A Multi-Strategy Framework for Enhancing Shatian Pomelo Detection in Real-World Orchards

2025-10-10

AI Summary

To address low detection accuracy of pomelos in real orchards—caused by illumination variations, scale diversity, occlusion, and heterogeneous imaging devices—this paper proposes a multi-strategy robust detection framework. First, we construct STP-AgriData, a multi-scenario agricultural dataset integrating field-collected and web-crawled pomelo images. Second, we design REAS-Det, a novel detector incorporating RFAConv (receptive-field-adaptive convolution), C3RFEM (a lightweight feature enhancement module), and MultiSEAM (a multi-scale self-attention mechanism), augmented with soft Non-Maximum Suppression to improve localization and duplicate removal under dense and occluded conditions. Experiments demonstrate that REAS-Det achieves 82.8% mAP@.50 and 53.3% mAP@.50:.95 on challenging field scenarios—substantially outperforming mainstream detectors including YOLOv5 and YOLOv8. This work establishes a transferable technical paradigm for intelligent fruit perception in orchard environments.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Object Detection & Categorization
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

As a specialty agricultural product with a large market scale, Shatian pomelo necessitates the adoption of automated detection to ensure accurate quantity and meet commercial demands for lean production. Existing research often involves specialized networks tailored for specific theoretical or dataset scenarios, but these methods tend to degrade performance in real-world. Through analysis of factors in this issue, this study identifies four key challenges that affect the accuracy of Shatian pomelo detection: imaging devices, lighting conditions, object scale variation, and occlusion. To mitigate these challenges, a multi-strategy framework is proposed in this paper. Firstly, to effectively solve tone variation introduced by diverse imaging devices and complex orchard environments, we utilize a multi-scenario dataset, STP-AgriData, which is constructed by integrating real orchard images with internet-sourced data. Secondly, to simulate the inconsistent illumination conditions, specific data augmentations such as adjusting contrast and changing brightness, are applied to the above dataset. Thirdly, to address the issues of object scale variation and occlusion in fruit detection, an REAS-Det network is designed in this paper. For scale variation, RFAConv and C3RFEM modules are designed to expand and enhance the receptive fields. For occlusion variation, a multi-scale, multi-head feature selection structure (MultiSEAM) and soft-NMS are introduced to enhance the handling of occlusion issues to improve detection accuracy. The results of these experiments achieved a precision(P) of 87.6%, a recall (R) of 74.9%, a mAP@.50 of 82.8%, and a mAP@.50:.95 of 53.3%. Our proposed network demonstrates superior performance compared to other state-of-the-art detection methods.

Problem

• Detecting Shatian pomelos in real-world orchards with accuracy
• Addressing challenges from imaging devices and lighting conditions
• Solving object scale variation and occlusion in fruit detection

Innovation

• Multi-scenario dataset combining real and internet-sourced images
• Data augmentation simulating illumination and contrast variations
• REAS-Det network with enhanced receptive fields and occlusion handling