AGMG-Net: Leveraging multiscale and fine-grained features for improved cargo recognition
Security systems place great emphasis on the safety of stored cargo, as any loss or tampering can result in significant economic damage. The cargo identification module within the security system faces the challenge of achieving a 99.99% recognition accuracy. However, current identification methods...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-08-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023746?viewType=HTML |
| _version_ | 1797672206050787328 |
|---|---|
| author | Aigou Li Chen Yang |
| author_facet | Aigou Li Chen Yang |
| author_sort | Aigou Li |
| collection | DOAJ |
| description | Security systems place great emphasis on the safety of stored cargo, as any loss or tampering can result in significant economic damage. The cargo identification module within the security system faces the challenge of achieving a 99.99% recognition accuracy. However, current identification methods are limited in accuracy due to the lack of cargo data, insufficient utilization of image features and minimal differences between actual cargo classes. First, we collected and created a cargo identification dataset named "Cargo" using industrial cameras. Subsequently, an Attention-guided Multi-granularity feature fusion model (AGMG-Net) was proposed for cargo identification. This model extracts both coarse-grained and fine-grained features of the cargo using two branch networks and fuses them to fully utilize the information contained in these features. Furthermore, the Attention-guided Multi-stage Attention Accumulation (AMAA) module is introduced for target localization, and the Multi-region Optimal Selection method Based on Confidence (MOSBC) module is used for target cropping. The features from the two branches are fused using a fusion branch in a Concat manner for multi-granularity feature fusion. The experimental results show that the proposed model achieves an average recognition rate of 99.58, 92.73 and 88.57% on the self-built dataset Cargo, and the publicly available datasets Flower and Butterfly20, respectively. This is better than the state-of-the-art model. Therefore, this research method accurately identifies cargo categories and provides valuable assistance to security systems. |
| first_indexed | 2024-03-11T21:26:40Z |
| format | Article |
| id | doaj.art-33649097839e480ea11d971cc4fd4d62 |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-03-11T21:26:40Z |
| publishDate | 2023-08-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-33649097839e480ea11d971cc4fd4d622023-09-28T01:15:52ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-08-01209167441676110.3934/mbe.2023746AGMG-Net: Leveraging multiscale and fine-grained features for improved cargo recognitionAigou Li 0Chen Yang1College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, ChinaCollege of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, ChinaSecurity systems place great emphasis on the safety of stored cargo, as any loss or tampering can result in significant economic damage. The cargo identification module within the security system faces the challenge of achieving a 99.99% recognition accuracy. However, current identification methods are limited in accuracy due to the lack of cargo data, insufficient utilization of image features and minimal differences between actual cargo classes. First, we collected and created a cargo identification dataset named "Cargo" using industrial cameras. Subsequently, an Attention-guided Multi-granularity feature fusion model (AGMG-Net) was proposed for cargo identification. This model extracts both coarse-grained and fine-grained features of the cargo using two branch networks and fuses them to fully utilize the information contained in these features. Furthermore, the Attention-guided Multi-stage Attention Accumulation (AMAA) module is introduced for target localization, and the Multi-region Optimal Selection method Based on Confidence (MOSBC) module is used for target cropping. The features from the two branches are fused using a fusion branch in a Concat manner for multi-granularity feature fusion. The experimental results show that the proposed model achieves an average recognition rate of 99.58, 92.73 and 88.57% on the self-built dataset Cargo, and the publicly available datasets Flower and Butterfly20, respectively. This is better than the state-of-the-art model. Therefore, this research method accurately identifies cargo categories and provides valuable assistance to security systems.https://www.aimspress.com/article/doi/10.3934/mbe.2023746?viewType=HTMLcomputer visioncargo identificationsecurity systemattention guidancemulti-branch network |
| spellingShingle | Aigou Li Chen Yang AGMG-Net: Leveraging multiscale and fine-grained features for improved cargo recognition Mathematical Biosciences and Engineering computer vision cargo identification security system attention guidance multi-branch network |
| title | AGMG-Net: Leveraging multiscale and fine-grained features for improved cargo recognition |
| title_full | AGMG-Net: Leveraging multiscale and fine-grained features for improved cargo recognition |
| title_fullStr | AGMG-Net: Leveraging multiscale and fine-grained features for improved cargo recognition |
| title_full_unstemmed | AGMG-Net: Leveraging multiscale and fine-grained features for improved cargo recognition |
| title_short | AGMG-Net: Leveraging multiscale and fine-grained features for improved cargo recognition |
| title_sort | agmg net leveraging multiscale and fine grained features for improved cargo recognition |
| topic | computer vision cargo identification security system attention guidance multi-branch network |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023746?viewType=HTML |
| work_keys_str_mv | AT aigouli agmgnetleveragingmultiscaleandfinegrainedfeaturesforimprovedcargorecognition AT chenyang agmgnetleveragingmultiscaleandfinegrainedfeaturesforimprovedcargorecognition |