Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

FCOS-LSC: A novel model for green fruit detection in a complex orchard environment

Zhao, Ruina, Guan, Yujie, Lu, Yuqi, Ji, Ze ORCID:, Yin, Xiang and Jia, Weikuan 2023. FCOS-LSC: A novel model for green fruit detection in a complex orchard environment. Plant Phenomics 5 , 0069. 10.34133/plantphenomics.0069

[thumbnail of plantphenomics.0069.pdf] PDF - Published Version
Available under License Creative Commons Attribution.

Download (3MB)


To better address the difficulties in designing green fruit recognition techniques in machine vision systems, we propose an optimized FCOS (full convolutional one-stage object detection) algorithm based on LSC attention blocks (FCOS-LSC) that are performed on level scales, spaces and channels of feature map. The method achieves efficient recognition and localization of green fruit images affected by overlapping occlusions, lighting conditions and capture angles. Specifically, the improved feature extraction network ResNet50 with added deformable convolution is used to fully extract green fruit feature information. The feature pyramid network (FPN) is employed to fully fuse low-level detail information and high-level semantic information in a cross-connected and top-down connected way. Next, the attention mechanisms are added to each of the three dimensions of scale, space (including the height and width of the feature map) and channel of the generated multi-scale feature map to improve the feature perception capability of the network. Finally, the classification and regression sub-networks of the model are applied to predict the fruit category and bounding box. In the classification branch, a new positive and negative sample selection strategy is applied to better distinguish supervised signals by designing weights in the loss function to achieve more accurate fruit detection. The proposed FCOS-LSC model has 38.65M parameters (Params), 38.72G floating point operations (FLOPs), and mean average precision (mAP) of 63.0% and 75.2% for detecting green apples and green persimmons, respectively. In summary, FCOS-LSC outperforms the state-of-the-art models in terms of precision and complexity to meet the accurate and efficient requirements of green fruit recognition by intelligent agricultural equipment. Correspondingly, FCOS-LSC can be used to improve the robustness and generalization of the green fruit detection models.

Item Type: Article
Date Type: Published Online
Status: Published
Schools: Engineering
Publisher: American Association for the Advancement of Science
ISSN: 2643-6515
Date of First Compliant Deposit: 11 July 2023
Date of Acceptance: 23 June 2023
Last Modified: 09 Aug 2023 11:19

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics