Research Article
Proposing Lane and Obstacle Detection Algorithm Using YOLO to Control Self-Driving Cars on Advanced Networks
Table 2
The parameters of the simulation system.
| No. | Parameter | Values |
| 1 | Road type | Limited access highway, mountain road, and urban road | 2 | Vehicle | Mixed traffic (car, pedestrian, traffic lights, etc.) | 3 | Weather conditions | Dry, clear, rain, and cloud | 4 | Camera | Camera HD-RGB, resolution 1280 720, and JPEG format | 5 | Roadway surface conditions | Dry, wet, and undamaged | 6 | Average speed | 1.335 seconds | 7 | Processor | Intel Core i5-9300H CPU 2.4 GHz | 8 | The maximum length of detected lane | 32 meters | 9 | YOLOv4 | Input: 416 416; and output: 80 classes | 10 | Software | Windows 10 64 bits, Python 3.7 bits, and OpenCV 4.1.0 | 11 | TuSimple dataset | 3626 training and 2782 testing videos | 12 | Lane width | 0 4 meters |
|
|