PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 6, 2026Agriculture0 citationsOpen Access

RGHD: A Risk-Gated Harvestability Decision Framework for Occlusion-Aware Greenhouse Melon Harvesting

View Full Paper
SSShijun SongHQHuixing QuSWShaowei Wang

Key Points

  • The central aim is to enhance safety in greenhouse melon harvesting by addressing leaf occlusion and dense clustering.
  • Developed the Risk-Gated Harvestability Decision (RGHD) framework
  • Integrated a YOLO11n detector with an EGSA-enhanced ShuffleNetV2 occlusion classifier
  • Utilized a logic-gated module to fuse occlusion, overlap, and scale cues
  • Implemented a Safety-First policy for operational guidance.
  • Achieved an mAP@0.5:0.95 of 75.8% with a processing speed of 113.3 FPS
  • Reduced proxy unsafe-acceptance rate from 8.7% to 4.4%, showing a 49.4% reduction in risk
  • Maintained decision precision at 88.0% under the Safety-First policy
  • Efficiency-First mode reached 91.0% recall, focusing on high throughput.

Abstract

Greenhouse melon harvesting is challenged by leaf occlusion and dense clustering, which often lead to unsafe harvesting attempts in conventional detection-only systems. To prioritize operational safety, this study proposes the Risk-Gated Harvestability Decision (RGHD) framework. The approach decouples candidate fruit detection from risk-aware reasoning by integrating a lightweight YOLO11n detector with an EGSA-enhanced ShuffleNetV2 occlusion classifier. A logic-gated module then fuses multi-source cues—occlusion, overlap, and scale—to enforce a Safety-First harvesting policy. Experimental results show the detector achieves an mAP@0.5:0.95 of 75.8% while running at 113.3 FPS. Under the Safety-First policy, the proxy unsafe-acceptance rate (FPR under our operational proxy) decreased from 8.7% to 4.4%, corresponding to a 49.4% relative reduction in the risk of unsafe attempts, while maintaining 88.0% decision precision. Although an Efficiency-First mode is available for high throughput (91.0% recall), the Safety-First strategy provides the robust crop protection necessary for autonomous systems. Overall, RGHD provides a lightweight, risk-aware decision layer that improves operational safety while preserving real-time performance in cluttered greenhouse scenes.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Song et al. (2026) studied this question.

synapsesocial.com/papers/69aa70b8531e4c4a9ff5ac48https://doi.org/10.3390/agriculture16050589
Ask AI
Helpful
Bookmark
Share
View Full Paper