Missing-Depth-Tolerant Oriented Object Detection for Day-Night Apple-Harvesting Perception

Abstract

Apple-harvesting perception must remain usable when depth measurements are unavailable. This study evaluates a single four-channel YOLOv8s-OBB detector that accepts RGB-D input when depth is available and RGB-Z input, with a zero-filled fourth channel, when depth is absent. Training-only input-level modality dropout exposes the detector to both sensing states without changing the inference graph. Apples are assigned to three operational visual categories—ripe_pickable, ripe_unpickable, and unripe—and oriented bounding boxes provide image-plane geometric cues. On an image-level split of 542 orchard images, pdrop = 0.5 gave the highest observed full-test mAP50 and mAP50-95 among the tested settings, at 0.7199 and 0.5380. Under full-test forced RGB-Z input, mAP50 was 0.7064, compared with 0.5906 without modality dropout and 0.6952 for the RGB-only baseline. On the paired night-time subset, mAP50 curve AUCs under three graded missing-depth masks were 0.7225–0.7355, compared with 0.6088–0.6444 without dropout. These results demonstrate empirical missing-depth tolerance within a single detector under the evaluated conditions. The dropout setting is empirical, and the results are single-run point estimates. Daytime images lack paired depth, so day/night comparisons do not isolate illumination robustness; the image-level split also does not establish scene-independent generalization. OBB outputs are image-plane cues, and the exploratory geometry-only simulation does not validate robotic grasping or field harvesting success.