Inova Cidade 2015
This award was granted by Instituto Smart City Business, for the Gerenciamento de Trânsito Inteligente - GET-IN project. We received this trophy in a cerimony in Curitiba, on May 20th, 2015. We thank Fundação de Amparo à Pesquisa e Desenvolvimento - FAPESB, for funding the project and giving all the assistance we needed.
Description: Want to go from point A to point B and don't know if there is a congestion? Would you like to have the minimum time path between A and B? That's the idea of this project: not only to detect automatically the congestion degree of a road, but also spatial relationship between cross-roads in order to suggest better ways to go.
Best Paper at ICSP 2013
Our paper entitled Highway Traffic Congestion Classification Using Holistic Properties was awarded as the best paper in the 15th International Conference on Signal Processing (ICSP), on the track of Pattern Recognition and Applications, in 2013.
Abstract: This work proposes a holistic method for highway traffic video classification based on vehicle crowd properties. The method classifies the traffic congestion into three classes: light, medium and heavy. This is done by usage of average crowd density and crowd speed. Firstly, the crowd density is estimated by background subtraction and the crowd speed is performed by pyramidal Kanade-Lucas-Tomasi (KLT) tracker algorithm. The features classification with neural networks show 94.50% of accuracy on experimental results from 254 highway traffic videos of UCSD data set.
Keywords: Pattern Recognition, Object Recognition and Motion, Neural Network Applications.