DLNet: Accurate segmentation of green fruit in obscured environments

Liu, Jie, Zhao, Yanna, Jia, Weikuan and Ji, Ze ORCID: https://orcid.org/0000-0002-8968-9902 2022. DLNet: Accurate segmentation of green fruit in obscured environments. Journal of King Saud University - Computer and Information Sciences 34 (9) , pp. 7259-7270. 10.1016/j.jksuci.2021.09.023

PDF - Published Version Available under License Creative Commons Attribution. Download (2MB)

Abstract

o achieve more accurate recognition and segmentation of obscured fruit in natural orchard environments, DLNet model is proposed. The model is improved for the more challenging problem of segmenting overlapping fruit from homochromatic backgrounds without considering various damages. This approach is tantamount to construct the detection network RS-RFP and the segmentation network DLNet. RS-RFP extends Full Convolutional One-Stage Object Detection (FCOS). Specifically, Feature Pyramid Network (FPN) by adding Gaussian non-local attention mechanism to build Refined Pyramid Network (RFP) for refining semantic features generated continuously by Residual Network (ResNet) and FPN. The DLNet segmentation framework is composed of a dual-layer Graph Attention Networks (GAT) layer is constructed to model the image as two overlapping layers, where the top GAT layer detects the occluded object (occluded) and the bottom GAT layer infers the partially occluded instance (occlude). Display modeling of the two-layer structure occlusion relationship can naturally the boundaries between the occluded and occlude instances and consider their interactions. The experimental results show that the method outperforms earlier segmentation models and achieves metric values of 80.9% and 81.2% for Average Precision (AP) box and AP mask respectively. In a reasonable running time, it meets the requirements of accuracy and robustness for picking robots and provides a reference for segmentation of other fruits and vegetables.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Publisher:	Elsevier
ISSN:	1319-1578
Date of First Compliant Deposit:	27 October 2022
Date of Acceptance:	27 September 2021
Last Modified:	07 May 2023 04:13
URI:	https://orca.cardiff.ac.uk/id/eprint/153674

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item