Lightweight Detection Method for X-ray Security Inspection with Occlusion

Identifying the classes and locations of prohibited items is the target of security inspection. However, X-ray security inspection images with insufficient feature extraction, imbalance between easy and hard samples, and occlusion lead to poor detection accuracy. To address the above problems, an ob...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2024-02, Vol.24 (3), p.1002
Main Authors: Wang, Zanshi, Wang, Xiaohua, Shi, Yueting, Qi, Hang, Jia, Minli, Wang, Weijiang
Format: Article
Language:English
Subjects:
Algorithms
Analysis
Classification
Datasets
Deep learning
Discriminant analysis
lightweight model
Methods
object detection
Safety and security measures
Security management
Sensors
X-ray security inspection
YOLOv8
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Identifying the classes and locations of prohibited items is the target of security inspection. However, X-ray security inspection images with insufficient feature extraction, imbalance between easy and hard samples, and occlusion lead to poor detection accuracy. To address the above problems, an object-detection method based on YOLOv8 is proposed. Firstly, an ASFF (adaptive spatial feature fusion) and a weighted feature concatenation algorithm are introduced to fully extract the scale features from input images. In this way, the model can learn further details in training. Secondly, CoordAtt (coordinate attention module), which belongs to the hybrid attention mechanism, is embedded to enhance the learning of features of interest. Then, the slide loss function is introduced to balance the simple samples and the difficult samples. Finally, Soft-NMS (non-maximum suppression) is introduced to resist the conditions containing occlusion. The experimental result shows that mAP (mean average precision) achieves 90.2%, 90.5%, 79.1%, and 91.4% on the Easy, Hard, and Hidden sets of the PIDray and SIXray public test set, respectively. Contrasted with original model, the mAP of our proposed YOLOv8n model increased by 2.7%, 3.1%, 9.3%, and 2.4%, respectively. Furthermore, the parameter count of the modified YOLOv8n model is roughly only 3 million.
ISSN:1424-8220
1424-8220
DOI:10.3390/s24031002