Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025AgricultureOpen Access

Enhanced YOLOv5 with ECA Module for Vision-Based Apple Harvesting Using a 6-DOF Robotic Arm in Occluded Environments

View Full Paper
Ask AI
Bookmark
Share

Authors

YXYan XuXQX. QiaoLDLi Ding

Discussion

Loading...

Member takes

Overview

This approach improves apple recognition and localization using a vision-based algorithm and a robotic arm, indicating effective harvesting in challenging settings.

Key Points

  • The ECA-enhanced YOLOv5 model achieved a confidence level of 90%, significantly improving target recognition under occlusion.
  • Experimental evaluations revealed an impressive in-range apple recognition rate of 98%, with mean Average Precision improved by 2.5% over baseline.
  • The robotic arm demonstrated a motion planning success rate of 92%, completing apple picking in 23 seconds per fruit.
  • The end-effector positioning error was consistently controlled within 1.5 mm, ensuring high precision in operations.

Cite This Study

Xu et al. (2025) studied this question.

synapsesocial.com/papers/68c1d7f654b1d3bfb60fa1f4https://doi.org/10.3390/agriculture15171850
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Fruit fast tracking and recognition of apple picking robot based on improved YOLOv52024 · 8 citations
  2. 2Precise Apple Detection and Localization in Orchards using YOLOv5 for Robotic Harvesting Systems2024
  3. 3Apple-Harvesting Robot Based on the YOLOv5-RACF Model2024 · 15 citations
  4. 4YOLO-CSB: A Model for Real-Time and Accurate Detection and Localization of Occluded Apples in Complex Orchard Environments2026 · 6 citations
  5. 5Extraction and Recognition of Robotic Apple Picking Image Features Based on YOLOv5 Detection Models2024