Vision-based estimation of the number of occupants using video cameras

Although occupancy information is critical to energy consumption of existing buildings, it still remains to be a major source of uncertainty. For reliable and accurate occupant modeling with minimal uncertainties, capturing precise occupant information on occupants is essential. This paper proposes a computer vision-based approach that utilizes deep learning architectures to estimate of the number of people in large, crowded spaces using multiple cameras. Various vision techniques (head detection, background elimination, head tracking) are implemented in three methods: (i) a method that instantaneously counts people in a scene, (ii) a method that incrementally counts people entering/exiting a room and (iii) a combination of the first two methods. These methods were applied in a classroom with heavy occlusions, and resulted in a high prediction capacity when compared to ground truth measurements. Future work in video-analytical approaches can address problems regarding lowering the computational cost of analysis, capturing occupancy data in complex room geometries and addressing concerns in privacy preservation.     

基于城市交通监控大数据的工作位置推理方法

基于时空数据的用户位置推理在产品推荐、精确营销、交通调度及城市规划等实际应用中有着重要的作用,然而,基于城市交通监控数据的位置推理问题尚未被探索,因此,提出了一种面向稀疏摄像头交通监控数据的工作位置推理方法。首先,收集了路网、兴趣点（POI）等城市交通外围数据,并通过路网匹配的预处理方式获取到了一个含有摄像头、POI等丰富语义信息的真实路网;其次,通过聚类车辆轨迹中所提取的起点-终点（O-D）对来获得车辆重要的停留区域,即候选工作区域;之后,利用所提的in/out访问时间模式的约束,从多个候选区域中匹配出最大可能的工作区域;最后,利用所获取的路网信息和路网周中POI的分布信息提取出车辆的可达POI集合,从而进一步缩小车主的工作位置范围。在一个省会城市真实的交通监控数据集上的综合实验评估和案例分析验证了所提方法的有效性。     

Universal background modeling for acoustic surveillance of urban traffic

Traffic congestion in modern cities is an increasing problem having significant consequences in our daily lives. This work proposes a non-intrusive, passive monitoring framework based on the acoustic modality which can be used either autonomously or as a part of a multimodal system and provide valuable information to an intelligent transportation system. We consider a large number of audio classes which are typically encountered in urban areas. We introduce a combination of a powerful audio representation mechanism based on time, frequency and wavelet domain features with universal background modeling which leads to higher recognition accuracies and detection rates (in terms of false alarm and miss probability rates) with respect to commonly employed methodologies. The basic advantage of a class-specific model derived using the universal background modeling logic is its tolerance to data which belong to other sound classes. Another important feature of the proposed system is its ability to detect crash incidents, which apart from their catastrophic impact on human life and property, have negative consequences on the traffic flow. Our experiments are based on the concurrent usage of professional sound effect collections which include audio recordings of high quality. We thoroughly examine the performance of the proposed system on isolated sound events as well as continuous audio streams using confusion matrices and detection error trade-off curves.     

Real-time path planning with limited information for autonomous unmanned air vehicles

We propose real-time path planning schemes employing limited information for fully autonomous unmanned air vehicles (UAVs) in a hostile environment. Two main algorithms are proposed under different assumptions on the information used and the threats involved. They consist of several simple (computationally tractable) deterministic rules for real-time applications. The first algorithm uses extremely limited information (only the probabilistic risk in the surrounding area with respect to the UAV's current position) and memory, and the second utilizes more knowledge (the location and strength of threats within the UAV's sensory range) and memory. Both algorithms provably converge to a given target point and produce a series of safe waypoints whose risk is almost less than a given threshold value. In particular, we characterize a class of dynamic threats (so-called, static-dependent threats) so that the second algorithm can efficiently handle such dynamic threats while guaranteeing its convergence to a given target. Challenging scenarios are used to test the proposed algorithms.     

Discrete-time point processes in urban traffic queue estimation

This research was motivated by the belief that it is possible to develop improved algorithms for the computer control of urban traffic. Previous research suggested that the computer software, and especially the filtering and prediction algorithms, is the limiting factor in computerized traffic control. Since the modern approach to filtering and prediction begins with the development of models for the generation of the data and since these models are also useful in the control problem, this paper deals with the modeling of traffic queues and filtering and prediction. It is shown that the data received from vehicle detectors is a discrete-time point process. The formation and dispersion of queues at a traffic signal is then modeled by a discrete-time time-varying Markov chain which is related to the observation point process. Three such models of increasing complexity are given. Recent results in the theory of point-process filtering and prediction are then used to derive the nonlinear minimum error variance filters/predictors corresponding to these models. It is then shown that these optimal estimators are computationally feasible in a micro-processor. All three algorithms were tested against the UTCS-1 traffic simulator and, in one case, against an algorithm in current use called ASCOT. Some results of these tests are shown. They indicate good performance in every case and better performance than ASCOT in the comparable case.     

一种利用UKF的高速公路实时交通状态估计方法

把无轨迹卡尔曼滤波器（UKF）和宏观随机交通流模型结合在一起,可以实现对高速公路交通状态的实时估计。高速公路被看作是由等距离的路段首尾相接而成的系统,每个路段中交通变量的更新不光与其自身有关,还受到相邻路段的影响。交通传感器通常设置在路段的交界处,而且数量远少于所需估计的交通状态。采用压缩状态空间的形式,将模型参数也作为交通状态而非常量进行估计。仿真结果表明UKF方法能够有效地估计和跟踪交通状态的变化,并且与扩展卡尔曼滤波方法相比具有更高的精确度。     

Using GIS to design a traffic information database for urban transport planning

The aim of this paper is to describe the development of a prototype geographical information system (GIS) for urban transport planning in a district of a South-East Kowloon redevelopment area. In this paper, the GIS database is developed with consideration of efficient data input and retrieval process in a way that is most useful to transportation planners for network travel demand projection and evaluation purposes. The GIS-transportation (GIS-T) database is designed for (a) realistic simulations of network in both two-dimensional and three-dimensional forms, (b) manipulating various types of transport-related information in one consistent database, and (c) supporting tools for scenario comparison between existing and future network flow change in a predefined study area. The results show that GIS-T would refine the database management process and demonstrate the potential of linking computer graphics and multimedia information in transport planning. More importantly, both existing and future network-flow performance are interactively displayed in graphical formats and, therefore, transport planners can gain a better understanding and insight to assess the performance of the proposed transportation system.     

Camera location optimisation for traffic surveillance in urban road networks with multiple user classes

New sensor technologies (e.g. surveillance cameras, loop detectors) enable the synthesis of disaggregated vehicle information from multiple locations. This article studies the camera location problem for traffic surveillance in urban road networks with multiple user classes. All users are differentiated by their own acceptance degree of camera monitoring and make their route choices in a logit-based stochastic user equilibrium manner. A bi-level programming model is proposed to formulate the problem and solved by the sensitivity analysis based branch and bound method. Numerical examples are presented to illustrate the model application and show the effectiveness of the solution method.     

基于蚁群算法的城域交通控制实时滚动优化

为求解城域交通控制实时滚动优化的混合整数规划模型，将滚动优化各阶段的控制变量映射为一个层状构造图，并定义局部启发信息和信息素更新公式，从而应用蚁群算法搜索各路口的最优信号灯相位序列．对算法复杂度作了理论分析，并通过仿真实验与单路口感应式信号控制技术进行比较，结果表明性能较好．     

Uniform metrical task systems with a limited number of states

We give a randomized algorithm (the “Wedge Algorithm”) of competitiveness for any metrical task system on a uniform space of k points, for any k?2, where , the kth harmonic number. This algorithm has better competitiveness than the Irani-Seiden algorithm if k is smaller than 10⁸. The algorithm is better by a factor of 2 if k<47.     

城市环境中交通信号灯准确识别与状态估计

根据交通信号灯灯板颜色和形状定位图像中的灯板位置. 将灯板区域的彩色图像转换到YCbCr 空间, 分割灯板区域中的红、黄、绿三色区域, 利用交通信号灯的形态特性定位交通灯位置. 用Gabor 小波和2 维独立分量分析提取感兴趣区域的特征, 送入最近邻分类器分类信号灯的类型. 用代表性的观测序列建立隐马尔科夫模型, 并结合识别和跟踪结果估计信号灯状态. 实验结果表明, 该算法能可靠、准确地识别出信号灯, 并有效地估计出信号灯的状态.     

Scheduling projects with limited number of preemptions

A recent paper (Ballestín F, Valls V, Quintanilla S. Preemption in resource-constrained project scheduling. European Journal of Operational Research 2008;189:1136–152) revealed the potential benefits of allowing one interruption when scheduling activities in a resource-constrained project. This paper further investigates the effect of interruption on project length in more general cases. To achieve this, a new model that covers most practical applications of discrete activity preemption is proposed and a metaheuristic algorithm for the problem is developed. Computational experiments on the standard j120 and j30 sets generated using ProGen study the difference in makespan between allowing m$m$ interruptions per activity, m=0,1,2,…$m=0,1,2,\dots$ . In the second part of the paper the usefulness of preemption in the presence of due dates is analysed.     

Real-time free viewpoint video from a range sensor and color cameras

We propose a method for computing a depth map at interactive rates from a set of closely spaced calibrated video cameras and a Time-of-Flight (ToF) camera. The objective is to synthesize free viewpoint videos in real-time. All computations are performed on the graphics processing unit, leaving the CPU available for other tasks. Depth information is computed from color camera data in textured regions and from ToF data in textureless ones. The trade-off between these two sources is determined locally based on the reliability of the depth estimates obtained from the color images. For this purpose, a confidence measure taking into account the shape of the photo-consistency score as a function of depth is used. The final depth map is computed by minimizing a cost function. This approach offers a significant time savings relative to other methods that apply denoising to the photo-consistency score maps, obtained at every depth, and importantly, still obtains acceptable quality of the rendered image.     

Dynamic calibration of pan-tilt-zoom cameras for traffic monitoring.

Pan-tilt-zoom (PTZ) cameras have been widely used in recent years for monitoring and surveillance applications. These cameras provide flexible view selection as well as a wider observation range. This makes them suitable for vision-based traffic monitoring and enforcement systems. To employ PTZ cameras for image measurement applications, one first needs to calibrate the camera to obtain meaningful results. For instance, the accuracy of estimating vehicle speed depends on the accuracy of camera calibration and that of vehicle tracking results. This paper presents a novel calibration method for a PTZ camera overlooking a traffic scene. The proposed approach requires no manual operation to select the positions of special features. It automatically uses a set of parallel lane markings and the lane width to compute the camera parameters, namely, focal length, tilt angle, and pan angle. Image processing procedures have been developed for automatically finding parallel lane markings. Interesting experimental results are presented to validate the robustness and accuracy of the proposed method.     

基于视频信息的城市路段交通安全状态评估方法研究

城市道路交通安全状态实时评估是智能交系统的重要研究内容。针对现有交通安全状态实时评估方法的评估效果不理想的问题,建立了基于视频信息的城市路段交通安全状态评估方法。首先,分析了基于视频信息的交通流参数快速检测方法;然后,从车速离散度的角度提出了影响城市路段交通安全状态的路段车速离散度的概念;最后,建立了基于路段车速离散度的城市路段交通安全状态评估方法。实验表明,所提方法能够实时合理地对城市道路的安全状态水平进行评估,评估结果可以为交通管理部门制定有效的城市路段交通安全改进方案提供相应的依据。     

The optimal locations of surveillance cameras on straight lanes

In this paper, we investigate the optimal locations of surveillance cameras on straight lanes. As known, inappropriate settings of surveillance cameras will result in some dead angles and dead space, and oversetting of surveillance cameras will waste limited resources. The considered location problem aims to minimize the maximal detection failure probability of points on straight lane subject to a limited budget. The problem is an important and complex location problem in practice. The purpose of this paper is twofold. Firstly, exact closed forms of optimal locations of single-type surveillance cameras are derived. Secondly, we apply a PSO algorithm for solving the types and locations of multiple-type surveillance cameras. Numerical results are reported and compared with those by well known software LINGO. Limited numerical results show the effectiveness of PSO especially when the budget is limited.     

Structural optimization with limited number of element properties

This note investigates the weight lost of a structure that presents a limited number of cross-sections for its members. A combined genetic algorithm-gradient approach is used to obtain the minimum weight structure for various numbers of cross-sections. The problem is investigated for the well known ten-bar truss structure. Results show that decreasing the number of cross-sections from nine to four has a small impact on the weight of approximately 5.3%.     

Newsvendor optimization with limited distribution information

Lack of complete distribution calls for stochastically robust models that, after exploiting available limited or partial information, offer risk-shielded solutions, or in other words, solutions that are insensitive to all possible distributions of random variables. We focus on the well-known newsvendor problem in this study, where the distribution of the random demand is only specified by its mean and one of the following: its standard deviation or its support. We propose a stochastically robust model for the newsvendor problem. More specifically, our model tries to minimize the regret that is defined as the ratio of the expected cost based on limited information to that based on complete information, called Relative Expected Value of Distribution (REVD). We show how to derive an optimal solution to the REVD model. Numerical examples are provided to compare our model with other similar approaches. The goal is to establish a confidence ratio that the decision from our model is not worse, relatively, too much than the decision based on the true distribution which would be never known exactly in real-world applications.