Search

Traffic lights are crucial for urban traffic management, as they significantly impact congestion reduction and travel safety. Traditional methods relying on hand-crafted rules and operator experience are limited in their ability to adapt to changing traffic environments. To address this challenge, we have been exploring intelligent traffic light control using deep reinforcement learning techniques. However, current approaches often suffer from inadequate training data and unstable training processes, leading to suboptimal performance and real-world consequences. In this study, we propose RELight, a novel random ensemble reinforcement learning-based traffic light control framework. RELight effectively utilizes collected empirical data, ensuring a stable and efficient training process. To evaluate the performance of our proposed framework, we conducted a comprehensive set of experiments on a variety of datasets, including four synthetic datasets and a real traffic dataset collected from surveillance cameras at an intersection in Hangzhou, China. The results show that RELight outperforms existing approaches, demonstrating its superiority and potential for practical traffic light control applications. [ABSTRACT FROM AUTHOR]

Smart cities can effectively improve urban life quality. But, with the rise in population size, there is an increase in the use of vehicles for transportation. In smart city development, traffic control and route planning are the primary tasks to address the problem of travel time estimation. It has become complex due to concerns of wrapped spatio-temporal data on dynamic real-time traffic conditions. The existing methods failed to estimate travel time efficiently due to not considering the spatio-temporal features and lack of computing resources. There is a need for a system like intelligent transportation system to monitor and accurately predict traffic flow to avoid traffic congestion and reduce the impact on the ecological system. This paper developed a novel hybrid deep learning model to estimate optimized travel time and possible trajectories. In this work, U-Net used to reduce the number of feature points for each temporal data and GNN is used to build the graph with connectivity between vehicular nodes. This hybrid model helps us predict traffic flow and aims to estimate accurate travel time from one location (node) to another. The model's performance is evaluated on the standard benchmark datasets Q-Traffic, TaxiBJ, and Chengdu. The experimental results show that the proposed framework significantly improves performance in extracting travel patterns and provides an optimal route with an estimated travel time than existing methods with RMSE 4%, MAE 20.49%, and MAPE 18%. The proposed model has accurately predicted the estimation of travel time of the vehicle for the given urban traffic data. [ABSTRACT FROM AUTHOR]

The technology that can recognize the license plates of vehicles in real time and manage them automatically is a key element of building an intelligent transportation system. License plate recognition is the most important technique in vehicle image processing used to identify a vehicle. Object recognition using a camera is greatly influenced by environmental factors in which the camera is installed. When the vehicle image is acquired, the image is distorted due to the tilting of the license plate, reflection of light, lighting effects, rainy weather, and nighttime, so that it is difficult to accurately recognize the license plate. In addition, when the geometric distortion of the license plate image or the degradation of the image quality is intensified, it may be more difficult to automatically recognize the license plate image. Therefore, in this paper, we propose a deep learning–based vehicles' license plate recognition method to detect license plate and recognize characters accurately in complex and diverse environments. As a deep learning model, the YOLO model can be used to detect robust license plates in a variety of environments and to recognize characters quickly and accurately. It can also be seen that the license plate accurately recognizes the license plate with geometric distortion. [ABSTRACT FROM AUTHOR]

With the enormous growth in the public and private vehicles fleet, traffic congestion is increasing at a very high rate. To deal with this, an intelligent mechanism is required.Therefore, this work proposes a novel Neuro-fuzzy based intelligent traffic light control system, which accounts for vehicle heterogeneity by dynamically generating traffic light phase duration considering the real-time heterogeneous traffic load. For this purpose, the proposed model establishes peer-to-peer connections among neighboring traffic light junctions to fetch the respective real-time traffic conditions and congestion. A fuzzy membership function is utilized to generate an intelligent traffic light phase duration. Further, to obtain an effective fuzzy membership function input value considering real-time heterogeneous traffic scenarios, an adaptive neural network is utilized. The proposed system adopts three execution modes: Congestion Mode (CM), Priority Mode (PM), and Fair Mode (FM). It automatically activates and switches to the best mode based on the live traffic conditions. The performance of the proposed model is evaluated via a realistic simulation on the Gwalior city map of India using an open-source simulator known as Simulation of Urban Mobility (SUMO). The results evident the effectiveness of the proposed model over the existing state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Crowd flow prediction is one of the most remarkable issues in a wide range of areas, from traffic control to public safety, and aims to forecast the inflow and outflow of crowds in each region of a city. Most existing studies adopt CNN and its variants to discover the spatial patterns of grid maps (each grid represents a region) while ignoring the correlation between distant regions that may share similar temporal patterns. In this paper, we propose a gnn-based prediction method, called STGs, for crowd flow prediction, which jointly constructs spatial and temporal graphs from grid maps and then implements graph neural networks to directly capture the relationship between regions. Additionally, we introduce a gated fusion mechanism to combine spatial and temporal embedding from the corresponding graph, which further improves the performance of our STGs. We conduct numerical experiments to compare STGs with other baseline models using two real-world datasets, BikeNYC and TLC. Experimental results demonstrate the superiority of our STGs model; specifically, our model reduces the mean absolute error (MAE) of crowd flow prediction by approximately 7-8% compared to state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

As vehicular networking has recently been developed and commercialized, vehicular cloud computing has received much attention in various research areas, such as intelligent transportation systems and vehicular ad hoc networks. An efficient intersection traffic control using vehicular cloud computing is one of the key research topics in intelligent transportation systems. To efficiently deal with intersection traffic control via vehicle-to-vehicle communications, we design a distributed mutual exclusion algorithm that does not rely on broadcast, which introduces communication overheads; instead, our algorithm use point-to-point messages sent between the vehicles to keep network traffic load lower. In our algorithmic design, to pass an intersection, the lead vehicle on a lane must get permissions from a subset of other vehicles and its following vehicles on the same lane can follow the lead vehicle without permissions unlike the previous research. To evaluate the performance of our distributed mutual exclusion algorithm, we conduct extensive experiments. The results show that our algorithmic design is both effective and efficient. [ABSTRACT FROM AUTHOR]

Today's high-end vehicles are technologically more sophisticated and smarter than the 'old machines with engine and wheels'. These vehicles are anticipated to provide consumers with safe, reliable, and infotainment-rich driving experience through intelligent transportation system, realized through a technology referred to as vehicular ad hoc network (VANET). VANET offers a plethora of applications to the consumers ranging from safety to infotainment. Among other messages defined by the dedicated short range communication standard, cooperative awareness messages (CAMs) are of paramount importance for the VANET applications. In VANET, vehicles share their frequent mobility information in the form of CAMs with neighbors for cooperative awareness, traffic view construction, maneuver, and cruise control. In this work we target the CAM-based traffic information dissemination. VANET applications construct short-range local and long-range extend traffic views with the information contained in scheduled CAMs (also known as beacons). To construct aforementioned traffic views, naïve approach is multi-hop communication; however, historically multi-hop communication does not scale efficiently in dynamic VANET due to computational and communication overhead. Therefore another alternative approach is essential to address the problems of the multi-hop communication in highly ephemeral VANET and to achieve maximum degree of the information dissemination in VANET. To fill the gap, in this paper we propose a geocast-based abstract piggybacking mechanism for traffic information dissemination in VANET through single-hop CAMs. In the proposed scheme, vehicles compress their local traffic view constructed through single-hop CAMs. The compressed local traffic view is referred to as traffic data unit (TDU). Every vehicle broadcasts its own TDU along with a number of TDUs received from other vehicles in the next scheduled CAM, in order to construct a long-range extended traffic view, also known as compressed data word (CDW). In other words, CDW is encapsulated into normal CAM in order to share it with the neighbors in the vicinity. The receivers of CDW use the received TDUs to construct the desired length of the long-range extended traffic view. The proposed scheme leverages only single-hop beacons data to construct both local and extended traffic views. Our simulation results show that the extended traffic view up to 1 km can be constructed with only single-hop beacons at the expense of 10 % of extra information with the regular CAM. The results also show that the effect of the extra overhead is not phenomenal from overhead standpoint. The proposed virtual multi-hop communication paradigm with single-hop CAM will reduce the overall communication thereby saving the bandwidth for other important safety related communications. [ABSTRACT FROM AUTHOR]