Growing concerns with environmental issues have resulted in alternatives for urban mobility and public transportation. Among the available options, battery-powered electric buses have been considered in terms of flexibility, sustainability, and emission of pollutants. These buses have a plug-in recharge system that allows them to run without any extra power supply. However, battery recharging during operation is necessary, and the number and location of charging stations are important issues for system operation. This paper presents a discrete event simulation that evaluates bus energy consumption using a mathematical model that takes into account different load and friction forces. An optimization strategy that utilizes a bi-objective genetic algorithm is then associated with simulation (in a simulation optimization approach) to minimize both the number of charging stations and the average extra time stopped in the station to recharge. Information, including passenger demand, bus speed, distances, and route elevation profiles, has been obtained for Curitiba public transportation. The parameters of buses' mobility are based on real data acquired, filtered, and analyzed for six express routes from raw data provided by the agency that controls public transportation and urban development. Fast battery recharge with typical parameters is considered at charging stations. The results show different arrangements for the number of stations, their location, and delays in bus schedule, as well as the corresponding bus energy levels in different routes.
1 January 2018 in Transportation Research Part D: Transport and Environment
This work addresses the problem of vehicle identification through non-overlapping cameras. As our main contribution, we introduce a novel dataset for vehicle identification, called Vehicle-Rear, that contains more than three hours of high-resolution videos, with accurate information about the make, model, color and year of nearly 3,000 vehicles, in addition to the position and identification of their license plates. To explore our dataset we design a two-stream Convolutional Neural Network (CNN) that simultaneously uses two of the most distinctive and persistent features available: the vehicle’s appearance and its license plate. This is an attempt to tackle a major problem: false alarms caused by vehicles with similar designs or by very close license plate identifiers. In the first network stream, shape similarities are identified by a Siamese CNN that uses a pair of low-resolution vehicle patches recorded by two different cameras. In the second stream, we use a CNN for Optical Character Recognition (OCR) to extract textual information, confidence scores, and string similarities from a pair of high-resolution license plate patches. Then, features from both streams are merged by a sequence of fully connected layers for decision. In our experiments, we compared the two-stream network against several well-known CNN architectures using single or multiple vehicle features. The architectures, trained models, and dataset are publicly available at https://github.com/icarofua/vehicle-rear .
1 January 2016 in Mathematical Problems in Engineering
The city of Curitiba, located at Southern Brazil, is recognized by its urban planning structured on three pillars: land use, collective transportation, and traffic. With 3.8 million people in its metropolitan area, the public transport system deals with approximately 2.5 million passengers daily. The structure and properties of such a transportation system have substantial implications for the urban planning and public politics for sustainable development of Curitiba. Therefore, this paper analyzes the structure of the public transportation system of Curitiba through the theory of complex networks in a static approach of network topology and presents a comparative analysis of the results from Curitiba, three cities from China (Shanghai, Beijing, and Guangzhou), and three cities from Poland (GOP, Warszawa, and Łódź). The transportation network was modeled as a complex network with exact geographical coordinates of its bus stops. In all bus lines, the method used was the P-Space. The results show that this bus network has characteristics of both small-world and scale-free networks.
We describe in this paper a Two-Stream Siamese Neural Network for vehicle re-identification. The proposed network is fed simultaneously with small coarse patches of the vehicle shape’s, with 96 × 96 pixels, in one stream, and fine features extracted from license plate patches, easily readable by humans, with 96 × 48 pixels, in the other one. Then, we combined the strengths of both streams by merging the Siamese distance descriptors with a sequence of fully connected layers, as an attempt to tackle a major problem in the field, false alarms caused by a huge number of car design and models with nearly the same appearance or by similar license plate strings. In our experiments, with 2 hours of videos containing 2982 vehicles, extracted from two low-cost cameras in the same roadway, 546 ft away, we achieved a F-measure and accuracy of 92.6% and 98.7%, respectively. We show that our network, available at https://github.com/icarofua/siamese-two-stream, outperforms other One-Stream architectures, even if they use higher resolution image features.
This study analyses the influence of passenger load, driving cycle, fuel price and four different types of buses on the cost of transport service for one bus rapid transit (BRT) route in Curitiba, Brazil. First, the energy use is estimated for different passenger loads and driving cycles for a conventional bi-articulated bus (ConvBi), a hybrid-electric two-axle bus (HybTw), a hybrid-electric articulated bus (HybAr) and a plug-in hybrid-electric two-axle bus (PlugTw). Then, the fuel cost and uncertainty are estimated considering the fuel price trends in the past. Based on this and additional cost data, replacement scenarios for the currently operated ConvBi fleet are determined using a techno-economic optimisation model. The lowest fuel cost ranges for the passenger load are estimated for PlugTw amounting to (0.198–0.289) USD/km, followed by (0.255–0.315) USD/km for HybTw, (0.298–0.375) USD/km for HybAr and (0.552–0.809) USD/km for ConvBi. In contrast, the coefficient of variation (\(C_{v}\)) of the combined standard uncertainty is the highest for PlugTw (\(C_{v}\): 15–17%) due to stronger sensitivity to varying bus driver behaviour, whereas it is the least for ConvBi (\(C_{v}\): 8%). The scenario analysis shows that a complete replacement of the ConvBi fleet leads to considerable higher cost of transport service on the BRT route, amounting to an increase by 64% to 139%, depending on the bus fleet composition. Meanwhile, the service quality is improved resulting in 42% up to 64% less waiting time for passengers at a bus stop.