Chinese Optics, Volume. 16, Issue 3, 607(2023)
Lightweight infrared detection of ammonia leakage using shuffle and self-attention
Figures & Tables(17)
Fig. 2. Change diagram of a real frame of infrared ammonia leakage
Fig. 3. Visualization results of the height/width ratio of the anchor in ammonia leak infrared detection data
Table 1. Initial candidate frame sizes of the three detection layers before and after clustering
View tableView in ArticleTable 1. Initial candidate frame sizes of the three detection layers before and after clustering
检测层 聚类前 聚类后 检测层1 （10,13）、（16,30）、（33,23） （11,10）、（29,12）、（34,29） 检测层2 （30,61）、（62,45）、（59,119） （52,61）、（62,18）、（64,38） 检测层3 （116,90）、（156,198）、（373,326） （91,38）、（115,22）、（201,45）
Table 2. Hyperparameter configuration
View tableView in ArticleTable 2. Hyperparameter configuration
超参数名称 超参数值 批大小 16 初始学习率 0.01 迭代次数 400 动量 0.937 学习率衰减策略 余弦退火策略 权重衰减 0.0005
Table 3. Objective evaluation indicators of image preprocessing algorithms
View tableView in ArticleTable 3. Objective evaluation indicators of image preprocessing algorithms
图像 PSNR/dB AG IE 原图像 23.40 1.90 7.06 预处理图像 2.17 7.53
Table 4. Comparison of network performances before and after image preprocessing
View tableView in ArticleTable 4. Comparison of network performances before and after image preprocessing
模型 Params/M Model size/M Speed/ms mAP/% YOLOv5s 7.05 14.40 3.60 92.80 Prep-YOLOv5s 7.05 14.40 3.60 93.80
Table 5. Comparison of network performance before and after clustering
View tableView in ArticleTable 5. Comparison of network performance before and after clustering
模型 Params/M Model size/M Speed/ms mAP/% YOLOv5s 7.05 14.40 3.60 92.80 Kms-YOLOv5s 7.05 14.40 3.60 93.70 Kms-Prep-YOLOv5s 7.05 14.40 3.60 94.30
Table 6. Comparison of evaluation indicators for different backbone networks
View tableView in ArticleTable 6. Comparison of evaluation indicators for different backbone networks
模型 GFLOPs Model size/M Params /M Speed /ms mAP /% GhostNet-YOLOv5s 10.60 10.50 5.08 3.00 93.90 MobileNetv3-YOLOv5s 6.30 7.40 3.54 2.80 93.50 ShuffleNetv2-YOLOv5s 4.60 3.40 1.53 2.70 93.80 SK5-YOLOv5s 4.80 3.40 1.57 2.70 94.40
Table 7. Comparison of network performance of different BottleNeck structures
View tableView in ArticleTable 7. Comparison of network performance of different BottleNeck structures
模型 Model size/M Params /M Speed /ms mAP /% SK5-YOLOv5s 3.40 1.57 2.70 94.40 SK5-YOLOv5s-CSPBottleNeck 3.40 1.54 2.70 93.70 SK5-YOLOv5s-GhostBottleNeck 3.30 1.50 2.60 94.20 SK5-YOLOv5s-CbamBottleNeck 3.20 1.47 2.50 92.90 SSANet 3.40 1.53 3.20 96.30
Table 8. Accuracy comparison of different models
View tableView in ArticleTable 8. Accuracy comparison of different models
Model GFLOPs Params/M Model size/M Speed/ms mAP/% YOLOv3 154.7 61.50 123.40 11.70 92.70 YOLOv3-tiny 12.90 8.70 17.40 3.40 37.40 YOLOv5s 16.30 7.05 14.40 3.60 92.80 YOLOx 26.64 8.94 71.90 8.43 89.78 SSANet 4.60 1.53 3.40 3.20 96.30
Tools
Get Citation
Copy Citation Text
Yin-hui ZHANG, Hong ZHUANG, Zi-fen HE, Hong-kuan YANG, Ying HUANG. Lightweight infrared detection of ammonia leakage using shuffle and self-attention[J]. Chinese Optics, 2023, 16(3): 607
Paper Information
Category: Original Article
Received: Jun. 14, 2022
Accepted: --
Published Online: May. 31, 2023
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20