Search

This paper presents a real-time taxi detection algorithm for embedded system. The detection is achieved by setting detection areas, license plate detection, vehicle roof detection, vehicle roof feature extraction and vehicle roof classification. In other words, a frame is extracted from the video and transformed into a rectangle image. After that, the system locates the license plate and followed by the vehicle roof. Then the features of the vehicle roof and the vehicle color are extracted. Finally, the features are input into a regression function, which is obtained from previous training data, to determine whether the vehicle is a taxi. These features are easy to extract so that the whole process is simple and robust. Due to the small cost of time, this method is suitable for embedded system.

Based on the Big Data collected from Space-Air-Ground, novel key technologies of intelligent transportation system are investigated, like sensor data acquisition, dynamic data transmission, mass data storage, multisource data fusion, data mining and analysis, etc. On this basis, a novel intelligent transportation cloud platform is designed, including Space-Air-Ground Big Data acquisition and transmission subsystem, cloud computing supporting platform, intelligent transportation application and service subsystem. With the help of the data visualization, data prediction, and decision-making, the whole traffic Big Data including people (passenger, driver), vehicle, and road traffic environment, can create the core added-values. The applications are: providing transportation data services for traffic enterprise users and business users, such as customized mining, and specific industry analysis; providing accurate transportation information services for the public; providing business model for all levels of users, such as data visualization and customized services.

Reducing travel time of emergency vehicles (EVs) has a potential in significant savings of life and property. Integrating modern intelligent transportation system (ITS) with EV signal preemption seems to be a solution. But existing EV signal preemption systems often break the current signal coordination and impact a lot on the normal traffic streams. In this paper the authors propose an emergency vehicle signal coordination (EVSC) approach, which is intended to provide "green wave" for EVs. Traffic simulations are conducted along an emergency corridor with eight (8) intersections in Qingdao, China. Multiple traffic measurements are compared between simulation outputs with and without EVSC operation. The result indicates that the proposed approach can reduce EV travel time by 26.9% without too much negative impact on the normal traffic streams.

This paper presents a real-time detection algorithm which detects abandoned objects in embedded Intelligent Video Surveillance (IVS) System. This algorithm uses two different Gaussian mixture models (GMM) with different learning rates to extract the foreground in order to detect the abandoned objects and output alarms. Experimental results show the algorithm is robust and well-performed in different circumstances.

Multiple-Input Multiple-Output - Orthogonal Frequency Division Multiplexing (MIMO-OFDM) is adopted to vehicular networks to increase the capacity, reliability and speed. In this paper, iterative demodulation and decoding algorithms are studied to approach the capacity of MIMO-OFDM vehicular networks. By analysing the drawbacks of the Gaussian approximation on the interference cancellation, non-Gaussian approximation is proposed to enhance the performance of interference cancellation based detectors with large constellations. Simulation results demonstrate that the proposed non-Gaussian algorithm can achieve a significant performance gain over existing ones with high order constellations.

Based on psychological experiments and psychophysical mechanisms, it is possible to acquire manufacturing workshop operator's behavior and cognitive situations. A comprehensive optimization model for complex industrial processes is proposed by integrating expert operator's behavior and electrophysiological characters. By using the proposed multiple layer modeling method includes process control, manufacturing and management factors, a human-in-the-loop control system can be created including the situation awareness of manufacturing process and workshop operator cognition.

Urban traffic congestion has already become an urgent problem. Artificial societies, Computational experiments, and Parallel execution (ACP) method is applied to urban traffic problems. In ACP framework, optimization for urban road networks achieves remarkable effect. Optimization for urban road networks is a problem of nonlinear and non-convex programming with typical large-scale continual and integer variables. Due to the complicated urban traffic system, this paper focuses on the ACP-based Computational experiments modeling. It hopes to find an optimization model that is further accord with the practical situation. To this end, the authors use a mixed integer nonlinear programming problem (MINLP) and an genetic algorithm (GA) for urban road networks optimization. The systemic simulation experiments show that the approach is more effective in improving traffic status and increasing traffic safety.

This paper presents a framework of Parallel Transportation Management and Control System for Subway Systems (PTMS-Subway) based on ACP approach. Firstly, based on multi-agent modeling, Artificial Subway Systems is constructed. Then, the design, content, and process of Computational Experiments Platform are performed. Finally, through an interactive Parallel Execution System between the actual and artificial subway systems, a set of practical strategies of management and control can be achieved. PTMS-Subway can improve the reliability, efficiency, safety, and service level of subway systems.