FCNet: A Transformer-Based Context-Aware Segmentation Framework for Detecting Camouflaged Fruits in Orchard Environments

Fruit segmentation is an essential task due to its importance in accurate disease pre-vention, yield estimation, and automated harvesting. However, accurate object seg-mentation in agricultural environments remains challenging due to visual complexities such as background clutter, occlusion, small object size, and color-texture similarities that lead to camouflaging. Traditional methods often struggle to detect partially oc-cluded or visually blended fruits, leading to poor detection performance. In this study, we propose a context-aware segmentation framework designed for orchard-level mango fruit detection. We integrate multiscale feature extraction based on PVTv2 ar-chitecture, a feature enhancement module using Atrous Spatial Pyramid Pooling (ASPP) and attention techniques, and a novel refinement mechanism employing a po-sition-based layer normalization (PLN). We conducted a comparative study against established segmentation models, employing both quantitative and qualitative evalu-ations. Results demonstrate the superior performance of our model across all metrics. An ablation study validated the contributions of the enhancement and refinement modules, with the former yielding performance gains of 2.43%, 3.10%, 5.65%, 4.19%, and 4.35% in S-measure, mean E-measure, weighted F-measure, mean F-measure, and IoU, respectively, and the latter achieving improvements of 2.07%, 1.93%, 6.85%, 4.84%, and 2.73%, in the said metrics.