GDMR-Net: A Novel Graphic Detection Neural Network via Multi-Crossed Attention and Rotation Annotation for Agronomic Applications in Supply Cyber Security
The development of smart agriculture holds great significance in ensuring the supply and cyber security of agricultural production. With the advancement of intelligent technologies, unmanned robots collaborating with the Internet of Things (IoT) play increasingly crucial roles in the realm of smart...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/13/12/2893 |
| _version_ | 1797382368675233792 |
|---|---|
| author | Zhangchi Xue Xueqi Zhao Yucheng Xiu Chenghao Hua Jianlei Kong |
| author_facet | Zhangchi Xue Xueqi Zhao Yucheng Xiu Chenghao Hua Jianlei Kong |
| author_sort | Zhangchi Xue |
| collection | DOAJ |
| description | The development of smart agriculture holds great significance in ensuring the supply and cyber security of agricultural production. With the advancement of intelligent technologies, unmanned robots collaborating with the Internet of Things (IoT) play increasingly crucial roles in the realm of smart agriculture; they have become effective means to ensure agricultural safety and supply security. However, in the pursuit of unmanned agronomic applications, there is an urgent challenge: these intelligent systems generally show low accuracy in target detection when relying on visual perception due to fine-grained changes and differing postures of crops. To solve this issue, we proposed a novel multi-target detection approach via incorporating graph representation learning and multi-crossed attention techniques. The proposed model first utilizes a lightweight backbone network to accurately identify the characteristics and conditions of crops. Then, the higher-order graphic feature extractor is designed to comprehensively observe fine-grained features and potential graphic relationships among massive crops, enabling better perception capabilities of agricultural robots, allowing them to adapt to complex environments. Additionally, we can address bilevel routing by combining ghost attention and rotation annotations to handle continuous posture changes during crop growth and mutual occlusion. An extensive set of experiments demonstrated that our proposed approach outperforms various advanced methods of crop detection, achieving identification accuracies up to 89.6% (mAP) and 94.7% (AP50). Ablation studies further proved the preferable stability, of which the parameter size is only 628 Mbyte, while maintaining a high processing speed of 89 frames per second. This provides strong support for application of the technique in smart agriculture production and supply cyber security. |
| first_indexed | 2024-03-08T21:04:23Z |
| format | Article |
| id | doaj.art-4cc0c7ebe1a14315adfc275e883f8bca |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-08T21:04:23Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-4cc0c7ebe1a14315adfc275e883f8bca2023-12-22T13:46:12ZengMDPI AGAgronomy2073-43952023-11-011312289310.3390/agronomy13122893GDMR-Net: A Novel Graphic Detection Neural Network via Multi-Crossed Attention and Rotation Annotation for Agronomic Applications in Supply Cyber SecurityZhangchi Xue0Xueqi Zhao1Yucheng Xiu2Chenghao Hua3Jianlei Kong4School of Cyberspace Security, Southeast University, Nanjing 211189, ChinaSchool of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaThe development of smart agriculture holds great significance in ensuring the supply and cyber security of agricultural production. With the advancement of intelligent technologies, unmanned robots collaborating with the Internet of Things (IoT) play increasingly crucial roles in the realm of smart agriculture; they have become effective means to ensure agricultural safety and supply security. However, in the pursuit of unmanned agronomic applications, there is an urgent challenge: these intelligent systems generally show low accuracy in target detection when relying on visual perception due to fine-grained changes and differing postures of crops. To solve this issue, we proposed a novel multi-target detection approach via incorporating graph representation learning and multi-crossed attention techniques. The proposed model first utilizes a lightweight backbone network to accurately identify the characteristics and conditions of crops. Then, the higher-order graphic feature extractor is designed to comprehensively observe fine-grained features and potential graphic relationships among massive crops, enabling better perception capabilities of agricultural robots, allowing them to adapt to complex environments. Additionally, we can address bilevel routing by combining ghost attention and rotation annotations to handle continuous posture changes during crop growth and mutual occlusion. An extensive set of experiments demonstrated that our proposed approach outperforms various advanced methods of crop detection, achieving identification accuracies up to 89.6% (mAP) and 94.7% (AP50). Ablation studies further proved the preferable stability, of which the parameter size is only 628 Mbyte, while maintaining a high processing speed of 89 frames per second. This provides strong support for application of the technique in smart agriculture production and supply cyber security.https://www.mdpi.com/2073-4395/13/12/2893smart agriculturefine-grained crop identificationgraph representationmulti-crossed ghost attentionrotating target detection |
| spellingShingle | Zhangchi Xue Xueqi Zhao Yucheng Xiu Chenghao Hua Jianlei Kong GDMR-Net: A Novel Graphic Detection Neural Network via Multi-Crossed Attention and Rotation Annotation for Agronomic Applications in Supply Cyber Security Agronomy smart agriculture fine-grained crop identification graph representation multi-crossed ghost attention rotating target detection |
| title | GDMR-Net: A Novel Graphic Detection Neural Network via Multi-Crossed Attention and Rotation Annotation for Agronomic Applications in Supply Cyber Security |
| title_full | GDMR-Net: A Novel Graphic Detection Neural Network via Multi-Crossed Attention and Rotation Annotation for Agronomic Applications in Supply Cyber Security |
| title_fullStr | GDMR-Net: A Novel Graphic Detection Neural Network via Multi-Crossed Attention and Rotation Annotation for Agronomic Applications in Supply Cyber Security |
| title_full_unstemmed | GDMR-Net: A Novel Graphic Detection Neural Network via Multi-Crossed Attention and Rotation Annotation for Agronomic Applications in Supply Cyber Security |
| title_short | GDMR-Net: A Novel Graphic Detection Neural Network via Multi-Crossed Attention and Rotation Annotation for Agronomic Applications in Supply Cyber Security |
| title_sort | gdmr net a novel graphic detection neural network via multi crossed attention and rotation annotation for agronomic applications in supply cyber security |
| topic | smart agriculture fine-grained crop identification graph representation multi-crossed ghost attention rotating target detection |
| url | https://www.mdpi.com/2073-4395/13/12/2893 |
| work_keys_str_mv | AT zhangchixue gdmrnetanovelgraphicdetectionneuralnetworkviamulticrossedattentionandrotationannotationforagronomicapplicationsinsupplycybersecurity AT xueqizhao gdmrnetanovelgraphicdetectionneuralnetworkviamulticrossedattentionandrotationannotationforagronomicapplicationsinsupplycybersecurity AT yuchengxiu gdmrnetanovelgraphicdetectionneuralnetworkviamulticrossedattentionandrotationannotationforagronomicapplicationsinsupplycybersecurity AT chenghaohua gdmrnetanovelgraphicdetectionneuralnetworkviamulticrossedattentionandrotationannotationforagronomicapplicationsinsupplycybersecurity AT jianleikong gdmrnetanovelgraphicdetectionneuralnetworkviamulticrossedattentionandrotationannotationforagronomicapplicationsinsupplycybersecurity |