Infrared Weak and Small Target Detection Algorithm Based on Deep Learning
und
30. Sept. 2024
Über diesen Artikel
Online veröffentlicht: 30. Sept. 2024
Seitenbereich: 47 - 55
DOI: https://doi.org/10.2478/ijanmc-2024-0026
Schlüsselwörter
© 2024 Lei Wang et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Figure 1.
Figure 2
Figure 3.
Figure 4.
Figure 5.
Figure 6.
experimental environment
| Experimental environment | Version |
|---|---|
| CPU | IntelCorei7-11800H |
| GPU | NVIDIA GeForce RTX2080 Ti |
| Language | Python3.8 |
| Deep Learning Framework | Pytorch1.14.0 |
| CUDA | 11.8.0 |
Ccomparison of algorithm enhancements
| index algorithm | PSNR | SSIM | Entropy | AG | EME |
|---|---|---|---|---|---|
| Original image | 6.2850 | 41.9135 | 2.6388 | ||
| SSR | 28.2970 | 0.85522 | 5.7150 | 44.2675 | 2.8967 |
| MSR | 28.7772 | 0.8676 | 6.2176 | 44.9135 | 2.8932 |
| DDE | 36.0989 | 0.9679 | 6.4594 | 44.2206 | 2.6857 |
| Bilateral filtering | 34.6621 | 0.8395 | 6.3155 | 21.7407 | 1.4891 |
| DDE+MSR | 28.7581 | 0.8436 | 6.2793 | 46.8969 | 2.8882 |
Comparative experiments of different parameters of shape-iou
| s | 0.1 | 0.2 | 0.3 | 0.4 | 0.5 | 0.6 | 1.0 |
|---|---|---|---|---|---|---|---|
| mAP(%) | 83.5 | 83.4 | 84.9 | 84.8 | 83.5 | 83.4 |
Compares the experimental results
| EMA | CMAixing | Shape-IoU | ATFL | P/% | R/% | AP/% | Param/106 |
|---|---|---|---|---|---|---|---|
| 73.2 | 75.2 | 84.6 | 32.81 | ||||
| √ | 72.2 | 76.3 | 85.5 | 33.40 | |||
| √ | 74.8 | 75.2 | 85.6 | 34.97 | |||
| √ | √ | 74.1 | 75.0 | 86.2 | 35.23 | ||
| √ | √ | 75.5 | 76.2 | 85.9 | 32.81 | ||
| √ | √ | √ | √ | 75.4 | 77.1 | 87.8 | 35.23 |