Recently, visual features extracted by convolutional neural networks (CNNs) have been widely used in computer vision. Most state-of-the-art CNNs adopt a convolutional layer to map the high dimensional features into th...
详细信息
Low dimensional binary hashing is the key point in large-scale image retrieval and person re-identification (re-ID). To promote the performance, we explore the possibility of deep supervised hashing using the label in...
详细信息
Tunnel moving target detection is subject to the influence of light condition and motion blur, the traditional motion detection method based on pixel points can not be very good at segmenting moving target. To solve t...
详细信息
ISBN:
(纸本)9781467390491
Tunnel moving target detection is subject to the influence of light condition and motion blur, the traditional motion detection method based on pixel points can not be very good at segmenting moving target. To solve this problem, frame difference detection method based on local structure of image and gray level information is proposed. The local mean difference information of the image is calculated by the improved algorithm, and then the similarity measure function and the gray scale measure function are constructed. The similarity measure function effectively describes the structural features of moving objects, and reduces the influence of image background information. The gray scale function is better to highlight the contrast of the target brightness, to increase the division of the target area and the background parts, and to realize the moving target detection correctly. The experimental results show that the detection method of the fusion structure and the gray level information can effectively segment the moving object.
Predicting the travel time in real time is challenging due to dynamic changes of the traffic. With the help of GPS, wireless mobile communication, and big data technologies, several link travel time distribution captu...
详细信息
Predicting the travel time in real time is challenging due to dynamic changes of the traffic. With the help of GPS, wireless mobile communication, and big data technologies, several link travel time distribution capturing algorithms have emerged to generate the prediction of the route travel time distribution in short term. In this paper, we propose a data fusion model which can combine the historical and real time distribution to predict the link level travel time distribution. In the model, the route is represented with Markov chain, where the Markov state is identified by the travel time of probe vehicles. Experimental results prove that the proposed method has high accuracy in predicting route travel time distribution, and it is robust in spite of the fluctuation of real-time data.
To analyze the convergence of PSO algorithm, a method based on two order constant coefficient recursive method is proposed in this paper. A new way to modify PSO and APSO algorithm achieved by adjusting the progress o...
详细信息
ISBN:
(纸本)9781467372121
To analyze the convergence of PSO algorithm, a method based on two order constant coefficient recursive method is proposed in this paper. A new way to modify PSO and APSO algorithm achieved by adjusting the progress of algorithm is also proposed, thus forming MPSO and MAPSO algorithm, and this paper also presents Auto-regulative PSO algorithm which can automatically adjust parameters in the iterations. Ten basic functions are used for experiments to study the performance of the algorithms, and the results of experiments prove that Auto-regulative PSO algorithm and MAPSO are superior to MPSO and APSO respectively.
At present, the collection of connected vehicles data is not a problem any more but the platform and visualization are the most needed for traffic data. Management of the collected data, platform operation, and visual...
详细信息
At present, the collection of connected vehicles data is not a problem any more but the platform and visualization are the most needed for traffic data. Management of the collected data, platform operation, and visualization technology are the topics of this paper. Through using the new ECharts data visualization tool, we could achieve large data in real-time display with an ordinary WEB browser.
Epidemic routing has emerged as a promising candidate for providing message dissemination method in vehicular ad hoc networks. In this paper, we present a novel model to evaluate the capacity of epidemic routing in ve...
详细信息
ISBN:
(纸本)9781467372121
Epidemic routing has emerged as a promising candidate for providing message dissemination method in vehicular ad hoc networks. In this paper, we present a novel model to evaluate the capacity of epidemic routing in vehicular networks with considering the traffic signal control as a significant factor in urban area. Our study reveal that epidemic routing can behave differently in various traffic signal control situations where messages can be forwarded by vehicles passing through the intersections from other directions. The simulation results prove the accuracy of the model.
Real-time travel time is one of the important value for traffic management and traffic control. With the help of Internet of Vehicles (IOV), the dynamic traffic information can be collected and distributed more correc...
详细信息
ISBN:
(纸本)9781509003679
Real-time travel time is one of the important value for traffic management and traffic control. With the help of Internet of Vehicles (IOV), the dynamic traffic information can be collected and distributed more correctly. In this paper, we propose a method to predict the remaining travel time (RTT) for a vehicle on the freeway in the IOV environment. The Markov chains are adopted to predict a vehicle's remaining travel time in real-time. The experimental results prove that the mean absolute percent error (MAPE) is less than 10%.
暂无评论