MS-YOLOv7:YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography
A multi-scale UAV aerial image object detection model MS-YOLOv7 based on YOLOv7 was proposed to address the issues of a large number of objects and a high proportion of small objects that commonly exist in the Unmanned Aerial Vehicle (UAV) aerial image. The new network is developed with a multiple d...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/7/3/188 |
| _version_ | 1797612357513379840 |
|---|---|
| author | LiangLiang Zhao MinLing Zhu |
| author_facet | LiangLiang Zhao MinLing Zhu |
| author_sort | LiangLiang Zhao |
| collection | DOAJ |
| description | A multi-scale UAV aerial image object detection model MS-YOLOv7 based on YOLOv7 was proposed to address the issues of a large number of objects and a high proportion of small objects that commonly exist in the Unmanned Aerial Vehicle (UAV) aerial image. The new network is developed with a multiple detection head and a CBAM convolutional attention module to extract features at different scales. To solve the problem of high-density object detection, a YOLOv7 network architecture combined with the Swin Transformer units is proposed, and a new pyramidal pooling module, SPPFS is incorporated into the network. Finally, we incorporate the SoftNMS and the Mish activation function to improve the network’s ability to identify overlapping and occlusion objects. Various experiments on the open-source dataset VisDrone2019 reveal that our new model brings a significant performance boost compared to other state-of-the-art (SOTA) models. Compared with the YOLOv7 object detection algorithm of the baseline network, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>mAP</mi><mn>0.5</mn></mrow></semantics></math></inline-formula> of MS-YOLOv7 increased by 6.0%, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>mAP</mi><mn>0.95</mn></mrow></semantics></math></inline-formula> increased by 4.9%. Ablation experiments show that the designed modules can improve detection accuracy and visually display the detection effect in different scenarios. This experiment demonstrates the applicability of the MS-YOLOv7 for UAV aerial photograph object detection. |
| first_indexed | 2024-03-11T06:40:08Z |
| format | Article |
| id | doaj.art-b73f4713189244b1b3383fd5d55c49a3 |
| institution | Directory Open Access Journal |
| issn | 2504-446X |
| language | English |
| last_indexed | 2024-03-11T06:40:08Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj.art-b73f4713189244b1b3383fd5d55c49a32023-11-17T10:39:40ZengMDPI AGDrones2504-446X2023-03-017318810.3390/drones7030188MS-YOLOv7:YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial PhotographyLiangLiang Zhao0MinLing Zhu1Computer School, Beijing Information Science and Technology University, Beijing 100101, ChinaComputer School, Beijing Information Science and Technology University, Beijing 100101, ChinaA multi-scale UAV aerial image object detection model MS-YOLOv7 based on YOLOv7 was proposed to address the issues of a large number of objects and a high proportion of small objects that commonly exist in the Unmanned Aerial Vehicle (UAV) aerial image. The new network is developed with a multiple detection head and a CBAM convolutional attention module to extract features at different scales. To solve the problem of high-density object detection, a YOLOv7 network architecture combined with the Swin Transformer units is proposed, and a new pyramidal pooling module, SPPFS is incorporated into the network. Finally, we incorporate the SoftNMS and the Mish activation function to improve the network’s ability to identify overlapping and occlusion objects. Various experiments on the open-source dataset VisDrone2019 reveal that our new model brings a significant performance boost compared to other state-of-the-art (SOTA) models. Compared with the YOLOv7 object detection algorithm of the baseline network, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>mAP</mi><mn>0.5</mn></mrow></semantics></math></inline-formula> of MS-YOLOv7 increased by 6.0%, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>mAP</mi><mn>0.95</mn></mrow></semantics></math></inline-formula> increased by 4.9%. Ablation experiments show that the designed modules can improve detection accuracy and visually display the detection effect in different scenarios. This experiment demonstrates the applicability of the MS-YOLOv7 for UAV aerial photograph object detection.https://www.mdpi.com/2504-446X/7/3/188UAVsmall object detectionYOLOv7attention mechanismSPPFS |
| spellingShingle | LiangLiang Zhao MinLing Zhu MS-YOLOv7:YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography Drones UAV small object detection YOLOv7 attention mechanism SPPFS |
| title | MS-YOLOv7:YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography |
| title_full | MS-YOLOv7:YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography |
| title_fullStr | MS-YOLOv7:YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography |
| title_full_unstemmed | MS-YOLOv7:YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography |
| title_short | MS-YOLOv7:YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography |
| title_sort | ms yolov7 yolov7 based on multi scale for object detection on uav aerial photography |
| topic | UAV small object detection YOLOv7 attention mechanism SPPFS |
| url | https://www.mdpi.com/2504-446X/7/3/188 |
| work_keys_str_mv | AT liangliangzhao msyolov7yolov7basedonmultiscaleforobjectdetectiononuavaerialphotography AT minlingzhu msyolov7yolov7basedonmultiscaleforobjectdetectiononuavaerialphotography |