What question did this study set out to answer?

February 24, 2026Open Access

Dual-Detector Vision and Depth-Aware Back-Projection for Accurate Apple Detection and 3D Localisation for Robotic Harvesting

View Full Paper

Ask AI

Bookmark

Authors

THTagor HossainThe University of Adelaide PSPeng ShiThe University of Adelaide LKLevente KovacsObuda University

Discussion

Member takes

Implication

Experimental methods demonstrate improved apple detection and 3D localisation in orchard environments, indicating strong applicability for robotic harvesting.

Key Points

The research aims to enhance apple detection and 3D localisation for robotic harvesting in challenging orchard settings.
Developed a dual-detector vision framework combining YOLOv8 and Mask R-CNN.
Implemented confidence-weighted fusion of bounding boxes and pixel-wise union of segmentation masks.
Utilised depth-aware back-projection for converting 2D representations into dense 3D models.
Employed a depth-consistency weighting strategy for improved centroid computation.
Applied local intensity normalisation to reduce the effects of varying illumination.
Achieved an accuracy of 98.9% and mAP of 94.2%.
Reported an F1-score of 93.3% and recall of 92.8%.
Demonstrated real-time performance at 86.42 FPS.
Confirmed the method's effectiveness in visually ambiguous orchard conditions.

Cite This Study

Hossain et al. (2026) studied this question.

synapsesocial.com/papers/699d4008de8e28729cf64ff5 https://doi.org/10.3390/robotics15020047

View Full Paper

Ask AI

Bookmark

Implication

Experimental methods demonstrate improved apple detection and 3D localisation in orchard environments, indicating strong applicability for robotic harvesting.

Dual-Detector Vision and Depth-Aware Back-Projection for Accurate Apple Detection and 3D Localisation for Robotic Harvesting

Discussion

Member takes

Implication

Key Points

Cite This Study

Dual-Detector Vision and Depth-Aware Back-Projection for Accurate Apple Detection and 3D Localisation for Robotic Harvesting

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider