A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5
Deep-learning-based object detection algorithms have significantly improved the performance of wheat spike detection. However, UAV images crowned with small-sized, highly dense, and overlapping spikes cause the accuracy to decrease for detection. This paper proposes an improved YOLOv5 (You Look Only...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/16/3095 |
| _version_ | 1797522261811396608 |
|---|---|
| author | Jianqing Zhao Xiaohu Zhang Jiawei Yan Xiaolei Qiu Xia Yao Yongchao Tian Yan Zhu Weixing Cao |
| author_facet | Jianqing Zhao Xiaohu Zhang Jiawei Yan Xiaolei Qiu Xia Yao Yongchao Tian Yan Zhu Weixing Cao |
| author_sort | Jianqing Zhao |
| collection | DOAJ |
| description | Deep-learning-based object detection algorithms have significantly improved the performance of wheat spike detection. However, UAV images crowned with small-sized, highly dense, and overlapping spikes cause the accuracy to decrease for detection. This paper proposes an improved YOLOv5 (You Look Only Once)-based method to detect wheat spikes accurately in UAV images and solve spike error detection and miss detection caused by occlusion conditions. The proposed method introduces data cleaning and data augmentation to improve the generalization ability of the detection network. The network is rebuilt by adding a microscale detection layer, setting prior anchor boxes, and adapting the confidence loss function of the detection layer based on the IoU (Intersection over Union). These refinements improve the feature extraction for small-sized wheat spikes and lead to better detection accuracy. With the confidence weights, the detection boxes in multiresolution images are fused to increase the accuracy under occlusion conditions. The result shows that the proposed method is better than the existing object detection algorithms, such as Faster RCNN, Single Shot MultiBox Detector (SSD), RetinaNet, and standard YOLOv5. The average accuracy (AP) of wheat spike detection in UAV images is 94.1%, which is 10.8% higher than the standard YOLOv5. Thus, the proposed method is a practical way to handle the spike detection in complex field scenarios and provide technical references for field-level wheat phenotype monitoring. |
| first_indexed | 2024-03-10T08:25:55Z |
| format | Article |
| id | doaj.art-f1c4d53314d44848a14c2419ba6fa457 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T08:25:55Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f1c4d53314d44848a14c2419ba6fa4572023-11-22T09:31:46ZengMDPI AGRemote Sensing2072-42922021-08-011316309510.3390/rs13163095A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5Jianqing Zhao0Xiaohu Zhang1Jiawei Yan2Xiaolei Qiu3Xia Yao4Yongchao Tian5Yan Zhu6Weixing Cao7National Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaKey Laboratory for Crop System Analysis and Decision Making, Ministry of Agriculture and Rural Affairs, Nanjing 210095, ChinaNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaNational Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University, Nanjing 210095, ChinaDeep-learning-based object detection algorithms have significantly improved the performance of wheat spike detection. However, UAV images crowned with small-sized, highly dense, and overlapping spikes cause the accuracy to decrease for detection. This paper proposes an improved YOLOv5 (You Look Only Once)-based method to detect wheat spikes accurately in UAV images and solve spike error detection and miss detection caused by occlusion conditions. The proposed method introduces data cleaning and data augmentation to improve the generalization ability of the detection network. The network is rebuilt by adding a microscale detection layer, setting prior anchor boxes, and adapting the confidence loss function of the detection layer based on the IoU (Intersection over Union). These refinements improve the feature extraction for small-sized wheat spikes and lead to better detection accuracy. With the confidence weights, the detection boxes in multiresolution images are fused to increase the accuracy under occlusion conditions. The result shows that the proposed method is better than the existing object detection algorithms, such as Faster RCNN, Single Shot MultiBox Detector (SSD), RetinaNet, and standard YOLOv5. The average accuracy (AP) of wheat spike detection in UAV images is 94.1%, which is 10.8% higher than the standard YOLOv5. Thus, the proposed method is a practical way to handle the spike detection in complex field scenarios and provide technical references for field-level wheat phenotype monitoring.https://www.mdpi.com/2072-4292/13/16/3095wheat spike detectionunmanned aerial vehicledeep learningYOLOv5 |
| spellingShingle | Jianqing Zhao Xiaohu Zhang Jiawei Yan Xiaolei Qiu Xia Yao Yongchao Tian Yan Zhu Weixing Cao A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5 Remote Sensing wheat spike detection unmanned aerial vehicle deep learning YOLOv5 |
| title | A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5 |
| title_full | A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5 |
| title_fullStr | A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5 |
| title_full_unstemmed | A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5 |
| title_short | A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5 |
| title_sort | wheat spike detection method in uav images based on improved yolov5 |
| topic | wheat spike detection unmanned aerial vehicle deep learning YOLOv5 |
| url | https://www.mdpi.com/2072-4292/13/16/3095 |
| work_keys_str_mv | AT jianqingzhao awheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT xiaohuzhang awheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT jiaweiyan awheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT xiaoleiqiu awheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT xiayao awheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT yongchaotian awheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT yanzhu awheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT weixingcao awheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT jianqingzhao wheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT xiaohuzhang wheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT jiaweiyan wheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT xiaoleiqiu wheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT xiayao wheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT yongchaotian wheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT yanzhu wheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 AT weixingcao wheatspikedetectionmethodinuavimagesbasedonimprovedyolov5 |