| Title |
A Smart Algorithm for Traffic Lights Intersections Control in Developing Countries |
| ID_Doc |
44574 |
| Authors |
Olaya-Quiñones, JD; Perafan-Villota, JC |
| Title |
A Smart Algorithm for Traffic Lights Intersections Control in Developing Countries |
| Year |
2022 |
| Published |
|
| DOI |
10.1007/978-3-030-91308-3_7 |
| Abstract |
Traffic jam is a problem that directly affects the quality of life of the population in large cities. This problem exacerbates at road intersections, where obsolete traffic control systems based on a static set of rules remain in use. We propose an algorithm that improves the vehicular flow at traffic-light intersections by optimizing a dynamic allocation of times. We train our own YOLO detector using a set of images captured from traffic cameras installed at a cross-road. Furthermore, we added an attention module to our detector which outperforms the original YOLO V3 by a mAP value of 2%. We used a fuzzy control to time allocation on intersections controlled by traffic lights. The number of vehicles detected in each intersection road allowed the creation of fuzzy rules. Since, at the local level, there are few traffic cameras installed on intersections, we build a simulated environment both to train our detector system and verify the efficiency of our algorithm. |
| Author Keywords |
Smart city; Traffic jam; Deep learning; Fuzzy logic; YOLO; Unit3D |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Conference Proceedings Citation Index - Science (CPCI-S) |
| EID |
WOS:000851233900007 |
| WoS Category |
Computer Science, Artificial Intelligence; Computer Science, Interdisciplinary Applications |
| Research Area |
Computer Science |
| PDF |
|