Smart real-time detection of risky roads using vehicles trajectories for intelligent transportation

Indeed, risky roads have a negative impact on traffic by causing road injuries with fatalities, which can lead to negative emotional, social, and economic influences on humans, countries, and the world. Additionally, taxi and rideshare passengers prefer to move on familiar and safe roads. Therefore, to ensure the high quality of transportation services, it is required to follow secure roads to avoid poorly maintained roads, areas with high incidences of car accidents, neighborhoods with high crime rates, and places with a history of terrorist attacks or civil unrest. In this regard, discovering risky roads is a need. This paper introduces a real-time framework, named RiskyMove , that helps drivers and passengers to follow safe roads and avoid risky once that are not safe for travel. Mainly, the RiskyMove framework employs a probabilistic method based on a Minimum Adaptive Viterbi (MAV) algorithm to identify risky paths during the trip and alarm the drivers to take precautions. An experimental evaluation of the RiskyMove with a real dataset of the movement of cabs in San Francisco illustrates the effectiveness of the proposed framework. • Novel Framework for Risk Detection : . Introduces RiskyMove , a real-time framework for detecting risky roads based on vehicle trajectories. . Enhances transportation safety by avoiding accident-prone or unsafe routes. • Advanced Algorithm for Path Analysis : . Implements a Minimum Adaptive Viterbi (MAV) algorithm to identify rarely used risky paths. . Performs trajectory similarity checks to alert drivers in real-time. • Real-World Data Validation : . Evaluated using over 10 million entries from the San Francisco taxi GPS dataset. . Achieves 88% accuracy in detecting risky paths, proving its practical effectiveness. • Scalability and Performance : . The system remains scalable with minimal latency, even as the number of trajectories increases. . Longer trips and reduced thresholds increase computational load, providing insights for optimization. • Potential for Future Enhancements : . Highlights integration opportunities with external risk factors such as weather, accident data, and crime statistics. . A foundation for future intelligent transportation systems focusing on real-time risk detection.