In urban cities, visual information on and along roadways is likely to distract drivers and lead to missing traffic signs and other accident-prone (AP) features. To avoid accidents due to missing these visual cues, this paper proposes a visual notification of AP-features to drivers based on real-time images obtained via dashcam. For this purpose, Google Street View images around accident hotspots (areas of dense accident occurrence) identified by a real-accident dataset are used to train a novel attention module to classify a given urban scene into an accident hotspot or a non-hotspot (area of sparse accident occurrence). The proposed module leverages channel, point, and spatial-wise attention learning on top of different CNN backbones. This leads to better classification results and more certain AP-features with better contextual knowledge when compared with CNN backbones alone. Our proposed module achieves up to 92% classification accuracy. The capability of detecting AP-features by the proposed model were analyzed by a comparative study of three different class activation map (CAM) methods, which are used to inspect specific AP-features causing the classification decision. The outputs of the CAM methods were processed by an image processing pipeline to extract only the AP-features that are explainable to drivers and notified using a visual notification system. Range of experiments was performed to prove the efficacy and AP-features of the system. Ablation of the AP-features taking 9.61%, on average, of the total area in each image sample increased the chance of a given area to be classified as a non-hotspot by up to 21.8%.

Advancement of mobile technologies has enabled economical collection, storage, processing, and sharing of traffic data. These data are made accessible to intended users through various application program interfaces (API) and can be used to recognize and mitigate congestion in real time. In this paper, quantitative (time of arrival) and qualitative (color-coded congestion levels) data were acquired from the Google traffic APIs. New parameters that reflect heterogeneous traffic conditions were defined and utilized for real-time control of traffic signals while maintaining the green-to-red time ratio. The proposed method utilizes a congestion-avoiding principle commonly used in computer networking. Adaptive congestion levels were observed on three different intersections of Delhi (India), in peak hours. It showed good variation, hence sensitive for the control algorithm to act efficiently. Also, simulation study establishes that proposed control algorithm decreases waiting time and congestion. The proposed method provides an economical alternative to expensive sensing and tracking technologies.

Traffic jams can be avoided by controlling traffic signals according to quickly building congestion with steep gradients on short temporal and small spatial scales. With the rising standards of computational technology, single-board computers, software packages, platforms, and APIs (Application Program Interfaces), it has become relatively easy for developers to create systems for controlling signals and informative systems. Hence, for enhancing the power of Intelligent Transport Systems in automotive telematics, in this study, we used crowdsourced traffic congestion data from Google to adjust traffic light cycle times with a system that is adaptable to congestion. One aim of the system proposed here is to inform drivers about the status of the upcoming traffic light on their route. Since crowdsourced data are used, the system does not entail the high infrastructure cost associated with sensing networks. A full system module-level analysis is presented for implementation. The system proposed is fail-safe against temporal communication failure. Along with a case study for examining congestion levels, generic information processing for the cycle time decision and status delivery system was tested and confirmed to be viable and quick for a restricted prototype model. The information required was delivered correctly over sustained trials, with an average time delay of 1.5 s and a maximum of 3 s.

Short distance travel and commute being inevitable, safe route planning in pandemics for micro-mobility, i.e., cycling and walking, is extremely important for the safety of oneself and others. Hence, we propose an application-based solution using COVID-19 occurrence data and a multi-criteria route planning technique for cyclists and pedestrians. This study aims at objectively determining the routes based on various criteria on COVID-19 safety of a given route while keeping the user away from potential COVID-19 transmission spots. The vulnerable spots include places such as a hospital or medical zones, contained residential areas, and roads with a high connectivity and influx of people. The proposed algorithm returns a multi-criteria route modeled on COVID-19-modified parameters of micro-mobility and betweenness centrality considering COVID-19 avoidance as well as the shortest available safe route for user ease and shortened time of outside environment exposure. We verified our routing algorithm in a part of Delhi, India, by visualizing containment zones and medical establishments. The results with COVID-19 data analysis and route planning suggest a safer route in the context of the coronavirus outbreak as compared to normal navigation and on average route extension is within 8%–12%. Moreover, for further advancement and post-COVID-19 era, we discuss the need for adding open data policy and the spatial system architecture for data usage, as a part of a pandemic strategy. The study contributes new micro-mobility parameters adapted for COVID-19 and policy guidelines based on aggregated contact tracing data analysis maintaining privacy, security, and anonymity.

Accurate traffic state estimation, vital for managing urban congestion, is often achieved through simulation. Real-time data is invaluable for this, yet obtaining multi-sensor data is challenging and costly. To bridge this gap, leveraging crowdsourced data from third-party sources, despite its anonymity, enriches available information for precise estimation. This passive crowdsourced data is often reported as estimated time of arrival (ETA) and color-coded traffic patterns. The paper introduces an effective calibration approach for a mesoscopic traffic simulation of a complex urban arterial network, primarily relying on crowdsourced data and incorporating sensor data, if accessible. The approach employs a nested genetic algorithm with average speed data, calculated using ETA to estimate vehicle counts, eliminating the need for time-consuming field surveys. A custom mutation operator-speed deviation adaptive gene mutator, is introduced for generating vehicle counts to replicate real-world traffic conditions in the intermediate time steps of simulation. Additionally, a route selection algorithm is developed using color-coded tracks from Google Maps for prioritizing routes based on congestion patterns. The study demonstrates a novel data-fusion technique, combining sensors with passive crowdsourced information for accurate traffic speed estimation. The proposed methodology was applied to two case studies of urban arterial networks. The values obtained from simulations during validation showed promising proximity to real values, yielding a mean absolute percentage error (MAPE) of 0.29% for a simpler network and 6.31% for the best 10 routes, and 10.33% for all of the 15 priority routes within a complex network.