An Improved YOLO Model for UAV Fuzzy Small Target Image Detection
High-altitude UAV photography presents several challenges, including blurry images, low image resolution, and small targets, which can cause low detection performance of existing object detection algorithms. Therefore, this study proposes an improved small-object detection algorithm based on the YOL...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/9/5409 |
| _version_ | 1797603009923907584 |
|---|---|
| author | Yanlong Chang Dong Li Yunlong Gao Yun Su Xiaoqiang Jia |
| author_facet | Yanlong Chang Dong Li Yunlong Gao Yun Su Xiaoqiang Jia |
| author_sort | Yanlong Chang |
| collection | DOAJ |
| description | High-altitude UAV photography presents several challenges, including blurry images, low image resolution, and small targets, which can cause low detection performance of existing object detection algorithms. Therefore, this study proposes an improved small-object detection algorithm based on the YOLOv5s computer vision model. First, the original convolution in the network framework was replaced with the SPD-Convolution module to eliminate the impact of pooling operations on feature information and to enhance the model’s capability to extract features from low-resolution and small targets. Second, a coordinate attention mechanism was added after the convolution operation to improve model detection accuracy with small targets under image blurring. Third, the nearest-neighbor interpolation in the original network upsampling was replaced with transposed convolution to increase the receptive field range of the neck and reduce detail loss. Finally, the CIoU loss function was replaced with the Alpha-IoU loss function to solve the problem of the slow convergence of gradients during training on small target images. Using the images of <i>Artemisia salina</i>, taken in Hunshandake sandy land in China, as a dataset, the experimental results demonstrated that the proposed algorithm provides significantly improved results (average precision = 80.17%, accuracy = 73.45% and recall rate = 76.97%, i.e., improvements by 14.96%, 6.24%, and 7.21%, respectively, compared with the original model) and also outperforms other detection algorithms. The detection of small objects and blurry images has been significantly improved. |
| first_indexed | 2024-03-11T04:24:15Z |
| format | Article |
| id | doaj.art-6cf73dba8df34a61ad2a8452a9802285 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T04:24:15Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-6cf73dba8df34a61ad2a8452a98022852023-11-17T22:33:36ZengMDPI AGApplied Sciences2076-34172023-04-01139540910.3390/app13095409An Improved YOLO Model for UAV Fuzzy Small Target Image DetectionYanlong Chang0Dong Li1Yunlong Gao2Yun Su3Xiaoqiang Jia4Department of Electronic Information Engineering, School of Information Engineering, Inner Mongolia University of Technology, Hohhot 010000, ChinaSchool of Information Engineering, Inner Mongolia University of Technology, Hohhot 010000, ChinaDepartment of Electronic Information Engineering, School of Information Engineering, Inner Mongolia University of Technology, Hohhot 010000, ChinaSchool of Information Engineering, Inner Mongolia University of Technology, Hohhot 010000, ChinaSchool of Information Engineering, Inner Mongolia University of Technology, Hohhot 010000, ChinaHigh-altitude UAV photography presents several challenges, including blurry images, low image resolution, and small targets, which can cause low detection performance of existing object detection algorithms. Therefore, this study proposes an improved small-object detection algorithm based on the YOLOv5s computer vision model. First, the original convolution in the network framework was replaced with the SPD-Convolution module to eliminate the impact of pooling operations on feature information and to enhance the model’s capability to extract features from low-resolution and small targets. Second, a coordinate attention mechanism was added after the convolution operation to improve model detection accuracy with small targets under image blurring. Third, the nearest-neighbor interpolation in the original network upsampling was replaced with transposed convolution to increase the receptive field range of the neck and reduce detail loss. Finally, the CIoU loss function was replaced with the Alpha-IoU loss function to solve the problem of the slow convergence of gradients during training on small target images. Using the images of <i>Artemisia salina</i>, taken in Hunshandake sandy land in China, as a dataset, the experimental results demonstrated that the proposed algorithm provides significantly improved results (average precision = 80.17%, accuracy = 73.45% and recall rate = 76.97%, i.e., improvements by 14.96%, 6.24%, and 7.21%, respectively, compared with the original model) and also outperforms other detection algorithms. The detection of small objects and blurry images has been significantly improved.https://www.mdpi.com/2076-3417/13/9/5409UAV photographysmall object detection algorithmYOLOv5sSPD-Convolution modulecoordinate attention mechanism |
| spellingShingle | Yanlong Chang Dong Li Yunlong Gao Yun Su Xiaoqiang Jia An Improved YOLO Model for UAV Fuzzy Small Target Image Detection Applied Sciences UAV photography small object detection algorithm YOLOv5s SPD-Convolution module coordinate attention mechanism |
| title | An Improved YOLO Model for UAV Fuzzy Small Target Image Detection |
| title_full | An Improved YOLO Model for UAV Fuzzy Small Target Image Detection |
| title_fullStr | An Improved YOLO Model for UAV Fuzzy Small Target Image Detection |
| title_full_unstemmed | An Improved YOLO Model for UAV Fuzzy Small Target Image Detection |
| title_short | An Improved YOLO Model for UAV Fuzzy Small Target Image Detection |
| title_sort | improved yolo model for uav fuzzy small target image detection |
| topic | UAV photography small object detection algorithm YOLOv5s SPD-Convolution module coordinate attention mechanism |
| url | https://www.mdpi.com/2076-3417/13/9/5409 |
| work_keys_str_mv | AT yanlongchang animprovedyolomodelforuavfuzzysmalltargetimagedetection AT dongli animprovedyolomodelforuavfuzzysmalltargetimagedetection AT yunlonggao animprovedyolomodelforuavfuzzysmalltargetimagedetection AT yunsu animprovedyolomodelforuavfuzzysmalltargetimagedetection AT xiaoqiangjia animprovedyolomodelforuavfuzzysmalltargetimagedetection AT yanlongchang improvedyolomodelforuavfuzzysmalltargetimagedetection AT dongli improvedyolomodelforuavfuzzysmalltargetimagedetection AT yunlonggao improvedyolomodelforuavfuzzysmalltargetimagedetection AT yunsu improvedyolomodelforuavfuzzysmalltargetimagedetection AT xiaoqiangjia improvedyolomodelforuavfuzzysmalltargetimagedetection |