A Lightweight Border Patrol Object Detection Network for Edge Devices
Border patrol object detection is an important basis for obtaining information about the border patrol area and for analyzing and determining the mission situation. Border Patrol Staffing is now equipped with medium to close range UAVs and portable reconnaissance equipment to carry out its tasks. In...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/22/3828 |
| _version_ | 1797465455499149312 |
|---|---|
| author | Lei Yue Haifeng Ling Jianhu Yuan Linyuan Bai |
| author_facet | Lei Yue Haifeng Ling Jianhu Yuan Linyuan Bai |
| author_sort | Lei Yue |
| collection | DOAJ |
| description | Border patrol object detection is an important basis for obtaining information about the border patrol area and for analyzing and determining the mission situation. Border Patrol Staffing is now equipped with medium to close range UAVs and portable reconnaissance equipment to carry out its tasks. In this paper, we designed a detection algorithm TP-ODA for the border patrol object detection task in order to improve the UAV and portable reconnaissance equipment for the task of border patrol object detection, which is mostly performed in embedded devices with limited computing power and the detection frame imbalance problem is improved; finally, the PDOEM structure is designed in the neck network to optimize the feature fusion module of the algorithm. In order to verify the improvement effect of the algorithm in this paper, the Border Patrol object dataset BDP is constructed. The experiments show that, compared to the baseline model, the TP-ODA algorithm improves mAP by 2.9%, reduces GFLOPs by 65.19%, reduces model volume by 63.83% and improves FPS by 8.47%. The model comparison experiments were then combined with the requirements of the border patrol tasks, and it was concluded that the TP-ODA model is more suitable for UAV and portable reconnaissance equipment to carry and can better fulfill the task of border patrol object detection. |
| first_indexed | 2024-03-09T18:22:40Z |
| format | Article |
| id | doaj.art-9f60e7c9a48e4c57aabc5c3656f21297 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T18:22:40Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-9f60e7c9a48e4c57aabc5c3656f212972023-11-24T08:11:10ZengMDPI AGElectronics2079-92922022-11-011122382810.3390/electronics11223828A Lightweight Border Patrol Object Detection Network for Edge DevicesLei Yue0Haifeng Ling1Jianhu Yuan2Linyuan Bai3Field Engineering College, Army Engineering University of PLA, Nanjing 210022, ChinaField Engineering College, Army Engineering University of PLA, Nanjing 210022, ChinaField Engineering College, Army Engineering University of PLA, Nanjing 210022, ChinaField Engineering College, Army Engineering University of PLA, Nanjing 210022, ChinaBorder patrol object detection is an important basis for obtaining information about the border patrol area and for analyzing and determining the mission situation. Border Patrol Staffing is now equipped with medium to close range UAVs and portable reconnaissance equipment to carry out its tasks. In this paper, we designed a detection algorithm TP-ODA for the border patrol object detection task in order to improve the UAV and portable reconnaissance equipment for the task of border patrol object detection, which is mostly performed in embedded devices with limited computing power and the detection frame imbalance problem is improved; finally, the PDOEM structure is designed in the neck network to optimize the feature fusion module of the algorithm. In order to verify the improvement effect of the algorithm in this paper, the Border Patrol object dataset BDP is constructed. The experiments show that, compared to the baseline model, the TP-ODA algorithm improves mAP by 2.9%, reduces GFLOPs by 65.19%, reduces model volume by 63.83% and improves FPS by 8.47%. The model comparison experiments were then combined with the requirements of the border patrol tasks, and it was concluded that the TP-ODA model is more suitable for UAV and portable reconnaissance equipment to carry and can better fulfill the task of border patrol object detection.https://www.mdpi.com/2079-9292/11/22/3828object detectiondeep learningcomputer visionborder patrol |
| spellingShingle | Lei Yue Haifeng Ling Jianhu Yuan Linyuan Bai A Lightweight Border Patrol Object Detection Network for Edge Devices Electronics object detection deep learning computer vision border patrol |
| title | A Lightweight Border Patrol Object Detection Network for Edge Devices |
| title_full | A Lightweight Border Patrol Object Detection Network for Edge Devices |
| title_fullStr | A Lightweight Border Patrol Object Detection Network for Edge Devices |
| title_full_unstemmed | A Lightweight Border Patrol Object Detection Network for Edge Devices |
| title_short | A Lightweight Border Patrol Object Detection Network for Edge Devices |
| title_sort | lightweight border patrol object detection network for edge devices |
| topic | object detection deep learning computer vision border patrol |
| url | https://www.mdpi.com/2079-9292/11/22/3828 |
| work_keys_str_mv | AT leiyue alightweightborderpatrolobjectdetectionnetworkforedgedevices AT haifengling alightweightborderpatrolobjectdetectionnetworkforedgedevices AT jianhuyuan alightweightborderpatrolobjectdetectionnetworkforedgedevices AT linyuanbai alightweightborderpatrolobjectdetectionnetworkforedgedevices AT leiyue lightweightborderpatrolobjectdetectionnetworkforedgedevices AT haifengling lightweightborderpatrolobjectdetectionnetworkforedgedevices AT jianhuyuan lightweightborderpatrolobjectdetectionnetworkforedgedevices AT linyuanbai lightweightborderpatrolobjectdetectionnetworkforedgedevices |