Hidden Dangerous Object Recognition in Terahertz Images Using Deep Learning Methods
As a harmless detection method, terahertz has become a new trend in security detection. However, there are inherent problems such as the low quality of the images collected by terahertz equipment and the insufficient detection accuracy of dangerous goods. This work advances BiFPN at the neck of YOLO...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/15/7354 |
| _version_ | 1797433036800786432 |
|---|---|
| author | Samuel Akwasi Danso Liping Shang Deng Hu Justice Odoom Quancheng Liu Benedicta Nana Esi Nyarko |
| author_facet | Samuel Akwasi Danso Liping Shang Deng Hu Justice Odoom Quancheng Liu Benedicta Nana Esi Nyarko |
| author_sort | Samuel Akwasi Danso |
| collection | DOAJ |
| description | As a harmless detection method, terahertz has become a new trend in security detection. However, there are inherent problems such as the low quality of the images collected by terahertz equipment and the insufficient detection accuracy of dangerous goods. This work advances BiFPN at the neck of YOLOv5 of the deep learning model as a mechanism to improve low resolution. We also perform transfer learning, thereby fine-tuning the pre-training weight of the backbone for migration learning in our model. Results from experimental analysis reveal that mAP@0.5 and mAP@0.5:0.95 values witness a percentage increase of 0.2% and 1.7%, respectively, attesting to the superiority of the proposed model to YOLOv5, which is the state-of-the-art model in object detection. |
| first_indexed | 2024-03-09T10:10:20Z |
| format | Article |
| id | doaj.art-51e4cda5b8f84e9c8c85918427eed310 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T10:10:20Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-51e4cda5b8f84e9c8c85918427eed3102023-12-01T22:48:41ZengMDPI AGApplied Sciences2076-34172022-07-011215735410.3390/app12157354Hidden Dangerous Object Recognition in Terahertz Images Using Deep Learning MethodsSamuel Akwasi Danso0Liping Shang1Deng Hu2Justice Odoom3Quancheng Liu4Benedicta Nana Esi Nyarko5School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaAs a harmless detection method, terahertz has become a new trend in security detection. However, there are inherent problems such as the low quality of the images collected by terahertz equipment and the insufficient detection accuracy of dangerous goods. This work advances BiFPN at the neck of YOLOv5 of the deep learning model as a mechanism to improve low resolution. We also perform transfer learning, thereby fine-tuning the pre-training weight of the backbone for migration learning in our model. Results from experimental analysis reveal that mAP@0.5 and mAP@0.5:0.95 values witness a percentage increase of 0.2% and 1.7%, respectively, attesting to the superiority of the proposed model to YOLOv5, which is the state-of-the-art model in object detection.https://www.mdpi.com/2076-3417/12/15/7354terahertz imageobject detectionhidden objectairport scanned object |
| spellingShingle | Samuel Akwasi Danso Liping Shang Deng Hu Justice Odoom Quancheng Liu Benedicta Nana Esi Nyarko Hidden Dangerous Object Recognition in Terahertz Images Using Deep Learning Methods Applied Sciences terahertz image object detection hidden object airport scanned object |
| title | Hidden Dangerous Object Recognition in Terahertz Images Using Deep Learning Methods |
| title_full | Hidden Dangerous Object Recognition in Terahertz Images Using Deep Learning Methods |
| title_fullStr | Hidden Dangerous Object Recognition in Terahertz Images Using Deep Learning Methods |
| title_full_unstemmed | Hidden Dangerous Object Recognition in Terahertz Images Using Deep Learning Methods |
| title_short | Hidden Dangerous Object Recognition in Terahertz Images Using Deep Learning Methods |
| title_sort | hidden dangerous object recognition in terahertz images using deep learning methods |
| topic | terahertz image object detection hidden object airport scanned object |
| url | https://www.mdpi.com/2076-3417/12/15/7354 |
| work_keys_str_mv | AT samuelakwasidanso hiddendangerousobjectrecognitioninterahertzimagesusingdeeplearningmethods AT lipingshang hiddendangerousobjectrecognitioninterahertzimagesusingdeeplearningmethods AT denghu hiddendangerousobjectrecognitioninterahertzimagesusingdeeplearningmethods AT justiceodoom hiddendangerousobjectrecognitioninterahertzimagesusingdeeplearningmethods AT quanchengliu hiddendangerousobjectrecognitioninterahertzimagesusingdeeplearningmethods AT benedictananaesinyarko hiddendangerousobjectrecognitioninterahertzimagesusingdeeplearningmethods |