Pine Cone Detection Using Boundary Equilibrium Generative Adversarial Networks and Improved YOLOv3 Model
The real-time detection of pine cones in Korean pine forests is not only the data basis for the mechanized picking of pine cones, but also one of the important methods for evaluating the yield of Korean pine forests. In recent years, there has been a certain number of detection accuracy for image pr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/16/4430 |
| _version_ | 1827710942639554560 |
|---|---|
| author | Ze Luo Huiling Yu Yizhuo Zhang |
| author_facet | Ze Luo Huiling Yu Yizhuo Zhang |
| author_sort | Ze Luo |
| collection | DOAJ |
| description | The real-time detection of pine cones in Korean pine forests is not only the data basis for the mechanized picking of pine cones, but also one of the important methods for evaluating the yield of Korean pine forests. In recent years, there has been a certain number of detection accuracy for image processing of fruits in trees using deep-learning methods, but the overall performance of these methods has not been satisfactory, and they have never been used in the detection of pine cones. In this paper, a pine cone detection method based on Boundary Equilibrium Generative Adversarial Networks (BEGAN) and You Only Look Once (YOLO) v3 mode is proposed to solve the problems of insufficient data set, inaccurate detection result and slow detection speed. First, we use traditional image augmentation technology and generative adversarial network BEGAN to implement data augmentation. Second, we introduced a densely connected network (DenseNet) structure in the backbone network of YOLOv3. Third, we expanded the detection scale of YOLOv3, and optimized the loss function of YOLOv3 using the Distance-IoU (DIoU) algorithm. Finally, we conducted a comparative experiment. The experimental results show that the performance of the model can be effectively improved by using BEGAN for data augmentation. Under same conditions, the improved YOLOv3 model is better than the Single Shot MultiBox Detector (SSD), the faster-regions with convolutional neural network (Faster R-CNN) and the original YOLOv3 model. The detection accuracy reaches 95.3%, and the detection efficiency is 37.8% higher than that of the original YOLOv3. |
| first_indexed | 2024-03-10T17:46:54Z |
| format | Article |
| id | doaj.art-67de61e033224c3f9387a23223759236 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T17:46:54Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-67de61e033224c3f9387a232237592362023-11-20T09:30:41ZengMDPI AGSensors1424-82202020-08-012016443010.3390/s20164430Pine Cone Detection Using Boundary Equilibrium Generative Adversarial Networks and Improved YOLOv3 ModelZe Luo0Huiling Yu1Yizhuo Zhang2College of Mechanical and Electrical Engineering, Northeast Forestry University, No.26 Hexing Road, Harbin 150040, ChinaCollege of Information and Computer Engineering, Northeast Forestry University, No.26 Hexing Road, Harbin 150040, ChinaCollege of Mechanical and Electrical Engineering, Northeast Forestry University, No.26 Hexing Road, Harbin 150040, ChinaThe real-time detection of pine cones in Korean pine forests is not only the data basis for the mechanized picking of pine cones, but also one of the important methods for evaluating the yield of Korean pine forests. In recent years, there has been a certain number of detection accuracy for image processing of fruits in trees using deep-learning methods, but the overall performance of these methods has not been satisfactory, and they have never been used in the detection of pine cones. In this paper, a pine cone detection method based on Boundary Equilibrium Generative Adversarial Networks (BEGAN) and You Only Look Once (YOLO) v3 mode is proposed to solve the problems of insufficient data set, inaccurate detection result and slow detection speed. First, we use traditional image augmentation technology and generative adversarial network BEGAN to implement data augmentation. Second, we introduced a densely connected network (DenseNet) structure in the backbone network of YOLOv3. Third, we expanded the detection scale of YOLOv3, and optimized the loss function of YOLOv3 using the Distance-IoU (DIoU) algorithm. Finally, we conducted a comparative experiment. The experimental results show that the performance of the model can be effectively improved by using BEGAN for data augmentation. Under same conditions, the improved YOLOv3 model is better than the Single Shot MultiBox Detector (SSD), the faster-regions with convolutional neural network (Faster R-CNN) and the original YOLOv3 model. The detection accuracy reaches 95.3%, and the detection efficiency is 37.8% higher than that of the original YOLOv3.https://www.mdpi.com/1424-8220/20/16/4430object detectionpine conedata augmentationBEGANYOLOv3 |
| spellingShingle | Ze Luo Huiling Yu Yizhuo Zhang Pine Cone Detection Using Boundary Equilibrium Generative Adversarial Networks and Improved YOLOv3 Model Sensors object detection pine cone data augmentation BEGAN YOLOv3 |
| title | Pine Cone Detection Using Boundary Equilibrium Generative Adversarial Networks and Improved YOLOv3 Model |
| title_full | Pine Cone Detection Using Boundary Equilibrium Generative Adversarial Networks and Improved YOLOv3 Model |
| title_fullStr | Pine Cone Detection Using Boundary Equilibrium Generative Adversarial Networks and Improved YOLOv3 Model |
| title_full_unstemmed | Pine Cone Detection Using Boundary Equilibrium Generative Adversarial Networks and Improved YOLOv3 Model |
| title_short | Pine Cone Detection Using Boundary Equilibrium Generative Adversarial Networks and Improved YOLOv3 Model |
| title_sort | pine cone detection using boundary equilibrium generative adversarial networks and improved yolov3 model |
| topic | object detection pine cone data augmentation BEGAN YOLOv3 |
| url | https://www.mdpi.com/1424-8220/20/16/4430 |
| work_keys_str_mv | AT zeluo pineconedetectionusingboundaryequilibriumgenerativeadversarialnetworksandimprovedyolov3model AT huilingyu pineconedetectionusingboundaryequilibriumgenerativeadversarialnetworksandimprovedyolov3model AT yizhuozhang pineconedetectionusingboundaryequilibriumgenerativeadversarialnetworksandimprovedyolov3model |