Bending diagnosis of rice seedling lines and guidance line extraction of automatic weeding equipment in paddy field. (August 2020)
- Record Type:
- Journal Article
- Title:
- Bending diagnosis of rice seedling lines and guidance line extraction of automatic weeding equipment in paddy field. (August 2020)
- Main Title:
- Bending diagnosis of rice seedling lines and guidance line extraction of automatic weeding equipment in paddy field
- Authors:
- Liu, Fuchun
Yang, Yang
Zeng, Yiming
Liu, Zeyong - Abstract:
- Highlights: A novel dataset of rice seedling images for objection detection was established. Deep learning method was used for guidance line extraction of automatic weeding equipment.. The performance of two different neural network models was compared. SSD was proved to suit the real-time guidance line extraction better than the Faster R-CNN. Abstract: Mechanical weeding is an efficient weeding method, which is of considerable significance to the paddy field ecosystem. However, traditional mechanical weeding methods can cause seedling damages due to the bending phenomenon of the seedling lines. Introducing computer vision and control technology to traditional mechanical weeding methods can help the system diagnose the bending phenomenon and avoid crushing the seedlings. In this paper, we propose a deep-learning-based method of seedling line bending diagnosis and guidance line extraction. To prove the proposed method effective in the mechanical weeding system, we choose the Faster Region-based Convolutional Network (R-CNN) and Single Shot MultiBox Detector (SSD) as the representative models of the single-phase method and the two-phase method. With a novel dataset of rice seedling images established, we compare and analyze the confidence and real-time performance of the trained models. The experimental results show that the Faster R-CNN model is better in terms of accuracy, yet the SSD model has more advantages in the speed. Comprehensively considering the system requiringHighlights: A novel dataset of rice seedling images for objection detection was established. Deep learning method was used for guidance line extraction of automatic weeding equipment.. The performance of two different neural network models was compared. SSD was proved to suit the real-time guidance line extraction better than the Faster R-CNN. Abstract: Mechanical weeding is an efficient weeding method, which is of considerable significance to the paddy field ecosystem. However, traditional mechanical weeding methods can cause seedling damages due to the bending phenomenon of the seedling lines. Introducing computer vision and control technology to traditional mechanical weeding methods can help the system diagnose the bending phenomenon and avoid crushing the seedlings. In this paper, we propose a deep-learning-based method of seedling line bending diagnosis and guidance line extraction. To prove the proposed method effective in the mechanical weeding system, we choose the Faster Region-based Convolutional Network (R-CNN) and Single Shot MultiBox Detector (SSD) as the representative models of the single-phase method and the two-phase method. With a novel dataset of rice seedling images established, we compare and analyze the confidence and real-time performance of the trained models. The experimental results show that the Faster R-CNN model is better in terms of accuracy, yet the SSD model has more advantages in the speed. Comprehensively considering the system requiring and model performances, the SSD model is a better choice in the automatic rice avoidance system. … (more)
- Is Part Of:
- Mechanical systems and signal processing. Volume 142(2020)
- Journal:
- Mechanical systems and signal processing
- Issue:
- Volume 142(2020)
- Issue Display:
- Volume 142, Issue 2020 (2020)
- Year:
- 2020
- Volume:
- 142
- Issue:
- 2020
- Issue Sort Value:
- 2020-0142-2020-0000
- Page Start:
- Page End:
- Publication Date:
- 2020-08
- Subjects:
- Deep learning -- Object detection -- Guidance line extraction -- Automatic rice avoidance
Structural dynamics -- Periodicals
Vibration -- Periodicals
Constructions -- Dynamique -- Périodiques
Vibration -- Périodiques
Structural dynamics
Vibration
Periodicals
621 - Journal URLs:
- http://www.sciencedirect.com/science/journal/08883270 ↗
http://firstsearch.oclc.org ↗
http://firstsearch.oclc.org/journal=0888-3270;screen=info;ECOIP ↗
http://www.elsevier.com/journals ↗ - DOI:
- 10.1016/j.ymssp.2020.106791 ↗
- Languages:
- English
- ISSNs:
- 0888-3270
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 5419.760000
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 13536.xml