What question did this study set out to answer?

February 8, 2026AgronomyOpen Access

YOLO-CSB: A Model for Real-Time and Accurate Detection and Localization of Occluded Apples in Complex Orchard Environments

View Full Paper

Ask AI

Bookmark

Authors

A model enhances apple detection accuracy in complex orchards, indicating improved robotic harvesting efficiency.

To improve the detection and localization of occluded apples in complex orchard environments for robotic harvesting.
Developed YOLO-CSB model based on YOLO11s
Constructed a comprehensive apple dataset under various conditions
Integrated CSFC Block and SEAM component for feature restoration
Employed efficient BiFPN approach for improved precision
Conducted validation through ablation analyses and comparative tests.
YOLO-CSB improved mean Average Precision (mAP) by 3.02% over YOLO11s
Achieved a mAP of 93.69%, precision of 88.82%, and recall of 87.58%
Laboratory detection accuracy reached 100%
Average localization errors were 4.15 mm, 3.96 mm, and 4.02 mm in X, Y, and Z directions.

Pan et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark