A Fast and Accurate Obstacle Segmentation Network for Guava-Harvesting Robot via Exploiting Multi-Level Features

Jiayan Yao, Qianwei Yu, Guangkun Deng, Tianjun Wu, Delin Zheng, Guichao Lin (), Lixue Zhu () and Peichen Huang
Additional contact information
Jiayan Yao: School of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Qianwei Yu: School of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Guangkun Deng: School of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Tianjun Wu: School of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Delin Zheng: School of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Guichao Lin: School of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Lixue Zhu: School of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Peichen Huang: College of Automation, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China

Sustainability, 2022, vol. 14, issue 19, 1-13

Abstract: Guava fruit is readily concealed by branches, making it difficult for picking robots to rapidly grip. For the robots to plan collision-free paths, it is crucial to segment branches and fruits. This study investigates a fast and accurate obstacle segmentation network for guava-harvesting robots. At first, to extract feature maps of different levels quickly, Mobilenetv2 is used as a backbone. Afterwards, a feature enhancement module is proposed to fuse multi-level features and recalibrate their channels. On the basis of this, a decoder module is developed, which strengthens the connection between each position in the feature maps using a self-attention network, and outputs a dense segmentation map. Experimental results show that in terms of the mean intersection over union, mean pixel accuracy, and frequency weighted intersection over union, the developed network is 1.83%, 1.60% and 0.43% higher than Mobilenetv2-deeplabv3+, and 3.77%, 2.43% and 1.70% higher than Mobilenetv2-PSPnet; our network achieved an inference speed of 45 frames per second and 35.7 billion floating-point operations per second. To sum up, this network can realize fast and accurate semantic segmentation of obstacles, and provide strong technical and theoretical support for picking robots to avoid obstacles.

Keywords: picking robot; semantic segmentation; obstacle segmentation; Mobilenetv2 (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/14/19/12899/pdf (application/pdf)
https://www.mdpi.com/2071-1050/14/19/12899/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:14:y:2022:i:19:p:12899-:d:937647

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().