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.

Framework of LightweightSRNet.

More »

Fig 1 Expand

Fig 2.

Overall architecture of the improved YOLOv8 network.

More »

Fig 2 Expand

Fig 3.

Structure of the HG-MHA.

More »

Fig 3 Expand

Fig 4.

Comparison of SC-BiFPN with other fusion methods.

More »

Fig 4 Expand

Fig 5.

Schematic Diagram of the Ghost Bottleneck Structure.

More »

Fig 5 Expand

Fig 6.

Structural Workflow of the C2f-Ghost-Sobel Module.

More »

Fig 6 Expand

Fig 7.

Target Distribution in the HIT-UAV Dataset.

More »

Fig 7 Expand

Fig 8.

Comparison of Images Before and After Super-Resolution Reconstruction.

(a) Before Reconstruction; (b) After Reconstruction; (c) GT.

More »

Fig 8 Expand

Table 1.

Comparison of detection performance using different RS methods.

More »

Table 1 Expand

Table 2.

Comparison of different attention mechanisms in infrared object detection.

More »

Table 2 Expand

Table 3.

Results of ablation experiments.

More »

Table 3 Expand

Fig 9.

Comparison of Training Results.

More »

Fig 9 Expand

Fig 10.

Attention Distribution Visualization.

(a) Without Attention Mechanism; (b) Original Infrared Image and Targets; (c) With Attention Mechanism.

More »

Fig 10 Expand

Table 4.

mAP (%) of each dataset under different object detection algorithms.

More »

Table 4 Expand

Fig 11.

Detection results on the HIT-UAV dataset using different algorithms.

From (a) to (g), the results correspond to Faster R-CNN, SSD, YOLOv5s, YOLOv7, YOLO-IR-Free, YOLO-DeepOC-IR, and ours, respectively.

More »

Fig 11 Expand

Fig 12.

Detection results on the FLIR dataset using different algorithms.

From (a) to (g), the results correspond to Faster R-CNN, SSD, YOLOv5s, YOLOv7, YOLO-IR-Free, YOLO-DeepOC-IR, and ours, respectively.

More »

Fig 12 Expand