A Small Object Detection Method for Drone-Captured Images Based on Improved YOLOv7
Due to the broad usage and widespread popularity of drones, the demand for a more accurate object detection algorithm for images captured by drone platforms has become increasingly urgent. This article addresses this issue by first analyzing the unique characteristics of datasets related to drones....
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/6/1002 |
| _version_ | 1797239446362390528 |
|---|---|
| author | Dewei Zhao Faming Shao Qiang Liu Li Yang Heng Zhang Zihan Zhang |
| author_facet | Dewei Zhao Faming Shao Qiang Liu Li Yang Heng Zhang Zihan Zhang |
| author_sort | Dewei Zhao |
| collection | DOAJ |
| description | Due to the broad usage and widespread popularity of drones, the demand for a more accurate object detection algorithm for images captured by drone platforms has become increasingly urgent. This article addresses this issue by first analyzing the unique characteristics of datasets related to drones. We then select the widely used YOLOv7 algorithm as the foundation and conduct a comprehensive analysis of its limitations, proposing a targeted solution. In order to enhance the network’s ability to extract features from small objects, we introduce non-strided convolution modules and integrate modules that utilize attention mechanism principles into the baseline network. Additionally, we improve the semantic information expression for small targets by optimizing the feature fusion process in the network. During training, we adopt the latest Lion optimizer and MPDIoU loss to further boost the overall performance of the network. The improved network achieves impressive results, with mAP<sub>50</sub> scores of 56.8% and 94.6% on the VisDrone2019 and NWPU VHR-10 datasets, respectively, particularly in detecting small objects. |
| first_indexed | 2024-04-24T17:51:40Z |
| format | Article |
| id | doaj.art-61ce244ce09642e397171ad74f8d6469 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-24T17:51:40Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-61ce244ce09642e397171ad74f8d64692024-03-27T14:02:35ZengMDPI AGRemote Sensing2072-42922024-03-01166100210.3390/rs16061002A Small Object Detection Method for Drone-Captured Images Based on Improved YOLOv7Dewei Zhao0Faming Shao1Qiang Liu2Li Yang3Heng Zhang4Zihan Zhang5College of Field Engineering, Army Engineering University of PLA, Nanjing 210007, ChinaCollege of Field Engineering, Army Engineering University of PLA, Nanjing 210007, ChinaCollege of Field Engineering, Army Engineering University of PLA, Nanjing 210007, ChinaCollege of Field Engineering, Army Engineering University of PLA, Nanjing 210007, ChinaCollege of Field Engineering, Army Engineering University of PLA, Nanjing 210007, ChinaCollege of Field Engineering, Army Engineering University of PLA, Nanjing 210007, ChinaDue to the broad usage and widespread popularity of drones, the demand for a more accurate object detection algorithm for images captured by drone platforms has become increasingly urgent. This article addresses this issue by first analyzing the unique characteristics of datasets related to drones. We then select the widely used YOLOv7 algorithm as the foundation and conduct a comprehensive analysis of its limitations, proposing a targeted solution. In order to enhance the network’s ability to extract features from small objects, we introduce non-strided convolution modules and integrate modules that utilize attention mechanism principles into the baseline network. Additionally, we improve the semantic information expression for small targets by optimizing the feature fusion process in the network. During training, we adopt the latest Lion optimizer and MPDIoU loss to further boost the overall performance of the network. The improved network achieves impressive results, with mAP<sub>50</sub> scores of 56.8% and 94.6% on the VisDrone2019 and NWPU VHR-10 datasets, respectively, particularly in detecting small objects.https://www.mdpi.com/2072-4292/16/6/1002object detectiondroneimproved YOLOv7 |
| spellingShingle | Dewei Zhao Faming Shao Qiang Liu Li Yang Heng Zhang Zihan Zhang A Small Object Detection Method for Drone-Captured Images Based on Improved YOLOv7 Remote Sensing object detection drone improved YOLOv7 |
| title | A Small Object Detection Method for Drone-Captured Images Based on Improved YOLOv7 |
| title_full | A Small Object Detection Method for Drone-Captured Images Based on Improved YOLOv7 |
| title_fullStr | A Small Object Detection Method for Drone-Captured Images Based on Improved YOLOv7 |
| title_full_unstemmed | A Small Object Detection Method for Drone-Captured Images Based on Improved YOLOv7 |
| title_short | A Small Object Detection Method for Drone-Captured Images Based on Improved YOLOv7 |
| title_sort | small object detection method for drone captured images based on improved yolov7 |
| topic | object detection drone improved YOLOv7 |
| url | https://www.mdpi.com/2072-4292/16/6/1002 |
| work_keys_str_mv | AT deweizhao asmallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT famingshao asmallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT qiangliu asmallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT liyang asmallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT hengzhang asmallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT zihanzhang asmallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT deweizhao smallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT famingshao smallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT qiangliu smallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT liyang smallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT hengzhang smallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 AT zihanzhang smallobjectdetectionmethodfordronecapturedimagesbasedonimprovedyolov7 |