Real-Time Recognition and Location of Indoor Objects

Object recognition and location has always been one of the research hotspots in machine vision.It is of great value and significance to the development and application of current service robots,industrial automation,unmanned driving and other fields.In order to realize the real-time recognition and location of indoor scene objects,this article proposes an improved YOLOv3 neural network model,which combines densely connected networks and residual networks to construct a new YOLOv3 backbone network,which is applied to the detection and recognition of objects in indoor scenes.In this article,RealSense D415 RGB-D camera is used to obtain the RGB map and depth map,the actual distance value is calculated after each pixel in the scene image is mapped to the real scene.Experiment results proved that the detection and recognition accuracy and real-time performance by the new network are obviously improved compared with the previous YOLOV3 neural network model in the same scene.More objects can be detected after the improvement of network which cannot be detected with the YOLOv3 network before the improvement.The running time of objects detection and recognition is reduced to less than half of the original.This improved network has a certain reference value for practical engineering application.

A Multi-Objective Obnoxious Facility Location Modelon a Plane

In this paper a Vertex Covering Obnoxious Facility Location model on a Plane has been designed with a combination of three interacting criteria as follows: 1) Minimize the overall importance of the various exist-ing facility points;2) Maximize the minimum distance from the facility to be located to the existing facility points;3) Maximize the number of existing facility points covered. Area restriction concept has been incor-porated so that the facility to be located should be within certain restricted area. The model developed here is a class of maximal covering problem, that is covering maximum number of points where the facility is within the upper bounds of the corresponding mth feasible region Two types of compromise solution methods have been designed to get a satisfactory solution of the multi-objective problem. A transformed non- linear programming algorithm has been designed for the proposed non-linear model. Rectilinear dis-tance norm has been considered as the distance measure as it is more appropriate to various realistic situa-tions. A numerical example has been presented to illustrate the solution algorithm.

模糊对象的空间Co-location模式挖掘研究

空间co-location模式表示的是空间对象的实例在一个相同的区域内频繁地空间并置.过去人们已经对确定及不确定数据的co-location模式挖掘问题进行了一些研究,但是针对模糊对象上进行的研究还没有.模糊对象在许多领域里都有着非常重要的应用,比如生物医学图像数据库和GIS.该文研究模糊对象的空间co-location模式挖掘问题.首先,定义模糊对象上空间co-location模式挖掘的相关概念,包括模糊参与率、模糊参与度等.其次,提出FB算法挖掘模糊对象的co-location模式.接着,提出了3种改进算法,包括剪枝对象、减少实例间连接、改进剪枝步,以提高挖掘性能、加快co-location规则的产生.最后通过大量的实验说明FB算法及其改进算法的效果和效率.

不均匀模糊空间对象的分层次co-location模式挖掘方法

针对现有的co-location模式挖掘算法无法有效处理不均匀分布空间对象的问题,提出一种不均匀模糊空间对象的分层次co-location模式挖掘方法。首先提出一种不均匀数据集的生成方法;然后对不均匀分布的数据集进行层次划分,使每个区域具有均匀的空间分布;再基于改进的PO_RI_PC算法对划分后的模糊对象进行空间数据挖掘。该方法基于距离变化系数构建每个子区域的邻域关系图,进而完成区域融合,实现co-location模式挖掘。实验结果表明,与传统方法相比,所提方法的执行效率更高,随实例个数和不均匀度的变化获得的co-location集个数更多,同比情况下平均提高约25%,获得了更精确的挖掘结果。

一种模糊对象的极大co-location模式挖掘算法

空间co-location模式表示的是空间对象的实例在一个相同的区域内频繁地进行空间并置。人们已经对确定和不确定数据co-location模式挖掘做了很多工作,也有很多成果,但对极大co-location模式挖掘研究较少,特别是针对模糊对象的极大co-location模式挖掘研究还未见报道。提出Mevent-tree算法来挖掘模糊对象的极大co-location模式,首先为每个对象构建空间对象树,从而得到候选模式,然后为候选模式集构建HUT树,最后在HUT树中从阶数最大的候选模式开始到阶数2为止,深度优先搜索极大co-location模式并在得到极大模式后对HUT树剪枝。接着提出两个改进算法,包括预处理阶段模糊对象的剪枝算法和在构造HUT树之前co-location候选模式的剪枝算法。最后通过大量实验验证了Mevent-tree算法和改进算法的效果和效率。

Robust location algorithm for NLOS environments

One of the main problems facing accurate location in wireless communication systems is non-line-of- sight （NLOS） propagation. Traditional location algorithms are based on classical techniques under minimizing a least-squares objective function and it loses optimality when the NLOS error distribution deviates from Gaussian distribution. An effective location algorithm based on a robust objective function is proposed to mitigate NLOS errors. The proposed method does not require the prior knowledge of the NLOS error distribution and can give a closed-form solution. A comparison is performed in different NLOS environments between the proposed algorithm and two additional ones （LS method and Chan＇s method with an NLOS correction）. The proposed algorithm clearly outperforms the other two.

Locating the position of objects in non-line-of-sight based on time delay estimation

Non-line-of-sight imaging detection is to detect hidden objects by indirect light and intermediary surface（diffuser）.It has very important significance in indirect access to an object or dangerous object detection, such as medical treatment and rescue. An approach to locating the positions of hidden objects is proposed based on time delay estimation. The time delays between the received signals and the source signal can be obtained by correlation analysis, and then the positions of hidden objects will be located. Compared with earlier systems and methods, the proposed approach has some modifications and provides significant improvements, such as quick data acquisition, simple system structure and low cost, and can locate the positions of hidden objects as well： this technology lays a good foundation for developing a practical system that can be used in real applications.

Efficient Location Services Using Hierarchical Topology of Mobile Ad Hoc Networks

The thesis work was carried out in two phases. Firstly, we have designed the Cluster-Based Object Location Algorithm (CBOLA) for finding the object location in a cluster based network topology. Secondly, to take the advantages of clustering architecture of Mobile Ad hoc Networks, we have especially designed Object Location Clusters Algorithm (OLCA) for efficient Object Location management in MANET. Our comparison of simulation analysis shows that the CBOLA is more efficient and accurate in location information services and more robust than GLS and HRLS. In addition, we believe that our comparative study with the various location services schemes was facilitated accurate results in ad hoc networks. we are portioned our network area by designing a new clustering algorithm called OLCA (Object Location Clusters Algorithm) for efficient object location in Mobile Ad hoc Networks. Simulation results and comparative analysis shows the performance and effectiveness of CBOLA and OLCA.

Models for Location Inventory Routing Problem of Cold Chain Logistics with NSGA-Ⅱ Algorithm

In this paper,a novel location inventory routing(LIR)model is proposed to solve cold chain logistics network problem under uncertain demand environment. The goal of the developed model is to optimize costs of location,inventory and transportation.Due to the complex of LIR problem( LIRP), a multi-objective genetic algorithm(GA), non-dominated sorting in genetic algorithm Ⅱ( NSGA-Ⅱ) has been introduced. Its performance is tested over a real case for the proposed problems. Results indicate that NSGA-Ⅱ provides a competitive performance than GA,which demonstrates that the proposed model and multi-objective GA are considerably efficient to solve the problem.

Budget constrained flow interception location model for congested systems

To study location problems with congestion demand, a bi-objective model based on flow intercep-tion problem is proposed.The model is formulated from the view of M/M/m queuing systems.Service quantity and quality are simultaneously considered as objectives, with constraint on total cost.Service quality includes deviation distance from preplanned trips and customers＇ waiting time.Service quantity is the number of intercep-tion customers.A multi-objective evolutionary algorithm combined with greedy heuristic is proposed.Finally a computational experiment is given, and the algorithm is proved to be efficient.

Research on Location-Routing Problem with Empirical Analysis for Regional Logistics Distribution

The location of the distribution facilities and the routing of the vehicles from these facilities are interdependent in many distribution systems. Such a concept recognizes the interdependence;attempts to integrate these two decisions have been limited. Multi-objective location-routing problem (MLRP) is combined with the facility location and the vehicle routing decision and satisfied the different objectives. Due to the problem complexity, simultaneous solution methods are limited, which are given in different objectives with conflicts in functions satisfied. Two kinds of optimal mathematical models are proposed for the solution of MLRP. Three methods have been emphatically developed for MLRP. MGA architecture makes it possible to search the solution space efficiently, which provides a path for searching the solution with two-objective LRP. At last the practical proof is given by random analysis for regional distribution with nine cities.

Design and Implementation of Lightning Analysis Software Based on Lightning Location System Data

This paper discusses the steps about how to design and implement software based on lightning location system data and its localization map.The system contains four major modules such as real-time lightning monitoring,historical query,lightning intensity zoning,lightning disaster statistics,etc.The system is able to automatically generate real-time lightning monitoring image,lightning animation,and lightning intensity zoning image,which contributes to the high accuracy of the calculation results and the efficiency of data analysis.The paper also points out the deficiencies of software life cycle management and proposes actionable solutions.

A Dynamic Interval Based Circular Safe Region Algorithm for Continuous Queries on Moving Objects

Moving object database (MOD) engine is the foundation of Location-Based Service (LBS) information systems. Continuous queries are important in spatial-temporal reasoning of a MOD. The communication costs were the bottleneck for improving query efficiency until the rectangular safe region algorithm partly solved this problem. However, this algorithm can be further improved, as we demonstrate with the dynamic interval based continuous queries algorithm on moving objects. Two components, circular safe region and dynamic intervals were adopted by our algorithm. Theoretical proof and experimental results show that our algorithm substantially outperforms the traditional periodic monitoring and the rectangular safe region algorithm in terms of monitoring accuracy, reducing communication costs and server CPU time. Moreover, in our algorithm, the mobile terminals do not need to have any computational ability.

Optimal setting and placement of FACTS devices using strength Pareto multi-objective evolutionary algorithm

This work proposes a novel approach for multi-type optimal placement of flexible AC transmission system(FACTS) devices so as to optimize multi-objective voltage stability problem. The current study discusses a way for locating and setting of thyristor controlled series capacitor(TCSC) and static var compensator(SVC) using the multi-objective optimization approach named strength pareto multi-objective evolutionary algorithm(SPMOEA). Maximization of the static voltage stability margin(SVSM) and minimizations of real power losses(RPL) and load voltage deviation(LVD) are taken as the goals or three objective functions, when optimally locating multi-type FACTS devices. The performance and effectiveness of the proposed approach has been validated by the simulation results of the IEEE 30-bus and IEEE 118-bus test systems. The proposed approach is compared with non-dominated sorting particle swarm optimization(NSPSO) algorithm. This comparison confirms the usefulness of the multi-objective proposed technique that makes it promising for determination of combinatorial problems of FACTS devices location and setting in large scale power systems.

A Mathematical Optimization Model for Locating Telecenters

Telecommuting is a Transportation Demand Management strategy to partially or completely replace the daily commute with telecommunication technologies. Research has revealed that telecommuting can be effectively done from special places provided for this purpose called telecenters. In telecenter-based telecommuting, trip lengths are shortened due to change in the location of work places. Thus suitable locations of telecenters play an important role in increasing the beneficial impacts of telecommuting in the transportation systems. In this research, a mathematical optimization model for finding optimal location and capacity of telecenters is proposed. This model is a bi-objective linear program, and a Fuzzy Goal Programming method with a preemptive structure is used to solve it. Telecommuting demand is classified into three groups of telecommuters and a priority structure that assigns the higher priority class to the closer telecenters is also incorporated into the model. The proposed model is implemented in a case study of finding optimal location of telecenters for government employees in Tehran (capital of Iran) metropolitan area. The base model is solved and its sensitivity to different parameters has been analyzed based on which, an optimal model is selected. The solution of this model is an optimal pattern for distribution of telecommuting capacities and yields the most system-wide benefits from implementation of telecommuting.

考虑区域资源利用均衡的电动公交充电站选址及充电路径问题

在新基建助推区域平衡发展和低碳双重背景下,研究电动公交充电站选址及充电路径问题,以经济效益最大化和区域资源利用均衡为目标,考虑公交司机可能充电时机以及充电需求、运营时间、利用率等约束条件建立两阶段多目标决策模型,设计多重嵌套式遗传算法求解模型,并应用于算例检验模型可行性。结果表明:仅考虑经济效益目标会产生充电“拥挤”、路途过长等弊端,而本文模型能有效缩小区域间公交充电效率差异,提高全局资源利用均衡性;通过降低充电站容量可提高充电站利用率与经济效益,但区域资源利用均衡性会减弱,且充电站容量对公交充电路途所耗费时间的作用较为敏感;适当增加区域资源利用均衡目标的权重更有利于提高总体优化效果。研究结果可为公交充电站选址和路径规划提供决策支持。

考虑需求密度和客户满意度的城市末端服务网点选址问题

为解决“最后一公里”的配送问题,结合城市末端配送需求的服务网点特点,考虑需求密度和客户满意度,建立了以时间满意度最大化、利润最大化和需求密度最大化为目标的多目标选址模型。设计了基于线性加权法的改进自适应遗传算法,采用自适应算子处理变异概率和交叉概率,并设计三种不同的交叉算子,扩大搜索邻域。在改进算子的基础上设计了多目标遗传算法,使用快速非支配排序法去除权重系数取值对选址结果的影响。利用北京市海淀区的快递服务网络数据进行实例分析,使用设计的两种遗传算法分别求解选址模型的全局最优解和帕累托前沿解;并将改进自适应遗传算法与传统遗传算法、自适应遗传算法的求解结果进行比较。结果显示:改进自适应遗传算法比传统遗传算法和自适应遗传算法收敛速度更快、搜索能力更优;若无法确定改进自适应遗传算法的权重,使用改进后的多目标遗传算法同样可以求到最优解。

考虑道路通行能力差异的多应急避难点选址模型及算法

合理的应急避难点选址可以有效提高疏散效率,而道路通行能力的差异性特征是影响避难点选址决策的重要因素。本文在道路通行容量和通行速度不同的情形下,以最大完成时间和总完成时间的组合函数最小化为目标,研究路图上有堵塞时间成本的k个避难点选址问题。首先,本文重点分析不同的道路通行容量和通行速度对疏散过程的影响,对疏散过程中的堵塞变化进行梳理,对路图进行等价转换。其次,本文基于等价路图把组合目标下的多避难点选址问题转化为有限个有最大完成时间限制的、以总完成时间最小化为目标的k避难点选址问题,之后基于动态规划设计多项式时间的求解算法。最后,本文给出相应的数值算例,并对组合目标函数中的权重系数进行敏感性分析。

基于改进NSGA-Ⅱ算法的选址与路径优化问题

为有效解决冷链物流过程中的污染气体排放量高和物流成本高的问题,通过对其配送中心选址和车辆路径优化问题的研究,开发了一个涉及到成本、时间及碳排放因素的冷链物流配送选址-路径多目标优化模型。针对模型求解困难的问题,基于免疫算子,提出改进的NSGA-Ⅱ算法,结合实际案例进行计算和分析。结果表明:碳排放量对冷链物流配送中心选址与运输路径选择的最优决策产生显著影响。改进的NSGA-Ⅱ算法比传统算法在运算效率、多样性和收敛性能方面更具有优势。研究结果证实了该模型及算法在指导冷链物流配送中心选址和车辆配送路径优化决策中的应用价值,为企业决策提供了新的理论支持。