorithm was proposed to search for the global kernel mode when the probability density has multiple peak modes. Firstly, a monotonically decreasing sequence of bandwidths was fixed a...
详细信息
A multi-bandwidth based tracking algorithm was proposed to search for the global kernel mode when the probability density has multiple peak modes. Firstly, a monotonically decreasing sequence of bandwidths was fixed according to the target scale. At each bandwidth, using mean shift to find out the maximum probability, and starting the next iteration at the previous convergence location. Finally, the best optimal mode could be obtained at the last bandwidth. To accelerate the convergence, over-relaxed strategy was introduced to enlarge the step size. Under the convergence rule, the learning rate was adaptively adjusted by Bhattacharyya coefficients of consecutive iteration convergence. The experimental results show that the proposed multi-bandwidth mean shift tracker is robust in high-speed object tracking, and perform well in occlusions. The adaptive over-relaxed strategy is effective to lower the convergence iterations by enlarging the step size.
This paper investigates the distributed formation control problem for a group of mobile Euler-Lagrange agents to achieve global stabilization by using virtual tensegrity structures. Firstly, a systematic approach to d...
详细信息
ISBN:
(纸本)9789881563897
This paper investigates the distributed formation control problem for a group of mobile Euler-Lagrange agents to achieve global stabilization by using virtual tensegrity structures. Firstly, a systematic approach to design tensegrity frameworks is elaborately explained to confine the interaction relationships between agents, which allows us to obtain globally rigid frameworks. Then, based on virtual tensegrity frameworks, distributed control strategies are developed such that the mobile agents converge to the desired formation globally. The theoretical analysis is further validated through simulations.
Intersection detection is a critical capacity for an Unmanned Ground Vehicle (UGV) to drive safely in structured urban environment. Large-scale intersections stamped on maps have plenty of features for detection while...
详细信息
Intersection detection is a critical capacity for an Unmanned Ground Vehicle (UGV) to drive safely in structured urban environment. Large-scale intersections stamped on maps have plenty of features for detection while some unmapped small-scale urban intersections are hard to be identified. In this paper, we propose a novel intersection detection method conducted on the basis of Hidden Markov Model (HMM). This method is based on the intersection scan model to obtain the traversable directions to classify the intersection. The scan model is effective in dealing with both LIDAR and visual data. Combination of the scan model and the HMM can accurately estimate the traversable directions in consideration of both real-time and historic data. Results from simulations and real-world experiments have shown the functionality of the presented approach.
作者:
Zheng ZhiPeng ZhihongChen JieSchool of Automation
Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing 100081 School of Automation
Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing 100081
This paper presents two aggregation strategies in convex intersection region for the distributed mobile sensor network (MSN) with heterogeneous dynamics. First, the authors analyze individual local perception model an...
详细信息
This paper presents two aggregation strategies in convex intersection region for the distributed mobile sensor network (MSN) with heterogeneous dynamics. First, the authors analyze individual local perception model and dynamics model, set the intersection of all the local perceptions as the region of interest (ROI). The MSN consists of sensors with first-order dynamics and second-order dynamics. Then, the authors design a control strategy to ensure that individuals aggregate at a point in the ROI relying on their local perceptions and the locations of neighbors within their communication scope. The authors describe this situation of aggregation as rendezvous. In addition, the authors introduce artificial potential field to make sensors deploy dispersedly in a bounded range near the ROI, which the authors call dispersed deployment. Finally, the authors prove the stability of the proposed strategies and validate the theoretical results by simulations. This research is applied for the cooperative deployment and data collection of mobile platforms with different dynamics under the condition of inaccurate perception.
In this paper,the weak signal detection under a stable noise is investigated based on bistable vibrational resonance(VR) which is driven by a high frequency *** the one hand,the energy of the high frequency drive sign...
详细信息
ISBN:
(纸本)9781509009107
In this paper,the weak signal detection under a stable noise is investigated based on bistable vibrational resonance(VR) which is driven by a high frequency *** the one hand,the energy of the high frequency drive signal is transferred to the low frequency weak signal when VR occurs;on the other hand,the control of stochastic resonance(SR) is achieved based on VR,which transfers more noise energy into useful signal *** addition,considering the requirements of real-time detection,the amplitude and frequency of the high frequency drive signal are optimized by the knowledge-based particle swarm optimization(KPSO),which takes the mean signal-noise-ratio(MSNR) of output as the fitness function,and the property that VR system produces the best resonance effect just when the valid system parameter a(B,Ω) is greater than zero as ***,the parameter compensation is combined to achieve multi-high frequency weak signals detection with a stable ***,the method is applied to the vibration fault diagnosis of a mono-crystalline silicon furnace,and the experiment results show the effectiveness and practicability of the method.
暂无评论