Fires and other related disasters provoke great destruction of high valuable environments and eco... more Fires and other related disasters provoke great destruction of high valuable environments and economical losses, especially when they are located in urban areas. In this work, we present a combined urban and forest fire spreading algorithm to be used in real time and interactive virtual simulations. The algorithm is pedagogical oriented and its purpose is not focused in achieving precise results that could be used to predict the fire evolution. The main objective is to obtain a fast, interactive and quasi-realistic virtual simulation to be used in the simulation of virtual scenarios where firefighters and controllers will be trained. The algorithm supports the main variables involved in the fire spreading (slope and wind) and the radiation effect. An additional method has been added to extinguish the fire.
On-demand public transport satisfies many of the needs that traditional public transport, with fi... more On-demand public transport satisfies many of the needs that traditional public transport, with fixed predetermined routes and schedules, cannot fulfill. Both schemas are able to work together, as it is discussed in this paper, being on-demand services a good alternative in the areas and time intervals where low demand makes fixed routes unsustainable. This work presents a new integrated real-time management system for road public transport services, focusing on the integration of three kinds of services: fixed services, on-demand fixed services and on-demand dynamic services. The architecture of the system and the features of the tailored algorithm for dynamic services are detailed in the paper. The main objective of the algorithm is to solve the multi-vehicle Dial-a-Ride Problem (DARP) minimizing the number of vehicles and the total distance of the routes. A heterogeneous capacitated fleet is used to serve the customers and the cost matrix is asymmetric, as real-life conditions are assumed. The desired quality of service is set by configurable parameters (e.g., waiting time window and maximum ride time). The algorithm is designed to work with two operating modes (insertion and optimization), concluding that a fast response can be achieved with the insertion mode, improving the results with the optimization mode.
IEEE Transactions on Intelligent Transportation Systems, 2012
In this paper we present a robust vision-based system for vehicle tracking and classification dev... more In this paper we present a robust vision-based system for vehicle tracking and classification devised for traffic flow surveillance. The system performs in real time achieving good results even in challenging situations, such as with moving casted shadows on sunny days, headlight reflections on the road, rainy days and traffic jams, using only a single standard camera. We propose a robust adaptive multi-cue segmentation strategy that detects foreground pixels corresponding to moving and stopped vehicles, even with noisy images due to compression. First, the approach adaptively thresholds a combination of luminance and chromaticity disparity maps between the learned background and the current frame. It then adds extra features derived from gradient differences, in order to improve the segmentation of dark vehicles with casted shadows, and removes headlights reflections on the road. The segmentation is further used by a two-step tracking approach, which combines the simplicity of a linear 2D Kalman filter, and the complexity of a 3D volume estimation using Markov Chain Monte Carlo (MCMC) methods. Experimental results show that our method can count and classify vehicles in real time with a high level of performance under different environmental situations, comparable to those of inductive loop detectors (ILD).
Fires and other related disasters provoke great destruction of high valuable environments and eco... more Fires and other related disasters provoke great destruction of high valuable environments and economical losses, especially when they are located in urban areas. In this work, we present a combined urban and forest fire spreading algorithm to be used in real time and interactive virtual simulations. The algorithm is pedagogical oriented and its purpose is not focused in achieving precise results that could be used to predict the fire evolution. The main objective is to obtain a fast, interactive and quasi-realistic virtual simulation to be used in the simulation of virtual scenarios where firefighters and controllers will be trained. The algorithm supports the main variables involved in the fire spreading (slope and wind) and the radiation effect. An additional method has been added to extinguish the fire.
On-demand public transport satisfies many of the needs that traditional public transport, with fi... more On-demand public transport satisfies many of the needs that traditional public transport, with fixed predetermined routes and schedules, cannot fulfill. Both schemas are able to work together, as it is discussed in this paper, being on-demand services a good alternative in the areas and time intervals where low demand makes fixed routes unsustainable. This work presents a new integrated real-time management system for road public transport services, focusing on the integration of three kinds of services: fixed services, on-demand fixed services and on-demand dynamic services. The architecture of the system and the features of the tailored algorithm for dynamic services are detailed in the paper. The main objective of the algorithm is to solve the multi-vehicle Dial-a-Ride Problem (DARP) minimizing the number of vehicles and the total distance of the routes. A heterogeneous capacitated fleet is used to serve the customers and the cost matrix is asymmetric, as real-life conditions are assumed. The desired quality of service is set by configurable parameters (e.g., waiting time window and maximum ride time). The algorithm is designed to work with two operating modes (insertion and optimization), concluding that a fast response can be achieved with the insertion mode, improving the results with the optimization mode.
IEEE Transactions on Intelligent Transportation Systems, 2012
In this paper we present a robust vision-based system for vehicle tracking and classification dev... more In this paper we present a robust vision-based system for vehicle tracking and classification devised for traffic flow surveillance. The system performs in real time achieving good results even in challenging situations, such as with moving casted shadows on sunny days, headlight reflections on the road, rainy days and traffic jams, using only a single standard camera. We propose a robust adaptive multi-cue segmentation strategy that detects foreground pixels corresponding to moving and stopped vehicles, even with noisy images due to compression. First, the approach adaptively thresholds a combination of luminance and chromaticity disparity maps between the learned background and the current frame. It then adds extra features derived from gradient differences, in order to improve the segmentation of dark vehicles with casted shadows, and removes headlights reflections on the road. The segmentation is further used by a two-step tracking approach, which combines the simplicity of a linear 2D Kalman filter, and the complexity of a 3D volume estimation using Markov Chain Monte Carlo (MCMC) methods. Experimental results show that our method can count and classify vehicles in real time with a high level of performance under different environmental situations, comparable to those of inductive loop detectors (ILD).
Uploads
Papers by Oihana Otaegui