Fig 4 - uploaded by Wilson Marcelo Román Vargas
Content may be subject to copyright.
Number of Ecuadorian traffic signs, divided into regulatory (red) and preventive (yellow), according to Fig. 3 notation. The name of the class is on the X axis, and the frequency of the signs is on the Y axis. (Color figure online)
Source publication
![Fig. 6. MR versus FPPI curve. System 1 is [7]'s proposal and System 2...](profile/Wilson-Roman-Vargas/publication/365739891/figure/fig4/AS:11431281123071968@1677603998584/MR-versus-FPPI-curve-System-1-is-7s-proposal-and-System-2-refers-to-the-current-work_Q320.jpg)
This research presents an application of the Deep Learning technology in the development of an automatic system detection of traffic signs of Ecuador. The development of this work has been divided into two parts, i) in first a database was built with regulatory and preventive traffic signs, taken in urban environments from several cities in Ecuador...
Context in source publication
Context 1
... labelled by hand; reaching a total of 37, 500 ROIs, divided into 52 classes, of which 28 correspond to regulatory ones, and the remaining ones are preventive. Many examples are shown in Fig. 3, where the regulatory signs are the ones with the biggest differences between countries. Additionally, the number of images per each class can be seen in Fig. 4, where the number of cases are evidently not homogenous. This is mainly because there are signs which appear with a higher frequency than others. For storage and labelling, we followed the format established in the famous GTSRB and GTSDB datasets ...
Similar publications
![Fire module [20]](publication/366762157/figure/fig3/AS:11431281233450571@1712056857468/Fire-module-20_Q320.jpg)
So far, slope collapse detection mainly depends on manpower, which has the following drawbacks: (1) low reliability, (2) high risk of human safe, (3) high labor cost. To improve the efficiency and reduce the human investment of slope collapse detection, this paper proposes an intelligent detection method based on deep learning technology for the ta...
