This dataset is composed of two video sequences recorded at the intersection of Guemes and Salguero street in Buenos Aires.
They were employed to test people detection and tracking algorithms.
They are called GS06 and GS54 datasets.
This is the implementation of the Movement Feature Space (MFS) used to estimate the number of vehicles present in a video sequence.
The MATLAB implementation follows the guidelines of my papers: "Pedestrian Detection Using a Feature Space Based on Colored Level Lines" (CIARP2012) or "Estimating the queue length at intersections using a movement feature space approach" (IET Image Processing Journal).
This is a real adaboost vehicle detector MATLAB implementation that follows the guidelines of my research paper: "A Cascade of Boosted Generative and Discriminative Classifiers for Vehicle Detection", EURASIP JASP, 2008.
This is my own MATLAB implementation of the John Platt's pseudo code from his "Sequential Minimal Optimization: A Fast Algorithm
for Training Support Vector Machine" article, used for a character recognition system.
It is also shared the datasets of the Multi-Style License Plate OCR, proposed in the CIARP 2011 paper: ''A Multi-style License Plate Recognition System Based on Tree of Shapes for Character Segmentation''.
