使用物体交互模型的车辆违停事件检测

随着平安城市与监控摄像头的发展,车辆违章停靠事件的自动检测在视频自动检测方法中具有重要意义.当前的目标检测算法,例如基于特征+分类器、基于视频背景差分、基于深度学习的方法等,大多关注车牌、交通标志的定位与识别,而忽略了对车辆违章等事件的判别.因此,发展了一种基于物体交互模型的车辆违章停靠事件检测方法:首先基于轮廓提取和SVM进行车牌检测;其次基于形状和颜色进行交通标志检测;最后基于物体交互模型来判断是否违停.上述方法在真实视频场景中的实验验证了方法的有效性和可靠性.     

基于源码模式挖掘的软件辅助开发技术研究

由于软件代码的复杂性,对于不了解框架的新手,很难利用开源社区中的代码来开发软件。因此,利用数据挖掘技术挖掘现有代码中的编程模式成为研究热点。文中介绍了频繁项挖掘Apriori算法,并提出了基于源码模式的软件辅助开发方法。它能够根据用户输入的关键字来智能匹配类库中的特定父类,挖掘基于此父类的编程模式,给出优先要重写的方法以及关联规则。实验结果表明,新手可以利用这些编码建议,快速学习一个新的框架,提高开发效率。     

吸附型“人工肝”辅助材料的制备及其性能研究Ⅱ.免疫吸附剂的制备及其吸附性能

本文介绍以醋酸乙烯酯为单体,二乙烯苯为交联剂制得大孔共聚物;经皂化、活化后,偶联IgG制得免疫吸附剂。讨论了不同活化剂对偶联配体的影响,观察其对人血清中的HBsAg的吸附性能。     

Detection of car parking space by using Hybrid Deep DenseNet Optimization algorithm

Internet of Things (IoT) and related applications have revolutionized most of our societal activities, enhancing the quality of human life. This study presents an IoT-based model that enables optimized parking space utilization. The paper implements a Hybrid Deep DenseNet Optimization (HDDNO) algorithm for predicting parking spot availability involving Machine Learning (ML) and deep learning techniques. The HDDNO-based ML model uses secondary data from the National Research Council Park (CNRPark) in Pisa, Italy. Different regression algorithms are employed to forecast parking lot availability for a given time as part of the prediction process. The DenseNet technique has generated promising results, whereas the HDDNO model yielded better accuracy. The use of five optimizers, namely, Adaptive Moment Estimation (Adam), Root Mean Squared Propagation (RMSprop), Adaptive Gradient (AdaGrad), AdaDelta, and Stochastic Gradient Descent (SGD), have played significant roles in minimizing the loss of the model. The part of Adam has enabled the HDDNO model to generate predictions with high accuracy 99.19% and low loss 0.0306%. This proposed methodology would significantly improve environmental safety and act as an initiative toward developing smart cities.     

A Second-row Parking Paradox

We consider two variations of the discrete car parking problem where at every vertex of ℤ cars (particles) independently arrive with rate one. The cars can park in two lines according to the following parking (adsorption) rules. In both models a car which arrives at a given vertex tries to park in the first line first. It parks (sticks) whenever the vertex and all of its nearest neighbors are not occupied yet. A car that cannot park in the first line will attempt to park in the second line. If it is obstructed in the second line as well, the attempt is discarded. In the screening model a) a car cannot pass through parked cars in the second line with midpoints adjacent to its vertex of arrival. In the model without screening b) cars park according to the same rules, but parking in the first line cannot be obstructed by parked cars in the second line. We show that both models are solvable in terms of finite-dimensional ODEs. We compare numerically the limits of first- and second-line densities, with time going to infinity. While it is not surprising that model a) exhibits an increase of the density in the second line from the first line, more remarkably this is also true for model b), albeit in a less pronounced way.     

Emerging quasi-0D states at vanishing total entropy of the 1D hard sphere system: A coarse-grained similarity to the car parking problem

A coarse-grained system of one-dimensional (1D) hard spheres (HSs) is created using the Delaunay tessellation, which enables one to define the quasi-0D state. It is found from comparing the quasi-0D and 1D free energy densities that a frozen state due to the emergence of quasi-0D HSs is thermodynamically more favorable than fluidity with a large-scale heterogeneity above crossover volume fraction of ${\varphi }_c=e/(1+e)=0.731\cdots$ , at which the total entropy of the 1D state vanishes. The Delaunay-based lattice mapping further provides a similarity between the dense HS system above ${\varphi }_c$ and the jamming limit in the car parking problem.     

Toward Cloud-Based Parking Facility Management System： A Preliminary Study

An e-tag used on the freeway is a kind of passive sensors composed of sensors and radio-frequency identification (RFID) tags. The principle of the electronic toll collection system is that the sensor emits radio waves touching the e-tag within a certain range, the e-tag will respond to the radio waves by induction, and the sensor will read and write information of the vehicles. Although the RFID technology is popularly used in campus management systems, there is no e-tag technology application used in a campus parking system. In this paper, we use the e-tag technology on a campus parking management system based on the cloud-based construction. By this, it helps to achieve automated and standardized management of the campus parking system, enhance management efficiency, reduce the residence time of the vehicles at the entrances and exits, and improve the efficiency of vehicles parked at the same time.     

The random parking problem

A new approach to the random parking problem is given.     

Autonomous parking control for intelligent vehicles based on a novel algorithm

Along with the increasing number of vehicles, parking space becomes narrow gradually, safety parking puts forward higher requirements on the driver's driving technology. How to safely, quickly and accurately park the vehiclo to parking space right? This paper presents an automatic parking scheme based on trajectory planning, which analyzing the mechanical model of the vehicle, establishing vehicle steering model and parking model, coming to the conclusion that it is the turning radius is independent of the vehicle speed at low speed. The Matlab simulation environment verifies the correctness and effectiveness of the proposed algorithm for parking. A class of the automatic parking problem of intelligent vehicles is solved.     

可穿戴型下肢助力机器人感知系统研究

在分析可穿戴型下肢助力机器人所需要的控制信息的基础上，设计了一套基于CAN总线的人体下肢运动信息感知系统。该系统主要包括可获取人体腿部和脚底状态的力传感器和获取髋关节和踝关节角度信息的编码器。实验结果表明，所设计的多传感器系统稳定，实时性好，满足可穿戴型下肢助力机器人系统控制的需要。