Apple Trajectory Prediction in Orchards: A YOLOv8-EK-IPF Approach

To address the challenge of accurate apple harvesting by orchard robots, which is hindered by dynamic changes in apple position due to wind interference and branch swaying, this study proposes an optimized prediction algorithm based on an integration of the extended Kalman filter (EKF) and an improv...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinxing Niu, Zhengyi Liu, Shuo Wang, Jiaxi Huang, Junlong Zhao
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/11/1160
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330895713992704
author Jinxing Niu
Zhengyi Liu
Shuo Wang
Jiaxi Huang
Junlong Zhao
author_facet Jinxing Niu
Zhengyi Liu
Shuo Wang
Jiaxi Huang
Junlong Zhao
author_sort Jinxing Niu
collection DOAJ
description To address the challenge of accurate apple harvesting by orchard robots, which is hindered by dynamic changes in apple position due to wind interference and branch swaying, this study proposes an optimized prediction algorithm based on an integration of the extended Kalman filter (EKF) and an improved particle filter (IPF), built upon initial apple detection and recognition using YOLOv8. The algorithm first employs spatial partitioning according to the cyclical motion patterns of apples to constrain the prediction results. Subsequently, it optimizes the rationality of particle weights within the particle filter (PF) and reduces its computational resource consumption by implementing historical position weighting and an adaptive particle number strategy. Finally, an adaptive error correction mechanism dynamically adjusts the respective weights of the EKF and IPF components, continuously enhancing the algorithm’s prediction accuracy. Experimental results demonstrate that, compared to the classic unscented Kalman filter (UKF) and unscented particle filter (UPF), the proposed EK-IPF algorithm reduces the mean absolute error (MAE) by 22.25% and 10.89%, respectively, and the root mean square error (RMSE) by 23.70% and 13.25%, respectively, indicating a significant improvement in overall prediction accuracy. This research provides technical support for dynamic apple trajectory prediction in orchard environments.
format Article
id doaj-art-bafdf98b5a824a90b4dedcfe7dc3c4d3
institution Kabale University
issn 2077-0472
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-bafdf98b5a824a90b4dedcfe7dc3c4d32025-08-20T03:46:47ZengMDPI AGAgriculture2077-04722025-05-011511116010.3390/agriculture15111160Apple Trajectory Prediction in Orchards: A YOLOv8-EK-IPF ApproachJinxing Niu0Zhengyi Liu1Shuo Wang2Jiaxi Huang3Junlong Zhao4School of Mechanical Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450011, ChinaSchool of Mechanical Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450011, ChinaSchool of Mechanical Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450011, ChinaSchool of Mechanical Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450011, ChinaSchool of Mechanical Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450011, ChinaTo address the challenge of accurate apple harvesting by orchard robots, which is hindered by dynamic changes in apple position due to wind interference and branch swaying, this study proposes an optimized prediction algorithm based on an integration of the extended Kalman filter (EKF) and an improved particle filter (IPF), built upon initial apple detection and recognition using YOLOv8. The algorithm first employs spatial partitioning according to the cyclical motion patterns of apples to constrain the prediction results. Subsequently, it optimizes the rationality of particle weights within the particle filter (PF) and reduces its computational resource consumption by implementing historical position weighting and an adaptive particle number strategy. Finally, an adaptive error correction mechanism dynamically adjusts the respective weights of the EKF and IPF components, continuously enhancing the algorithm’s prediction accuracy. Experimental results demonstrate that, compared to the classic unscented Kalman filter (UKF) and unscented particle filter (UPF), the proposed EK-IPF algorithm reduces the mean absolute error (MAE) by 22.25% and 10.89%, respectively, and the root mean square error (RMSE) by 23.70% and 13.25%, respectively, indicating a significant improvement in overall prediction accuracy. This research provides technical support for dynamic apple trajectory prediction in orchard environments.https://www.mdpi.com/2077-0472/15/11/1160extended Kalman filterparticle filtertrajectory predictionstate estimationYOLOv8apple
spellingShingle Jinxing Niu
Zhengyi Liu
Shuo Wang
Jiaxi Huang
Junlong Zhao
Apple Trajectory Prediction in Orchards: A YOLOv8-EK-IPF Approach
Agriculture
extended Kalman filter
particle filter
trajectory prediction
state estimation
YOLOv8
apple
title Apple Trajectory Prediction in Orchards: A YOLOv8-EK-IPF Approach
title_full Apple Trajectory Prediction in Orchards: A YOLOv8-EK-IPF Approach
title_fullStr Apple Trajectory Prediction in Orchards: A YOLOv8-EK-IPF Approach
title_full_unstemmed Apple Trajectory Prediction in Orchards: A YOLOv8-EK-IPF Approach
title_short Apple Trajectory Prediction in Orchards: A YOLOv8-EK-IPF Approach
title_sort apple trajectory prediction in orchards a yolov8 ek ipf approach
topic extended Kalman filter
particle filter
trajectory prediction
state estimation
YOLOv8
apple
url https://www.mdpi.com/2077-0472/15/11/1160
work_keys_str_mv AT jinxingniu appletrajectorypredictioninorchardsayolov8ekipfapproach
AT zhengyiliu appletrajectorypredictioninorchardsayolov8ekipfapproach
AT shuowang appletrajectorypredictioninorchardsayolov8ekipfapproach
AT jiaxihuang appletrajectorypredictioninorchardsayolov8ekipfapproach
AT junlongzhao appletrajectorypredictioninorchardsayolov8ekipfapproach