Learn More
—We consider geoinformation inventory systems containing locations and types of traffic signs and road surface markings in a given geographical region. Such systems allow a human operator to assess the current state of the traffic infrastructure by comparing a recent georeferenced video with the prescribed state stored in the inventory. We are concerned(More)
This paper addresses detection, tracking and recognition of traffic signs in video. Previous research has shown that very good detection recalls can be obtained by state-of-the-art detection algorithms. Unfortunately, satisfactory precision and localization accuracy are more difficultly achieved. We follow the intuitive notion that it should be easier to(More)
—This paper reviews the popular traffic sign detection methods prevalent in recent literature. The methods are divided into three categories: color-based, shape-based, and learning-based. Color-based detection methods from eleven different works are studied and summarized in a table for easy reference. Three shape-based detection methods are presented, and(More)
We study the problem of traffic sign detection in the context of traffic infrastructure inventory. The data acquired during filming the roads in Croatia is presented. Based on recent approaches, and motivated by constraints present in our data, we employ the Viola-Jones object detector for triangular warning signs detection. The detector achieves correct(More)
Geoinformation inventories are often employed as a tool for providing a comprehensive view onto the required state of traffic control infrastructure. They are especially important in road safety inspection where, in combination with georeferenced video, they enable repeatable off-line and off-site assessments as an attractive aternative to classic onsite(More)
This expert paper describes the characteristics of six most used free software tools for general data mining that are available today: RapidMiner, R, Weka, KNIME, Orange, and scikit-learn. The goal is to provide the interested researcher with all the important pros and cons regarding the use of a particular tool. A comparison of the implemented algorithms(More)
Feature selection (FS) methods can be used in data pre-processing to achieve efficient data reduction. This is useful for finding accurate data models. Since exhaustive search for optimal feature subset is infeasible in most cases, many search strategies have been proposed in literature. The usual applications of FS are in classification, clustering, and(More)
—We describe a system that employs a single calibrated camera mounted on a moving vehicle to produce a road appearance map as a comprehensive mosaic of individual orthogonal views. The system first transforms the current image of the road acquired from a driver's perspective into the orthogonal view by inverse perspective mapping. Consequently, the(More)
We introduce a novel local spatio-temporal descriptor intended to model the spatio-temporal behavior of a tracked object of interest in a general manner. The basic idea of the descriptor is the accumulation of histograms of an image function value through time. The histograms are calculated over a regular grid of patches inside the bounding box of the(More)
There are numerous classification methods developed in the field of machine learning. Some of these methods, such as artificial neural networks and support vector machines, are used extensively in biomedical time-series classification. Other methods have been used less often for no apparent reason. The aim of this work is to examine the applicability of(More)