EM-YOLO: An X-ray Prohibited-Item-Detection Method Based on Edge and Material Information Fusion
Using X-ray imaging in security inspections is common for the detection of objects. X-ray security images have strong texture and RGB features as well as the characteristics of background clutter and object overlap, which makes X-ray imaging very different from other real-world imaging methods. To b...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/20/8555 |
| _version_ | 1827719903196479488 |
|---|---|
| author | Bing Jing Pianzhang Duan Lu Chen Yanhui Du |
| author_facet | Bing Jing Pianzhang Duan Lu Chen Yanhui Du |
| author_sort | Bing Jing |
| collection | DOAJ |
| description | Using X-ray imaging in security inspections is common for the detection of objects. X-ray security images have strong texture and RGB features as well as the characteristics of background clutter and object overlap, which makes X-ray imaging very different from other real-world imaging methods. To better detect prohibited items in security X-ray images with these characteristics, we propose EM-YOLOv7, which is composed of both an edge feature extractor (EFE) and a material feature extractor (MFE). We used the Soft-WIoU NMS method to solve the problem of object overlap. To better extract features, the attention mechanism CBAM was added to the backbone. According to the results of several experiments on the SIXray dataset, our EM-YOLOv7 method can better complete prohibited-item-detection tasks during security inspection with detection accuracy that is 4% and 0.9% higher than that of YOLOv5 and YOLOv7, respectively, and other SOTA models. |
| first_indexed | 2024-03-10T20:55:13Z |
| format | Article |
| id | doaj.art-f2d3a42d40aa44eaaea0a96ef698ba5b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:55:13Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f2d3a42d40aa44eaaea0a96ef698ba5b2023-11-19T18:04:41ZengMDPI AGSensors1424-82202023-10-012320855510.3390/s23208555EM-YOLO: An X-ray Prohibited-Item-Detection Method Based on Edge and Material Information FusionBing Jing0Pianzhang Duan1Lu Chen2Yanhui Du3School of Information and Network Security, People’s Public Security University of China, Beijing 102206, ChinaSchool of Information Engineering, Shenyang University of Chemical Technology, Shenyang 110142, ChinaSchool of Vehicle and Mobility, Tsinghua University, Beijing 100190, ChinaSchool of Information and Network Security, People’s Public Security University of China, Beijing 102206, ChinaUsing X-ray imaging in security inspections is common for the detection of objects. X-ray security images have strong texture and RGB features as well as the characteristics of background clutter and object overlap, which makes X-ray imaging very different from other real-world imaging methods. To better detect prohibited items in security X-ray images with these characteristics, we propose EM-YOLOv7, which is composed of both an edge feature extractor (EFE) and a material feature extractor (MFE). We used the Soft-WIoU NMS method to solve the problem of object overlap. To better extract features, the attention mechanism CBAM was added to the backbone. According to the results of several experiments on the SIXray dataset, our EM-YOLOv7 method can better complete prohibited-item-detection tasks during security inspection with detection accuracy that is 4% and 0.9% higher than that of YOLOv5 and YOLOv7, respectively, and other SOTA models.https://www.mdpi.com/1424-8220/23/20/8555X-ray security inspectiondeep learningobject detectionattention mechanism |
| spellingShingle | Bing Jing Pianzhang Duan Lu Chen Yanhui Du EM-YOLO: An X-ray Prohibited-Item-Detection Method Based on Edge and Material Information Fusion Sensors X-ray security inspection deep learning object detection attention mechanism |
| title | EM-YOLO: An X-ray Prohibited-Item-Detection Method Based on Edge and Material Information Fusion |
| title_full | EM-YOLO: An X-ray Prohibited-Item-Detection Method Based on Edge and Material Information Fusion |
| title_fullStr | EM-YOLO: An X-ray Prohibited-Item-Detection Method Based on Edge and Material Information Fusion |
| title_full_unstemmed | EM-YOLO: An X-ray Prohibited-Item-Detection Method Based on Edge and Material Information Fusion |
| title_short | EM-YOLO: An X-ray Prohibited-Item-Detection Method Based on Edge and Material Information Fusion |
| title_sort | em yolo an x ray prohibited item detection method based on edge and material information fusion |
| topic | X-ray security inspection deep learning object detection attention mechanism |
| url | https://www.mdpi.com/1424-8220/23/20/8555 |
| work_keys_str_mv | AT bingjing emyoloanxrayprohibiteditemdetectionmethodbasedonedgeandmaterialinformationfusion AT pianzhangduan emyoloanxrayprohibiteditemdetectionmethodbasedonedgeandmaterialinformationfusion AT luchen emyoloanxrayprohibiteditemdetectionmethodbasedonedgeandmaterialinformationfusion AT yanhuidu emyoloanxrayprohibiteditemdetectionmethodbasedonedgeandmaterialinformationfusion |