Figures & data
Figure 2. Comparing the loading time between HTTP/1.1 and HTTP/2 (De Saxcé, Oprescu, and Chen Citation2015).
![Figure 2. Comparing the loading time between HTTP/1.1 and HTTP/2 (De Saxcé, Oprescu, and Chen Citation2015).](/cms/asset/c75c725d-5d92-4d67-b8e6-3396b1d99ffd/tsea_a_2014244_f0002_oc.jpg)
Figure 3. Vessel model with coordinate systems (base_link, navigation, base_scan) in ROS RVIZ, and Unity (NJORD Citation2021).
![Figure 3. Vessel model with coordinate systems (base_link, navigation, base_scan) in ROS RVIZ, and Unity (NJORD Citation2021).](/cms/asset/74618a32-3ae3-4773-bd83-94b34a27a25e/tsea_a_2014244_f0003_oc.jpg)
Figure 12. LabelImg program for labelling and labeled text file (representing class, x position, y position, width, height).
![Figure 12. LabelImg program for labelling and labeled text file (representing class, x position, y position, width, height).](/cms/asset/8d34647b-9286-4d52-9129-18522d1f3a33/tsea_a_2014244_f0012_oc.jpg)
Figure 13. YOLO v4 models – Training process (red line – mAP, blue line – Loss).
![Figure 13. YOLO v4 models – Training process (red line – mAP, blue line – Loss).](/cms/asset/9c765b29-a243-4977-8fd2-0ca8ef5ae1b2/tsea_a_2014244_f0013a_oc.jpg)
Figure 14. YOLO v4 – tiny models – Training process (red line – mAP, blue line – Loss).
![Figure 14. YOLO v4 – tiny models – Training process (red line – mAP, blue line – Loss).](/cms/asset/46782649-f208-4728-8ba0-5d26d3ee096d/tsea_a_2014244_f0014_oc.jpg)
Table 1. Performances of YOLOv4 by Hyperparameter
Table 2. Performances of YOLOv4-tiny by Hyperparameter