Real-time monitoring of pepper harvesting loss using lightweight vision model
Authors:
- Pengcheng DuPDPengcheng Du
- Wei HanWHWei Han
- Yulong XuYXYulong Xu
- Wenwu HuWHWenwu Hu
- Yang XiangYXYang Xiang
Preprint
- 30 March 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Real-time monitoring of pepper losses during mechanized harvesting is essential for optimizing operational parameters and reducing yield loss. However, accurate detection of fallen peppers in field environments remains challenging due to heavy dust interference and complex backgrounds.To address these issues, this study proposes a robust vision-based monitoring method that integrates image enhancement and lightweight object detection. First, the Dark Channel Prior (DCP) algorithm is applied to reduce dust effects and restore image clarity under degraded field conditions. Then, an improved YOLOv8n-based model, termed Pepper_YOLOv8n, is developed by optimizing the neck structure and incorporating the SimAM attention mechanism together with the Self-Calibrated Illumination Network (SCINet) module, thereby enhancing feature representation for small and partially occluded targets.Experimental results show that the proposed model achieves a precision of 90.1%, recall of 89.7%, and an mAP of 96.8%. Compared with the baseline YOLOv8n, recall and mAP are improved by 4.0% and 1.9%, respectively, while the inference time is reduced by 1.5 ms on a workstation.To further validate its practical applicability, a real-time edge detection system is developed based on the D-Robotics RDK X5 platform. With post-training quantization (PTQ), the deployed model reduces computational complexity (FLOPs decreased by 3.6G) and achieves an inference speed of 18.2 ms per frame, meeting the requirements for real-time monitoring during field harvesting operations.The proposed method provides an effective solution for intelligent monitoring of harvesting losses and offers practical support for precision agriculture and smart agricultural machinery.Keywords
This publication has 8 references indexed in Scilit:
- A Machine Vision-Based Method of Impurity Detection for Rapeseed HarvestersProcesses, 2024
- DedustGAN: Unpaired learning for image dedusting based on Retinex with GANsExpert Systems with Applications, 2023
- Sand-dust image enhancement using RGB color balance methodOptics and Precision Engineering, 2023
- Development of Impurity-Detection System for Tracked Rice Combine Harvester Based on DEM and Mask R-CNNSensors, 2022
- Real-time grain impurity sensing for rice combine harvesters using image processing and decision-tree algorithmComputers and Electronics in Agriculture, 2020
- Study on the Hungarian algorithm for the maximum likelihood data association problemJournal of Systems Engineering and Electronics, 2007
- Efficient Non-Maximum Suppression2006
- Contrast restoration of weather degraded imagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003