Shatian pomelo detection in orchards is essential for yield estimation and lean production, but models tuned to ideal datasets often degrade in practice due to device-dependent tone shifts, illumination changes, large scale variation, and frequent occlusion. We introduce STP-AgriData, a multi-scenario dataset combining real-orchard imagery with curated web images, and apply contrast/brightness augmentations to emulate unstable lighting. To better address scale and occlusion, we propose REAS-Det, featuring Global-Selective Visibility Convolution (GSV-Conv) that expands the visible feature space under global semantic guidance while retaining efficient spatial aggregation, plus C3RFEM, MultiSEAM, and Soft-NMS for refined separation and localization. On STP-AgriData, REAS-Det achieves 86.5% precision, 77.2% recall, 84.3% mAP@0.50, and 53.6% mAP@0.50:0.95, outperforming recent detectors and improving robustness in real orchard environments. The source code is available at: https://github.com/Genk641/REAS-Det.
@article{arxiv.2510.09948,
title = {A Multi-Strategy Framework for Enhancing Shatian Pomelo Detection in Real-World Orchards},
author = {Pan Wang and Yihao Hu and Xiaodong Bai and Jingchu Yang and Leyi Zhou and Aiping Yang and Xiangxiang Li and Meiping Ding and Jianguo Yao},
journal= {arXiv preprint arXiv:2510.09948},
year = {2026}
}