Proceedings of the 2023 4th International Conference on Artificial Intelligence and Education (ICAIE 2023)

<Previous Article In Volume
Next Article In Volume>

Location of Mulberry Leaf Picking Points Based on Improved Mask RCNN

Authors
Siyong Zeng1, Yingchun Hu2, *, Shanghao Qin1
1College of Electrical Engineering, Guangxi Normal University, Guilin, 541004, China
2Teachers College for Vocational and Technical Education, Guangxi Normal University, Guilin, 541004, China
*Corresponding author. Email: 148405822@qq.com
Corresponding Author
Yingchun Hu
Available Online 22 September 2023.
DOI
10.2991/978-94-6463-242-2_42How to use a DOI?
Keywords
Picking points; Mask RCNN; Path enhancement; Mulberry leaf node area; Skeletonization
Abstract

In response to the current situation of high labor cost and low efficiency in mulberry leaf picking in China, and the lack of information on the location of mulberry leaf picking points in the intelligent development process of mulberry leaf picking, a mulberry leaf picking point positioning method based on improved Mask RCNN is proposed. Firstly, we make the following improvements to Mask RCNN: 1) replace the ResNet network in the original Mask RCNN with ResNeXt network; 2) Add a bottom-up fusion path to the FPN network and propose a multi-scale region recommendation network; 3) design convolutional kernels of different sizes for different feature layers. Then we used the improved Mask RCNN to segment the node area of mulberry leaf, and used a thinning algorithm to skeleton the node area and located the corresponding points as picking points. The results showed that the average accuracy and F1 index of the proposed method for identifying mulberry leaf node areas are 89.1% and 75.7%, respectively, which are 2.8 and 3.5 percentage points higher than the original Mask RCNN network, which providing a theoretical basis for intelligent mulberry leaf picking machines.

Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2023 4th International Conference on Artificial Intelligence and Education (ICAIE 2023)
Series
Atlantis Highlights in Computer Sciences
Publication Date
22 September 2023
ISBN
10.2991/978-94-6463-242-2_42
ISSN
2589-4900
DOI
10.2991/978-94-6463-242-2_42How to use a DOI?
Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Siyong Zeng
AU  - Yingchun Hu
AU  - Shanghao Qin
PY  - 2023
DA  - 2023/09/22
TI  - Location of Mulberry Leaf Picking Points Based on Improved Mask RCNN
BT  - Proceedings of the 2023 4th International Conference on Artificial Intelligence and Education (ICAIE 2023)
PB  - Atlantis Press
SP  - 337
EP  - 344
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-242-2_42
DO  - 10.2991/978-94-6463-242-2_42
ID  - Zeng2023
ER  -