Artificial Intelligence in Agriculture · 2024 · 10 citations · 26 references
AgricultureAgricultural EngineeringComputer ScienceComputer VisionRemote SensingYield MonitoringAgricultural ApplicationsAgricultural Machine VisionObject DetectionRemote Sensing For Yield EstimationSensor Data AcquisitionYield Map GenerationAccuracyAerial Image-based Yield EstimationDrones For Crop SurveyingUav-based EstimationUnmanned Aerial Vehicle Crop MonitoringUnmanned Aerial Vehicle SensingUnsupervised Transfer LearningWater Yield Estimation
Accurate watermelon yield estimation is crucial to the agricultural value chain, as it guides the allocation of agricultural resources as well as facilitates inventory and logistics planning. The conventional method of watermelon yield estimation relies heavily on manual labor, which is both time-consuming and labor-intensive. To address this, this work proposes an algorithmic pipeline that utilizes unmanned aerial vehicle (UAV) videos for detection and counting of watermelons. This pipeline uses You Only Look Once version 8 s (YOLOv8s) with panorama stitching and overlap partitioning, which facilitates the overall number estimation of watermelons in field. The watermelon detection model, based on YOLOv8s and obtained using transfer learning, achieved a detection accuracy of 99.20 %, demonstrating its potential for application in yield estimation. The panorama stitching and overlap partitioning based detection and counting method uses panoramic images as input and effectively mitigates the duplications compared with the video tracking based detection and counting method. The counting accuracy reached over 96.61 %, proving a promising application for yield estimation. The high accuracy demonstrates the feasibility of applying this method for overall yield estimation in large watermelon fields. • An algorithmic pipeline of UAV videos for detection and counting of watermelons. • Input of panoramic images enables the overall watermelon yield estimation in field. • Panorama stitching and overlap partitioning method enhances yield estimation accuracy. • Proposed method decreases duplications compared to tracking-based counting method.
26
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick et al. · 2017 · 28.7K citations
Path Aggregation Network for Instance Segmentation
Shu Liu, Lu Qi, Haifang Qin et al. · 2018 · 8.8K citations
Sensing, smart and sustainable technologies for Agri-Food 4.0
Jhonattan Miranda, Pedro Ponce, Arturo Molina et al. · Computers in Industry · 2019 · 297 citations