UN-YOLOv5s: A UAV-Based Aerial Photography Detection Algorithm
With the progress of science and technology, artificial intelligence is widely used in various disciplines and has produced amazing results. The research of the target detection algorithm has significantly improved the performance and role of unmanned aerial vehicles (UAVs), and plays an irreplaceab...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/13/5907 |
| _version_ | 1797590885067653120 |
|---|---|
| author | Junmei Guo Xingchen Liu Lingyun Bi Haiying Liu Haitong Lou |
| author_facet | Junmei Guo Xingchen Liu Lingyun Bi Haiying Liu Haitong Lou |
| author_sort | Junmei Guo |
| collection | DOAJ |
| description | With the progress of science and technology, artificial intelligence is widely used in various disciplines and has produced amazing results. The research of the target detection algorithm has significantly improved the performance and role of unmanned aerial vehicles (UAVs), and plays an irreplaceable role in preventing forest fires, evacuating crowded people, surveying and rescuing explorers. At this stage, the target detection algorithm deployed in UAVs has been applied to production and life, but making the detection accuracy higher and better adaptability is still the motivation for researchers to continue to study. In aerial images, due to the high shooting height, small size, low resolution and few features, it is difficult to be detected by conventional target detection algorithms. In this paper, the UN-YOLOv5s algorithm can solve the difficult problem of small target detection excellently. The more accurate small target detection (MASD) mechanism is used to greatly improve the detection accuracy of small and medium targets, The multi-scale feature fusion (MCF) path is combined to fuse the semantic information and location information of the image to improve the expression ability of the novel model. The new convolution SimAM residual (CSR) module is introduced to make the network more stable and focused. On the VisDrone dataset, the mean average precision (mAP) of UAV necessity you only look once v5s(UN-YOLOv5s) is 8.4% higher than that of the original algorithm. Compared with the same version, YOLOv5l, the mAP is increased by 2.2%, and the Giga Floating-point Operations Per Second (GFLOPs) is reduced by 65.3%. Compared with the same series of YOLOv3, the mAP is increased by 1.8%, and GFLOPs is reduced by 75.8%. Compared with the same series of YOLOv8s, the detection accuracy of the mAP is improved by 1.1%. |
| first_indexed | 2024-03-11T01:29:49Z |
| format | Article |
| id | doaj.art-e5cd1eacfbc74165aad4c51690b1ce24 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:29:49Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e5cd1eacfbc74165aad4c51690b1ce242023-11-18T17:28:32ZengMDPI AGSensors1424-82202023-06-012313590710.3390/s23135907UN-YOLOv5s: A UAV-Based Aerial Photography Detection AlgorithmJunmei Guo0Xingchen Liu1Lingyun Bi2Haiying Liu3Haitong Lou4The School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaThe School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaThe School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaThe School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaThe School of Information and Automation Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaWith the progress of science and technology, artificial intelligence is widely used in various disciplines and has produced amazing results. The research of the target detection algorithm has significantly improved the performance and role of unmanned aerial vehicles (UAVs), and plays an irreplaceable role in preventing forest fires, evacuating crowded people, surveying and rescuing explorers. At this stage, the target detection algorithm deployed in UAVs has been applied to production and life, but making the detection accuracy higher and better adaptability is still the motivation for researchers to continue to study. In aerial images, due to the high shooting height, small size, low resolution and few features, it is difficult to be detected by conventional target detection algorithms. In this paper, the UN-YOLOv5s algorithm can solve the difficult problem of small target detection excellently. The more accurate small target detection (MASD) mechanism is used to greatly improve the detection accuracy of small and medium targets, The multi-scale feature fusion (MCF) path is combined to fuse the semantic information and location information of the image to improve the expression ability of the novel model. The new convolution SimAM residual (CSR) module is introduced to make the network more stable and focused. On the VisDrone dataset, the mean average precision (mAP) of UAV necessity you only look once v5s(UN-YOLOv5s) is 8.4% higher than that of the original algorithm. Compared with the same version, YOLOv5l, the mAP is increased by 2.2%, and the Giga Floating-point Operations Per Second (GFLOPs) is reduced by 65.3%. Compared with the same series of YOLOv3, the mAP is increased by 1.8%, and GFLOPs is reduced by 75.8%. Compared with the same series of YOLOv8s, the detection accuracy of the mAP is improved by 1.1%.https://www.mdpi.com/1424-8220/23/13/5907YOLOv5artificial intelligencetarget detectionaerial image |
| spellingShingle | Junmei Guo Xingchen Liu Lingyun Bi Haiying Liu Haitong Lou UN-YOLOv5s: A UAV-Based Aerial Photography Detection Algorithm Sensors YOLOv5 artificial intelligence target detection aerial image |
| title | UN-YOLOv5s: A UAV-Based Aerial Photography Detection Algorithm |
| title_full | UN-YOLOv5s: A UAV-Based Aerial Photography Detection Algorithm |
| title_fullStr | UN-YOLOv5s: A UAV-Based Aerial Photography Detection Algorithm |
| title_full_unstemmed | UN-YOLOv5s: A UAV-Based Aerial Photography Detection Algorithm |
| title_short | UN-YOLOv5s: A UAV-Based Aerial Photography Detection Algorithm |
| title_sort | un yolov5s a uav based aerial photography detection algorithm |
| topic | YOLOv5 artificial intelligence target detection aerial image |
| url | https://www.mdpi.com/1424-8220/23/13/5907 |
| work_keys_str_mv | AT junmeiguo unyolov5sauavbasedaerialphotographydetectionalgorithm AT xingchenliu unyolov5sauavbasedaerialphotographydetectionalgorithm AT lingyunbi unyolov5sauavbasedaerialphotographydetectionalgorithm AT haiyingliu unyolov5sauavbasedaerialphotographydetectionalgorithm AT haitonglou unyolov5sauavbasedaerialphotographydetectionalgorithm |