Detection of Power Poles in Orchards Based on Improved Yolov5s Model
During the operation of agricultural unmanned aerial vehicles (UAVs) in orchards, the presence of power poles and wires pose a serious threat to flight safety, and can even lead to crashes. Due to the difficulty of directly detecting wires, this research aimed to quickly and accurately detect wire p...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/13/7/1705 |
| _version_ | 1827734345557737472 |
|---|---|
| author | Yali Zhang Xiaoyang Lu Wanjian Li Kangting Yan Zhenjie Mo Yubin Lan Linlin Wang |
| author_facet | Yali Zhang Xiaoyang Lu Wanjian Li Kangting Yan Zhenjie Mo Yubin Lan Linlin Wang |
| author_sort | Yali Zhang |
| collection | DOAJ |
| description | During the operation of agricultural unmanned aerial vehicles (UAVs) in orchards, the presence of power poles and wires pose a serious threat to flight safety, and can even lead to crashes. Due to the difficulty of directly detecting wires, this research aimed to quickly and accurately detect wire poles, and proposed an improved Yolov5s deep learning object detection algorithm named Yolov5s-Pole. The algorithm enhances the model’s generalization ability and robustness by applying Mixup data augmentation technique, replaces the C3 module with the GhostBottleneck module to reduce the model’s parameters and computational complexity, and incorporates the Shuffle Attention (SA) module to improve its focus on small targets. The results show that when the improved Yolov5s-Pole model was used for detecting poles in orchards, its accuracy, recall, and mAP@50 were 0.803, 0.831, and 0.838 respectively, which increased by 0.5%, 10%, and 9.2% compared to the original Yolov5s model. Additionally, the weights, parameters, and GFLOPs of the Yolov5s-Pole model were 7.86 MB, 3,974,310, and 9, respectively. Compared to the original Yolov5s model, these represent compression rates of 42.2%, 43.4%, and 43.3%, respectively. The detection time for a single image using this model was 4.2 ms, and good robustness under different lighting conditions (dark, normal, and bright) was demonstrated. The model is suitable for deployment on agricultural UAVs’ onboard equipment, and is of great practical significance for ensuring the efficiency and flight safety of agricultural UAVs. |
| first_indexed | 2024-03-11T01:23:59Z |
| format | Article |
| id | doaj.art-e1f15e5503ba4abab5ef5067b0708d12 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-11T01:23:59Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-e1f15e5503ba4abab5ef5067b0708d122023-11-18T17:54:56ZengMDPI AGAgronomy2073-43952023-06-01137170510.3390/agronomy13071705Detection of Power Poles in Orchards Based on Improved Yolov5s ModelYali Zhang0Xiaoyang Lu1Wanjian Li2Kangting Yan3Zhenjie Mo4Yubin Lan5Linlin Wang6College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaNational Center for International Collaboration Research on Precision Agricultural Aviation Pesticides Spraying Technology, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaNational Center for International Collaboration Research on Precision Agricultural Aviation Pesticides Spraying Technology, Guangzhou 510642, ChinaSchool of Artificial Intelligence, Shenzhen Polytechnic University, Shenzhen 518055, ChinaDuring the operation of agricultural unmanned aerial vehicles (UAVs) in orchards, the presence of power poles and wires pose a serious threat to flight safety, and can even lead to crashes. Due to the difficulty of directly detecting wires, this research aimed to quickly and accurately detect wire poles, and proposed an improved Yolov5s deep learning object detection algorithm named Yolov5s-Pole. The algorithm enhances the model’s generalization ability and robustness by applying Mixup data augmentation technique, replaces the C3 module with the GhostBottleneck module to reduce the model’s parameters and computational complexity, and incorporates the Shuffle Attention (SA) module to improve its focus on small targets. The results show that when the improved Yolov5s-Pole model was used for detecting poles in orchards, its accuracy, recall, and mAP@50 were 0.803, 0.831, and 0.838 respectively, which increased by 0.5%, 10%, and 9.2% compared to the original Yolov5s model. Additionally, the weights, parameters, and GFLOPs of the Yolov5s-Pole model were 7.86 MB, 3,974,310, and 9, respectively. Compared to the original Yolov5s model, these represent compression rates of 42.2%, 43.4%, and 43.3%, respectively. The detection time for a single image using this model was 4.2 ms, and good robustness under different lighting conditions (dark, normal, and bright) was demonstrated. The model is suitable for deployment on agricultural UAVs’ onboard equipment, and is of great practical significance for ensuring the efficiency and flight safety of agricultural UAVs.https://www.mdpi.com/2073-4395/13/7/1705deep learningpower poleYolov5object detection |
| spellingShingle | Yali Zhang Xiaoyang Lu Wanjian Li Kangting Yan Zhenjie Mo Yubin Lan Linlin Wang Detection of Power Poles in Orchards Based on Improved Yolov5s Model Agronomy deep learning power pole Yolov5 object detection |
| title | Detection of Power Poles in Orchards Based on Improved Yolov5s Model |
| title_full | Detection of Power Poles in Orchards Based on Improved Yolov5s Model |
| title_fullStr | Detection of Power Poles in Orchards Based on Improved Yolov5s Model |
| title_full_unstemmed | Detection of Power Poles in Orchards Based on Improved Yolov5s Model |
| title_short | Detection of Power Poles in Orchards Based on Improved Yolov5s Model |
| title_sort | detection of power poles in orchards based on improved yolov5s model |
| topic | deep learning power pole Yolov5 object detection |
| url | https://www.mdpi.com/2073-4395/13/7/1705 |
| work_keys_str_mv | AT yalizhang detectionofpowerpolesinorchardsbasedonimprovedyolov5smodel AT xiaoyanglu detectionofpowerpolesinorchardsbasedonimprovedyolov5smodel AT wanjianli detectionofpowerpolesinorchardsbasedonimprovedyolov5smodel AT kangtingyan detectionofpowerpolesinorchardsbasedonimprovedyolov5smodel AT zhenjiemo detectionofpowerpolesinorchardsbasedonimprovedyolov5smodel AT yubinlan detectionofpowerpolesinorchardsbasedonimprovedyolov5smodel AT linlinwang detectionofpowerpolesinorchardsbasedonimprovedyolov5smodel |