Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 22, 2026HorticulturaeOpen Access

Research on Target-Region Segmentation and Robust Sphere Fitting for RGB-D Apple Picking-Point Localization

View Full Paper
Ask AI
Bookmark
Share

Authors

YLYing LiuKZKaisen ZhangLJLinlong Jing

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved apple picking-point localization in orchards, indicating real-time application potential.

Key Points

  • This research aims to improve apple picking-point localization in complex orchard environments affected by occlusion.
  • Developed a lightweight semantic segmentation network (OA-LiteSegNet) for accurate apple foreground detection.
  • Reconstructed point clouds from depth maps guided by segmentation results for improved localization.
  • Employed robust sphere fitting to estimate apple sphere centers and diameters.
  • OA-LiteSegNet achieved 90.35% mIoU and 76.27% BF1 with 5.92M parameters and 11.30 GFLOPs.
  • Average sphere-center error of the proposed method was 2.88 mm, significantly lower than the conventional method's 9.11 mm.
  • The method maintained stable performance across varying occlusion types.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/6a0ff3ecd674f7c03778ce4ahttps://doi.org/10.3390/horticulturae12050594
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. 1High-precision apple recognition and localization method based on RGB-D and improved SOLOv2 instance segmentation2024 · 30 citations
  2. 2Dual-Detector Vision and Depth-Aware Back-Projection for Accurate Apple Detection and 3D Localisation for Robotic Harvesting2026
  3. 3Cluster segmentation and stereo vision-based apple localization algorithm for robotic harvesting2025 · 2 citations
  4. 4A Novel YOLO-Like Multi-Branch Architecture for Accurate Apple Detection and Segmentation Under Orchard Constraints2025
  5. 5YOLO-CSB: A Model for Real-Time and Accurate Detection and Localization of Occluded Apples in Complex Orchard Environments2026 · 6 citations