Security Inspection Image Object Detection Method with Attention Mechanism and Multilayer Feature Fusion Strategy

Table 1. Number of convolution kernels of Backbone in different YOLOv5 networks
View table
Table 1. Number of convolution kernels of Backbone in different YOLOv5 networks
Network YOLOv5s YOLOv5m YOLOv5l YOLOv5x
Model size /MB 27 84 192 367
Focus 32 48 64 80
CBL-1 64 96 128 160
CBL-2 128 192 256 320
CBL-3 256 384 512 640
CBL-4 512 768 1024 1208

Table 2. Comparison results of SA modules
View table
Table 2. Comparison results of SA modules
Module mAP /% （mAP，0.50∶0.95）/% N_P
YOLOv5s 87.2 55.9 0
YOLOv5s+SA 88.7 56.3 2048
YOLOv5s+SAd 88.9 56.4 940
YOLOv5s +E-SAd 90.4 57.6 17832

Table 3. Comparison results of channel attention module
View table
Table 3. Comparison results of channel attention module
Module mAP /% （mAP，0.5∶0.95）/% N_P
YOLOv5s 87.2 55.9 0
YOLOv5s+SE 88.1 56.3 43008
YOLOv5s+ECA 89.4 58.7 22868
YOLOv5s+iECA（k=3） 91.5 59.5 25668
YOLOv5s+iECA（k=5） 91.4 59.2 32786

Table 4. Comparison results of ablation experiments of each module
View table
Table 4. Comparison results of ablation experiments of each module
No. Modules ASFF E-SAd iECA mAP /%
1 YOLOv5s × × × 87.2
2 YOLOv5s+E-SAd+iECA × √ √ 92.5
3 YOLOv5s+ASFF √ × × 91.3
4 YOLOv5s+ASFF+E-SAd √ √ × 92.2
5 YOLOv5s+ASFF+iECA √ × √ 92.7
6 YOLOv5s+ASFF+E-SAd+iECA √ √ √ 94.5

Table 5. Detection results of different networks

View table

Table 5. Detection results of different networks

Network	Backbone	P	R	mAP /%	Module size /m
Faster RCNN	VGG	0.874	0.759	86.8	160
RetinaNet	ResNet+FPN	0.904	0.790	90.0	140
YOLOv4	CSP DarkNet53	0.920	0.812	91.7	240
PP-YOLOv2	ResNet50-vd	0.949	0.865	93.4	83
YOLOv5s	CSP DarkNet	0.890	0.782	87.2	22
YOLOv5x	CSP DarkNet	0.968	0.889	95.6	320
B-YOLO	Dark Net+CSP	0.907	0.800	90.4	39
YOLOv5+	GhostBottleneck	0.896	0.795	88.2	24
YOLOv5s-AFA	CSP DarkNet	0.967	0.871	94.5	26

Tools

Get Citation

Copy Citation Text

Hong Zhang, Sicong Zhang. Security Inspection Image Object Detection Method with Attention Mechanism and Multilayer Feature Fusion Strategy[J]. Laser & Optoelectronics Progress, 2022, 59(16): 1610013

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites