In this paper, an image capture and processing system based on PC104 and FPGA is designed. The communication between PC104 and FPGA is achieved by PC104-PLUS bus. The FPGA co-processor accomplishes the image capture o...
详细信息
ISBN:
(纸本)9781479900305
In this paper, an image capture and processing system based on PC104 and FPGA is designed. The communication between PC104 and FPGA is achieved by PC104-PLUS bus. The FPGA co-processor accomplishes the image capture of CMOS camera and image pretreatment. The PC104 controller, as an upper computer monitor, realizes feature point detection based on LSD line detector and Camshift target tracking algorithm based on the color. Based on the design of the image capture and processing system, the concrete implementation scheme of the image capture and processing system is proposed. And the practicability of our image capture and processing system is demonstrated by feature point detection of a color mark and target tracking algorithm.
作者:
Shen, Z.Wang, K.Wang, F. -Y.Chinese Acad Sci
State Key Lab Management & Control Complex Syst Beijing Engn Res Ctr Intelligent Syst & Technol Inst Automat Beijing 100190 Peoples R China NUDT
Ctr Mil Computat Expt & Automat Changsha Hunan Peoples R China
Micro-simulation becomes more and more important in the Intelligent Transportation systems (ITS) research, because it can provide detailed descriptions of the system. For a multi-agent systems (MAS) modeling of an ITS...
详细信息
ISBN:
(纸本)9781479929146
Micro-simulation becomes more and more important in the Intelligent Transportation systems (ITS) research, because it can provide detailed descriptions of the system. For a multi-agent systems (MAS) modeling of an ITS, the computation burden is large, as it involves the computation of the state changing of all the agents. And, there are many multi-objective optimization problems in the ITS research. In this paper, we solve the traffic light signaling optimization problem and we take the average delay time and the average stop times as two objectives. We use a famous method of Non-dominated Sorting Genetic Algorithm II (NSGA-II). As NSGA-II can be viewed as an intelligent way of running a number of micro-simulations, usually the computation burden is huge. Graphics Processing Units (GPUs) have been a popular tool for parallel computing. The real transportation system runs in parallel and we think that a parallel tool is more suitable for the simulation and optimization of the system. We test GPU based NSGA-II method on a 4 intersection lattice road network, and on the 18 intersection road network of the Zhongguancun area of Beijing. Compared with the CPU version, the GPU version implementation achieves a speedup factor of 21.46 and 27.64 respectively.
The robotic fish with two long fins is one kind of underwater robot system imitating stingray's motion. The robotic fish generates thrust by use of two long fins located on both sides of body symmetrically. A driv...
详细信息
ISBN:
(纸本)9781479900305
The robotic fish with two long fins is one kind of underwater robot system imitating stingray's motion. The robotic fish generates thrust by use of two long fins located on both sides of body symmetrically. A driver control system for the motion control of fin rays is designed based on FPGA(Field Programmable Gate Array). Several kinds of motion modes can be achieved through tuning motion parameters. In order to facilitate updating control algorithm, reducing the probability of damaging the robot system and improving debugging efficiency, a solution for remote updating the driver program of the robotic fish wirelessly is proposed in this paper based on the dedicated remote system update circuitry integrated in ALTERA FPGA. In addition, a remote update system is designed in this paper. The designed control program updating system facilitates the debugging and optimization of multi-fin coordination control algorithm for the robotic fish with two long fins greatly.
Based on the conventional cruise control, vehicle adaptive cruise control (ACC) measures the distance and the relative velocity to the preceding vehicle real time via distance sensor, computes appropriate control outp...
详细信息
ISBN:
(纸本)9781479900305
Based on the conventional cruise control, vehicle adaptive cruise control (ACC) measures the distance and the relative velocity to the preceding vehicle real time via distance sensor, computes appropriate control output with respect to throttle or brake pedal, and control the velocity or headway automatically. Under the basically security guarantee, ACC could improve the comfort and reduce fuel consumption. This paper comprehensively investigates the theory and technology for ACC of last decades. We conclude the main approach of modeling, control and optimization of ACC, and note that data-based ACC system which conforms driver character and habit has been a new trend.
With the availability of increasingly more new data sources collected for transportation in recent years, the computational effort for traffic flow forecasting in standalone modes has become increasingly demanding for...
详细信息
With the availability of increasingly more new data sources collected for transportation in recent years, the computational effort for traffic flow forecasting in standalone modes has become increasingly demanding for large-scale networks. Distributed modeling strategies can be utilized to reduce the computational effort. In this paper, we present a MapReduce-based approach to processing distributed data to design a MapReduce framework of a traffic forecasting system, including its system architecture and data-processing algorithms. The work presented here can be applied to many traffic forecasting systems with models requiring a learning process (e. g., the neural network approach). We show that the learning process of the forecasting model under our framework can be accelerated from a computational perspective. Meanwhile, model fusion, which is the key problem of distributed modeling, is explicitly treated in this paper to enhance the capability of the forecasting system in data processing and storage.
In this paper, we investigate the energy savings in small-cell networks in the enhanced Local Area architecture at two stages. At the cell planning stage, we derive the optimal base station (BS) density in terms of th...
详细信息
ISBN:
(纸本)9781467357531
In this paper, we investigate the energy savings in small-cell networks in the enhanced Local Area architecture at two stages. At the cell planning stage, we derive the optimal base station (BS) density in terms of the minimum total BS power consumption under certain coverage requirement. Results show that the optimal BS density depends on both the coverage requirement and the BS power consumption model. At the dynamic cell operation stage, we evaluate the feasibility of dynamic BS switching off scheme quantitatively by system level simulations following assumptions and models in 3GPP. Results show that the energy savings are achieved at the cost of data rate loss, and the overall energy efficiency improvement is marginal.
One of the most difficult challenges in automatic face recognition is computing facial similarity between two images captured in different modalities, called heterogeneous face recognition. In this paper, we propose a...
详细信息
ISBN:
(纸本)9781479923410
One of the most difficult challenges in automatic face recognition is computing facial similarity between two images captured in different modalities, called heterogeneous face recognition. In this paper, we propose a novel method, named as coupled latent least squares regression, to improve the heterogeneous face recognition performance. The basic assumption is that the images of one person captured in different modalities can be viewed as modality-specific transforms of a latent ideal object. We formulate this assumption in the least squares regression framework, so as to learn the coupled transforms for different modalities. In particular, the local consistency information in the each modality is considered as a constraint to improve the generalization. Extensive experiments on two cases of heterogeneous face recognition (visible light vs. near infrared, and photo vs. sketch) validate the efficiency of the proposed method.
In this paper, we design and develop Vehicle License Plate Recognition (VLPR) System, which is one part of comprehensive video management platform for parking lot. Combined with intelligent video analysis module, the ...
详细信息
Unlike triple-polarized antennas, dual-polarized antennas can be easily implemented into thickness limited devices and thus have received much attention recently. Dual-polarized antennas have the potential to double t...
详细信息
ISBN:
(纸本)9781467328159
Unlike triple-polarized antennas, dual-polarized antennas can be easily implemented into thickness limited devices and thus have received much attention recently. Dual-polarized antennas have the potential to double the channel capacity in comparison with an omnidirectional single-input single-output (SISO) system. However, in real three-dimensional (3D) scenarios, dual-polarized antennas cannot capture the arriving power from the third polarization direction, which is orthogonal to the two-dimensional (2D) polarization plane. This will lead to power loss, which may significantly affect the resultant channel capacity. By proposing a novel two-sphere single-bounced geometry-based stochastic model (GBSM) and rigorously analyzing the change of polarization after single-bounced scattering, this paper studies the impact of the power loss on the channel capacity and specifies the conditions under which the channel capacity of dual-polarized systems is even worse than that of omnidirectional SISO systems. Not only that this is the first endeavor on this subject, but also this work is of practical importance in guiding appropriate deployment of dual-polarized antennas in real 3D indoor scenarios.
As the computing technology develops, micro-simulation becomes more and more important in the Intelligent Transportation systems (ITS) research, because it can provide detailed descriptions of the system. However, for...
详细信息
暂无评论