FBSM: Foveabox-based boundary-aware segmentation method for green apples in natural orchards

Jia, Weikuan, Wang, Zhifen, Zhao, Ruina, Ji, Ze ORCID: https://orcid.org/0000-0002-8968-9902, Yin, Xiang and Liu, Guoliang 2025. FBSM: Foveabox-based boundary-aware segmentation method for green apples in natural orchards. Expert Systems with Applications 260 , 125426. 10.1016/j.eswa.2024.125426 Item availability restricted.

PDF - Accepted Post-Print Version Restricted to Repository staff only until 22 August 2025 due to copyright restrictions. Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (1MB)

Abstract

Image segmentation of target fruits is an essential part of machine vision systems, aiming to facilitate more accurate early fruit measurement and machine harvesting in natural orchard environments. Given that instance-level pooling and down-sampling operations in conventional segmentation models often lead to the loss of detailed information, resulting in coarse partitioning masks, we endeavor to restore the boundary information of the masks. To achieve high-quality fruit segmentation with clear boundaries and refined masks, a Foveabox-based boundary-aware segmentation model (FBSM) is constructed by adding a multi-stage mask prediction head incorporating fine-grained features to the anchor-free detection model FoveaBox to realize accurate segmentation of green apple fruits. At each stage, a bi-layer fusion structure (BFS) is employed to fully fuse the fine-grained features in a double-fusion manner to guide the subsequent instance mask prediction. Finally, the boundary recovery module (BRM) is leveraged to recover the lost boundary detail information and obtain more accurate boundaries for the continuous optimization process of the fruit instance mask. Experimental results demonstrate that the proposed FBSM model achieves a mean average precision (mAP) of 60.7 % for green apple instance segmentation in unstructured natural orchard environments, surpassing traditional instance segmentation models. Moreover, it enhances base model detection accuracy by 1.3 % while striking a better balance between detection and segmentation performance.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Publisher:	Elsevier
ISSN:	0957-4174
Date of First Compliant Deposit:	12 November 2024
Date of Acceptance:	20 September 2024
Last Modified:	26 Nov 2024 16:15
URI:	https://orca.cardiff.ac.uk/id/eprint/173878

Actions (repository staff only)

Edit Item