X-Ray Object Detection Based on Pyramid Convolution and Strip Pooling

Fig. 5. Pyramid convolution kernel structure and pyramid convolution residual block structure. (a) Shallow layer pyramid convolution;(b) shallow middle layer pyramid convolution; (c) middle layer pyramid convolution; (d) deep layer pyramid convolution; (e) pyramid convolution residual block

Download full size

Fig. 6. Pyramid Hourglass-104 network structure

Download full size

Fig. 7. Strip pooling module

Download full size

Fig. 8. Strip pooling head. (a) Sharing scheme; (b) unshared scheme

Download full size

Fig. 9. SIXray_OD dataset.(a) Example 1; (b) example 2; (c) example 3; (d) example 4

Download full size

Fig. 10. Comparison of detection results. (a) CenterNet; (b) proposed algorithm

Download full size

Table 1. Statistics of SIXray_OD dataset
View table
Table 1. Statistics of SIXray_OD dataset
Category Knife Scissors Wrench Gun Pliers Total
Number of images 12488 9272 31608 23488 18128 69744

Table 2. Comparative experimental results of different detection networks
View table
Table 2. Comparative experimental results of different detection networks
Network Backbone mAP50 /%
SSD VGG16 71.89
YOLOv3 DarkNet-53 64.34
Faster R-CNN VGG16 78.41
CenterNet Hourglass-104 86.6

Table 3. Ablation experimental results of each improvement point

View table

Table 3. Ablation experimental results of each improvement point

Experiment	Py_Hourglass_104	Strip pooling	IoU loss	AP /%
Experiment	Py_Hourglass_104	Strip pooling	IoU loss	mAP50	Gun	Knife	Pliers	Wrench	Scissors
CenterNet				86.6	95.69	90.44	88.21	83.62	75.04
Experiment 1	✓			87.3	96.00	91.23	88.65	84.53	76.09
Experiment 2		✓		87.5	96.21	91.16	89.12	84.07	76.94
Experiment 3			✓	87.4	95.86	90.64	89.54	85.72	75.25
Experiment 4	✓	✓		88.0	96.38	91.12	89.86	85.92	76.73
Experiment 5	✓		✓	87.7	96.12	91.53	89.05	85.18	76.62
Experiment 6		✓	✓	87.9	96.15	91.85	89.24	85.10	77.06
Experiment 7	✓	✓	✓	88.3	96.40	91.88	89.90	85.90	77.43

Table 4. Pyramid convolution scheme

View table

Table 4. Pyramid convolution scheme

Scheme	Pyramid convolution residual block used
Scheme 1	［shallow、shallow middle、shallow middle，middle、deep］
Scheme 2	［shallow、shallow、shallow middle、shallow middle、deep］
Scheme 3	［shallow、shallow、shallow middle、middle、deep］

Table 5. Comparison results of different pyramid convolution schemes
View table
Table 5. Comparison results of different pyramid convolution schemes
Experiment Scheme 1 Scheme 2 Scheme 3 mAP50 /%
CenterNet 86.6
Experiment 1 ✓ 87.3
Experiment 2 ✓ 87.0
Experiment 3 ✓ 86.9

Table 6. Experimental results of pyramid convolution using position comparison
View table
Table 6. Experimental results of pyramid convolution using position comparison
Experiment D_a D mAP50 /%
CenterNet 86.6
Experiment 1 ✓ 87.3
Experiment 2 ✓ 84.7
Experiment 3 ✓ ✓ 87.0

Table 7. Experimental results of strip pooling using position comparison
View table
Table 7. Experimental results of strip pooling using position comparison
Experiment Backbone Preprocessing subnet Strip pooling head 1 Strip pooling head 2 mAP50 /%
No 86.6
Experiment 1 ✓ 85.6
Experiment 2 ✓ 86.4
Experiment 3 ✓ 87.4
Experiment 4 ✓ 87.8

Tools

Get Citation

Copy Citation Text

Jingqian Qiao, Liang Zhang. X-Ray Object Detection Based on Pyramid Convolution and Strip Pooling[J]. Laser & Optoelectronics Progress, 2022, 59(4): 0410017

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites