There has been a significant number of security concerns in recent times; as a result, security cameras have been installed to monitor activities and to prevent crimes in most public places. These analysis are done either through video analytic or forensic analysis operations on human observations. To this end, within the research context of this thesis, a proactive machine vision based military recognition system has been developed to help monitor activities in the military environment. The proposed object detection, recognition and re-identification systems have been presented in this thesis. A novel technique for military personnel recognition is presented in this thesis. Initially the detected camouflaged personnel are segmented using a grabcut segmentation algorithm. Since in general a camouflaged personnel's uniform appears to be similar both at the top and the bottom of the body, an image patch is initially extracted from the segmented foreground image and used as the region of interest. Subsequently the colour and texture features are extracted from each patch and used for classification. A second approach for personnel recognition is proposed through the recognition of the badge on the cap of a military person. A feature matching metric based on the extracted Speed Up Robust Features (SURF) from the badge on a personnel's cap enabled the recognition of the personnel's arm of service. A state-of-the-art technique for recognising vehicle types irrespective of their view angle is also presented in this thesis. Vehicles are initially detected and segmented using a Gaussian Mixture Model (GMM) based foreground/background segmentation algorithm. A Canny Edge Detection (CED) stage, followed by morphological operations are used as pre-processing stage to help enhance foreground vehicular object detection and segmentation. Subsequently, Region, Histogram Oriented Gradient (HOG) and Local Binary Pattern (LBP) features are extracted from the refined foreground vehicle object and used as features for vehicle type recognition. Two different datasets with variant views of front/rear and angle are used and combined for testing the proposed technique. For night-time video analytics and forensics, the thesis presents a novel approach to pedestrian detection and vehicle type recognition. A novel feature acquisition technique named, CENTROG, is proposed for pedestrian detection and vehicle type recognition in this thesis. Thermal images containing pedestrians and vehicular objects are used to analyse the performance of the proposed algorithms. The video is initially segmented using a GMM based foreground object segmentation algorithm. A CED based pre-processing step is used to enhance segmentation accuracy prior using Census Transforms for initial feature extraction. HOG features are then extracted from the Census transformed images and used for detection and recognition respectively of human and vehicular objects in thermal images. Finally, a novel technique for people re-identification is proposed in this thesis based on using low-level colour features and mid-level attributes. The low-level colour histogram bin values were normalised to 0 and 1. A publicly available dataset (VIPeR) and a self constructed dataset have been used in the experiments conducted with 7 clothing attributes and low-level colour histogram features. These 7 attributes are detected using features extracted from 5 different regions of a detected human object using an SVM classifier. The low-level colour features were extracted from the regions of a detected human object. These 5 regions are obtained by human object segmentation and subsequent body part sub-division. People are re-identified by computing the Euclidean distance between a probe and the gallery image sets. The experiments conducted using SVM classifier and Euclidean distance has proven that the proposed techniques attained all of the aforementioned goals. The colour and texture features proposed for camouflage military personnel recognition surpasses the state-of-the-art methods. Similarly, experiments prove that combining features performed best when recognising vehicles in different views subsequent to initial training based on multi-views. In the same vein, the proposed CENTROG technique performed better than the state-of-the-art CENTRIST technique for both pedestrian detection and vehicle type recognition at night-time using thermal images. Finally, we show that the proposed 7 mid-level attributes and the low-level features results in improved performance accuracy for people re-identification.

This thesis compares different approaches to estimating budgets for Kuhn-Tucker (KT) demand systems, more specifically for the multiple discrete-continuous extreme value (MDCEV) model. The approaches tested include: (1) The log-linear regression approach (2) The stochastic frontier regression approach, and (3) arbitrarily assumed budgets that are not necessarily modeled as a function of decision maker characteristics and choice-environment characteristics. The log-linear regression approach has been used in the literature to model the observed total expenditure as way of estimating budgets for the MDCEV models. This approach allows the total expenditure to depend on the characteristics of the choice-maker and the choice environment. However, this approach does not offer an easy way to allow the total expenditure to change due to changes in choice alternative-specific attributes, but only allows a reallocation of the observed total expenditure among the different choice alternatives. To address this issue, we propose the stochastic frontier regression approach. The approach is useful when the underlying budgets driving a choice situation are unobserved, but only the expenditures on the choice alternatives of interest are observed. The approach is based on the notion that consumers operate under latent budgets that can be conceived (and modeled using stochastic frontier regression) as the maximum possible expenditure they are willing to incur. To compare the efficacy of the above-mentioned approaches, we performed two empirical assessments: (1) The analysis of out-of-home activity participation and time-use (with a budget on the total time available for out-of-home activities) for a sample of non-working adults in Florida, and (2) The analysis of household vehicle type/vintage holdings and usage (with a budget on the total annual mileage) for a sample of households in Florida. A comparison of the MDCEV model predictions (based on budgets from the above mentioned approaches) demonstrates that the log-linear regression approach and the stochastic frontier approach performed better than arbitrarily assumed budgets approaches. This is because both approaches consider heterogeneity in budgets due to socio-demographics and other explanatory factors rather than arbitrarily imposing uniform budgets on all consumers. Between the log-linear regression and the stochastic frontier regression approaches, the log-linear regression approach resulted in better predictions (vis-à-vis the observed distributions of the discrete-continuous choices) from the MDCEV model. However, policy simulations suggest that the stochastic frontier approach allows the total expenditures to either increase or decrease as a result of changes in alternative-specific attributes. While the log-linear regression approach allows the total expenditures to change as a result of changes in relevant socio-demographic and choice-environment characteristics, it does not allow the total expenditures to change as a result of changes in alternative-specific attributes.

Activity-based travel demand model systems are increasingly being deployed to microsimulate daily activity-travel patterns of individuals. However, a critical dimension that is often missed in these models is that of vehicle type choice. The current dissertation addresses this issue head-on and contributes to the field of transportation planning in three major ways. First, this research develops a comprehensive vehicle micro-simulation framework that incorporates state-of-the-art household vehicle type choice, usage, and evolution models. The novelty of the framework developed is that it accommodates all the dimensions characterizing vehicle fleet/usage decisions, as well as accommodates all dimensions of vehicle transactions (i.e., fleet evolution) over time. The models estimated are multiple discrete-continuous models (vehicle type being the discrete component and vehicle mileage being the continuous component) and spatial discrete choice models that explicitly accommodate for multiple vehicle ownership and spatial interactions among households. More importantly, the vehicle fleet simulator developed in this study can be easily integrated within an activity-based microsimulation framework. Second, the vehicle fleet evolution and composition models developed in this dissertation are used to predict the vehicle fleet characteristics, annual mileage, and the associated fuel consumption and green-house gas (GHG) emissions for future years as a function of the built environment, demographics, fuel and related technology, and policy scenarios. This exercise contributes in substantial ways to the identification of promising strategies to increase the penetration of alternative-fuel vehicles and fuel-efficient vehicles, reduce energy consumption, and reduce greenhouse gas emissions. Lastly, this research captures several complex interactions between vehicle ownership, location, and activity-travel decisions of individuals by estimating 1) a joint tour-based model of tour complexity, passenger accompaniment, vehicle type choice, and tour length, and 2) an integrated model of residential location, work location, vehicle ownership, and commute tour characteristics. The methodology used for estimating these models allows the specification and estimation of multi-dimensional choice model systems covering a wide spectrum of dependent variable types (including multinomial, ordinal, count, and continuous) and may be viewed as a major advance with the potential to lead to redefine the way activity-based travel model systems are structured and implemented. / text

No description available.

abstract: Vehicle type choice is a significant determinant of fuel consumption and energy sustainability; larger, heavier vehicles consume more fuel, and expel twice as many pollutants, than their smaller, lighter counterparts. Over the course of the past few decades, vehicle type choice has seen a vast shift, due to many households making more trips in larger vehicles with lower fuel economy. During the 1990s, SUVs were the fastest growing segment of the automotive industry, comprising 7% of the total light vehicle market in 1990, and 25% in 2005. More recently, due to rising oil prices, greater awareness to environmental sensitivity, the desire to reduce dependence on foreign oil, and the availability of new vehicle technologies, many households are considering the use of newer vehicles with better fuel economy, such as hybrids and electric vehicles, over the use of the SUV or low fuel economy vehicles they may already own. The goal of this research is to examine how vehicle miles traveled, fuel consumption and emissions may be reduced through shifts in vehicle type choice behavior. Using the 2009 National Household Travel Survey data it is possible to develop a model to estimate household travel demand and total fuel consumption. If given a vehicle choice shift scenario, using the model it would be possible to calculate the potential fuel consumption savings that would result from such a shift. In this way, it is possible to estimate fuel consumption reductions that would take place under a wide variety of scenarios. / Dissertation/Thesis / M.S. Civil Engineering 2013

After significant efforts from many parties, the World-wide harmonized Light duty Test Procedure (WLTP) has seen its light first as the UNECE Global Technical Regulation and then as the procedure adopted in the type-approval of light-duty vehicles in Europe. The paper focuses its attention on the main procedural differences between the WLTP and the New European Driving Cycle (NEDC), which is the test-procedure currently used in Europe. In general terms the WLTP appears to be a significant improvement compared to the NEDC. The main differences between two test procedures are identified and their impact on CO2 emissions quantified using the in-house built simulation software CO2MPAS. On the basis of each of these differences, the paper assesses the potential total impact on the final reported type-approval CO2 emissions. The biggest impact on CO2 emissions is coming from the changes in the road load determination procedure (∼10% increase). Procedural changes concerning the test in the laboratory will bring another 8% and post-processing and declaration of results will result in difference of approximately 5% (each). Overall, the WLTP is likely to increase the type-approval CO2 emissions by approximately 25%. Therefore, the WLTP will be able to reduce more than half of the gap identified between the type-approval and real-life figures in Europe. This should be seen as a considerable improvement given the ontological limitations of a laboratory-based test procedure.

An analysis of the effect of passing vehicles’ characteristics and their impact on other drivers’ velocities was investigated. Three experimental studies were proposed and likely outcomes were discussed. Experiment 1 focused on the effect of passing vehicle type (SUV, sedan or truck) on driver speed. Drivers were hypothesized as going faster when the same vehicle type as they were driving passed them versus when no vehicle or a different vehicle passed them. Experiment 2 focused on the effect of passing SUV age on driver’s speed. Evidence suggests passing older SUVs will increase the driver’s speed more than new SUVs. Experiment 3 focused on the effect of passing SUV color on speed. Drivers were hypothesized to go faster when brighter colors (red and yellow) rather than cooler colors (grey and black) were painted on the vehicle.

abstract: This dissertation research contributes to the advancement of activity-based travel forecasting models along two lines of inquiry. First, the dissertation aims to introduce a continuous-time representation of activity participation in tour-based model systems in practice. Activity-based travel demand forecasting model systems in practice today are largely tour-based model systems that simulate individual daily activity-travel patterns through the prediction of day-level and tour-level activity agendas. These tour level activity-based models adopt a discrete time representation of activities and sequence the activities within tours using rule-based heuristics. An alternate stream of activity-based model systems mostly confined to the research arena are activity scheduling systems that adopt an evolutionary continuous-time approach to model activity participation subject to time-space prism constraints. In this research, a tour characterization framework capable of simulating and sequencing activities in tours along the continuous time dimension is developed and implemented using readily available travel survey data. The proposed framework includes components for modeling the multitude of secondary activities (stops) undertaken as part of the tour, the time allocated to various activities in a tour, and the sequence in which the activities are pursued. Second, the dissertation focuses on the implementation of a vehicle fleet composition model component that can be used not only to simulate the mix of vehicle types owned by households but also to identify the specific vehicle that will be used for a specific tour. Virtually all of the activity-based models in practice only model the choice of mode without due consideration of the type of vehicle used on a tour. In this research effort, a comprehensive vehicle fleet composition model system is developed and implemented. In addition, a primary driver allocation model and a tour-level vehicle type choice model are developed and estimated with a view to advancing the ability to track household vehicle usage through the course of a day within activity-based travel model systems. It is envisioned that these advances will enhance the fidelity of activity-based travel model systems in practice. / Dissertation/Thesis / Doctoral Dissertation Civil and Environmental Engineering 2014

Elektrifizierte Lastenfahrräder werden als ein Lösungsansatz für die wachsenden Herausforderungen des städtischen Wirtschaftsverkehrs gesehen. Fokus dieser Arbeit ist eine Abschätzung des Einsatzpotenzials dieses Fahrzeugkonzepts unter Betrachtung von konzeptionellen, verkehrlichen und wirtschaftlichen Aspekten. Als kumulative Dissertation enthält sie fünf Fachartikel, gruppiert zu drei Forschungsbeiträgen. Im ersten Forschungsbeitrag wird erörtert, wie erfolgversprechend das E-Lastenrad, eine Neuauflage des alten Konzepts Lastenfahrrad, in einem Markt mit ersten Anwendern (Kurierdienstleistung) ist. Die Auftragsstruktur im Stadtkuriergeschäft bietet ein substanzielles Marktpotenzial für E-Lastenräder, allerdings erschwert die Positionierung zwischen zwei etablierten Modi (Pkw und Fahrrad) den Markteintritt. Der zweite Teil der Analyse weitet den Blick auf alle Branchen und bietet eine strukturierte Beschreibung der verschiedenartigen Einflussfaktoren (Treiber und Hemmnisse), die auf die Lastenradnutzung im städtischen Wirtschaftsverkehr wirken. Als relevante Entscheidungskriterien konnten identifiziert werden: fahrzeugseitige Aspekte, Strukturen und Prozesse des adoptierenden Unternehmens, Einstellungen der Entscheider*innen, weiche Faktoren sowie regulative und räumliche Rahmenbedingungen. Der dritte Beitrag thematisiert die operative Eignung des E-Lastenrads, indem seine Fahrtzeiten einem Pkw gegenübergestellt werden. Bei Strecken bis zu 3 km sind beide Modi nahezu gleich schnell. Die Hälfte aller Fahrten bis 20 km Distanz würde bei einem Wechsel vom Pkw zum Lastenrad höchstens 2–10 min länger dauern (ohne Berücksichtigung der Parksuchzeit). Bereits kleine Änderungen an den Verkehrsbedingungen könnten noch bestehende Vorteile des Pkw spürbar verringern. Insgesamt erweitert die Arbeit maßgeblich das Wissen zu einem „neuen alten“ Fahrzeugkonzept, dem ein Potenzial zur Auflösung von bislang auf das Automobil hin ausgerichteten Systemen beigemessen wird. / Shifting trips to electric cargo bikes is one possible solution to deal with the growing challenges of urban commercial transport. This thesis combines conceptual, transport-related, and economic aspects as a foundation to assess the feasibility of this vehicle concept for freight and service trips. It contains five scientific papers, which provide three research contributions. The first contribution identifies the potentials of electric cargo bikes among first users (i.e., courier logistics services). Electric cargo bikes are an updated and re-envisioned version of freight bicycles. The features of point-to-point courier logistics assignments offer a substantial market opportunity for electric cargo bikes. However, being positioned between two established modes (i.e., car and bicycle) handicaps the market entry of cargo bikes. For the second contribution, the scope was widened to include all business sectors. A structured description is presented of the various determinants (i.e., drivers and barriers) affecting commercial cargo bike use. Among these were vehicle-specific factors, structures and practices of the company, attitudes of decision-makers, soft factors, regulatory frameworks, and spatial conditions. The third contribution explores the travel time differences between electric cargo bikes and cars for commercial trips. For trip distances of up to 3 kilometers, the travel times of both modes largely overlap. Half of all trips up to 20 kilometers would take only a maximum of 2 to 10 minutes longer by electric cargo bike (excluding the additional time for finding a parking spot). Small modifications in traffic could have considerable effects in reducing the current travel time advantages of cars. Consequently, this dissertation contributes towards the state-of-research by expanding the scientific knowledge of a type of vehicle that has the potential to disrupt car-dependent transportation systems.