Precision Detection of Dense Litchi Fruit in UAV Images Based on Improved YOLOv5 Model
The utilization of unmanned aerial vehicles (UAVs) for the precise and convenient detection of litchi fruits, in order to estimate yields and perform statistical analysis, holds significant value in the complex and variable litchi orchard environment. Currently, litchi yield estimation relies predom...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/16/4017 |
| _version_ | 1827728766008295424 |
|---|---|
| author | Zhangjun Xiong Lele Wang Yingjie Zhao Yubin Lan |
| author_facet | Zhangjun Xiong Lele Wang Yingjie Zhao Yubin Lan |
| author_sort | Zhangjun Xiong |
| collection | DOAJ |
| description | The utilization of unmanned aerial vehicles (UAVs) for the precise and convenient detection of litchi fruits, in order to estimate yields and perform statistical analysis, holds significant value in the complex and variable litchi orchard environment. Currently, litchi yield estimation relies predominantly on manual rough counts, which often result in discrepancies between the estimated values and the actual production figures. This study proposes a large-scene and high-density litchi fruit recognition method based on the improved You Only Look Once version 5 (YOLOv5) model. The main objective is to enhance the accuracy and efficiency of yield estimation in natural orchards. First, the PANet in the original YOLOv5 model is replaced with the improved Bi-directional Feature Pyramid Network (BiFPN) to enhance the model’s cross-scale feature fusion. Second, the P2 feature layer is fused into the BiFPN to enhance the learning capability of the model for high-resolution features. After that, the Normalized Gaussian Wasserstein Distance (NWD) metric is introduced into the regression loss function to enhance the learning ability of the model for litchi tiny targets. Finally, the Slicing Aided Hyper Inference (SAHI) is used to enhance the detection of tiny targets without increasing the model’s parameters or computational memory. The experimental results show that the overall <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> value of the improved YOLOv5 model has been effectively increased by 22%, compared to the original YOLOv5 model’s <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> value of 50.6%. Specifically, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><msub><mi>P</mi><mi>s</mi></msub></mrow></semantics></math></inline-formula> value for detecting small targets has increased from 27.8% to 57.3%. The model size is only 3.6% larger than the original YOLOv5 model. Through ablation and comparative experiments, our method has successfully improved accuracy without compromising the model size and inference speed. Therefore, the proposed method in this paper holds practical applicability for detecting litchi fruits in orchards. It can serve as a valuable tool for providing guidance and suggestions for litchi yield estimation and subsequent harvesting processes. In future research, optimization can be continued for the small target detection problem, while it can be extended to study the small target tracking problem in dense scenarios, which is of great significance for litchi yield estimation. |
| first_indexed | 2024-03-10T23:36:34Z |
| format | Article |
| id | doaj.art-53fad834ee354c5b9227268b057c985d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:36:34Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-53fad834ee354c5b9227268b057c985d2023-11-19T02:53:24ZengMDPI AGRemote Sensing2072-42922023-08-011516401710.3390/rs15164017Precision Detection of Dense Litchi Fruit in UAV Images Based on Improved YOLOv5 ModelZhangjun Xiong0Lele Wang1Yingjie Zhao2Yubin Lan3College of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaThe utilization of unmanned aerial vehicles (UAVs) for the precise and convenient detection of litchi fruits, in order to estimate yields and perform statistical analysis, holds significant value in the complex and variable litchi orchard environment. Currently, litchi yield estimation relies predominantly on manual rough counts, which often result in discrepancies between the estimated values and the actual production figures. This study proposes a large-scene and high-density litchi fruit recognition method based on the improved You Only Look Once version 5 (YOLOv5) model. The main objective is to enhance the accuracy and efficiency of yield estimation in natural orchards. First, the PANet in the original YOLOv5 model is replaced with the improved Bi-directional Feature Pyramid Network (BiFPN) to enhance the model’s cross-scale feature fusion. Second, the P2 feature layer is fused into the BiFPN to enhance the learning capability of the model for high-resolution features. After that, the Normalized Gaussian Wasserstein Distance (NWD) metric is introduced into the regression loss function to enhance the learning ability of the model for litchi tiny targets. Finally, the Slicing Aided Hyper Inference (SAHI) is used to enhance the detection of tiny targets without increasing the model’s parameters or computational memory. The experimental results show that the overall <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> value of the improved YOLOv5 model has been effectively increased by 22%, compared to the original YOLOv5 model’s <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> value of 50.6%. Specifically, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><msub><mi>P</mi><mi>s</mi></msub></mrow></semantics></math></inline-formula> value for detecting small targets has increased from 27.8% to 57.3%. The model size is only 3.6% larger than the original YOLOv5 model. Through ablation and comparative experiments, our method has successfully improved accuracy without compromising the model size and inference speed. Therefore, the proposed method in this paper holds practical applicability for detecting litchi fruits in orchards. It can serve as a valuable tool for providing guidance and suggestions for litchi yield estimation and subsequent harvesting processes. In future research, optimization can be continued for the small target detection problem, while it can be extended to study the small target tracking problem in dense scenarios, which is of great significance for litchi yield estimation.https://www.mdpi.com/2072-4292/15/16/4017UAVtiny object detectionlitchiYOLOv5SAHI |
| spellingShingle | Zhangjun Xiong Lele Wang Yingjie Zhao Yubin Lan Precision Detection of Dense Litchi Fruit in UAV Images Based on Improved YOLOv5 Model Remote Sensing UAV tiny object detection litchi YOLOv5 SAHI |
| title | Precision Detection of Dense Litchi Fruit in UAV Images Based on Improved YOLOv5 Model |
| title_full | Precision Detection of Dense Litchi Fruit in UAV Images Based on Improved YOLOv5 Model |
| title_fullStr | Precision Detection of Dense Litchi Fruit in UAV Images Based on Improved YOLOv5 Model |
| title_full_unstemmed | Precision Detection of Dense Litchi Fruit in UAV Images Based on Improved YOLOv5 Model |
| title_short | Precision Detection of Dense Litchi Fruit in UAV Images Based on Improved YOLOv5 Model |
| title_sort | precision detection of dense litchi fruit in uav images based on improved yolov5 model |
| topic | UAV tiny object detection litchi YOLOv5 SAHI |
| url | https://www.mdpi.com/2072-4292/15/16/4017 |
| work_keys_str_mv | AT zhangjunxiong precisiondetectionofdenselitchifruitinuavimagesbasedonimprovedyolov5model AT lelewang precisiondetectionofdenselitchifruitinuavimagesbasedonimprovedyolov5model AT yingjiezhao precisiondetectionofdenselitchifruitinuavimagesbasedonimprovedyolov5model AT yubinlan precisiondetectionofdenselitchifruitinuavimagesbasedonimprovedyolov5model |