Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Overall network architecture of FCMI-YOLO.

More »

Fig 1 Expand

Fig 2.

The structure of FasterNext.

(a) FasterNet. (b) S-FasterNet. (c) FasterNext.

More »

Fig 2 Expand

Fig 3.

The principle of Partial Convolution.

More »

Fig 3 Expand

Fig 4.

Comparison curve of ReLU and SiLU activation functions.

More »

Fig 4 Expand

Table 1.

Parameters of the FasterNext and C3.

More »

Table 1 Expand

Fig 5.

The principle of MLCA mechanism.

More »

Fig 5 Expand

Fig 6.

The structure of MLCA mechanism.

More »

Fig 6 Expand

Fig 7.

Schematic diagram of Inner-IoU.

More »

Fig 7 Expand

Fig 8.

Distribution of the dataset.

More »

Fig 8 Expand

Table 2.

Parameters of the dataset.

More »

Table 2 Expand

Table 3.

Model train environment.

More »

Table 3 Expand

Table 4.

Primary training parameters for the model.

More »

Table 4 Expand

Table 5.

Performance of fire detector based on different model versions of YOLOv5.

More »

Table 5 Expand

Table 6.

Performance comparison of YOLOv5s with FasterNext module replacement.

More »

Table 6 Expand

Fig 9.

Comparison of detection results of different methods in FasterNext.

(a) YOLOv5s. (b) YOLOv5s + FasterNext (Backbone). (c) YOLOv5s + FasterNext(Neck). (d) YOLOv5s + FasterNext(Backbone + Neck).

More »

Fig 9 Expand

Fig 10.

Comparison of mAP@0.5 for different ratios.

More »

Fig 10 Expand

Table 7.

Performance comparison of different loss functions.

More »

Table 7 Expand

Table 8.

Ablation experiments results of YOLOv5s.

More »

Table 8 Expand

Fig 11.

Detection results of YOLOv5s and FCMI-YOLO under different exposure levels.

(a) Fire in the close interior. (b) Remote outdoor fire. (c) Fire in the Night.

More »

Fig 11 Expand

Fig 12.

Comparison of mAP@0.5 and Recall for mainstream algorithms.

More »

Fig 12 Expand

Table 9.

Performance comparison of mainstream algorithms.

More »

Table 9 Expand

Fig 13.

Detection results of FCMI-YOLO, YOLOv6s, YOLOv9s, and YOLOv11s.

More »

Fig 13 Expand

Fig 14.

System diagram.

More »

Fig 14 Expand

Table 10.

NPU utilization and FPS Under different processing methods.

More »

Table 10 Expand

Fig 15.

mAP performance of FCMI-YOLO on the Orange Pi 5 Plus.

More »

Fig 15 Expand

Fig 16.

Detection results of FCMI-YOLO and YOLOv5s at 30m and 75m on the OrangePi 5 Plus.

More »

Fig 16 Expand