תפריט נגישות
ניגודיות עדינהניגודיות גבוהה
מונוכרום
הדגשת קישורים
חסימת אנימציה
פונט קריא
סגור
איפוס הגדרות נגישות
להורדת מודול נגישות חינם תפריט נגישותניגודיות עדינהניגודיות גבוההמונוכרוםהדגשת קישוריםחסימת אנימציהפונט קריאסגוראיפוס הגדרות נגישותלהורדת מודול נגישות חינםLaborious fruit thinning is required for attaining high-quality Medjoul dates. Thinning automation can significantly reduce labor and improve efficiency. An image processing apparatus developed for robotic Medjoul thinning is presented. Instance segmentation based on Mask R-CNN was applied to identify the fruit bunch components: spikelets and rachis. Motion planning parameters were extracted using the derived masks: rachis center point (RCP), rachis orientation angle, and spikelets remaining length. RCP and rachis orientation angle were computed geometrically, spikelets remaining length was estimated with a convolutional neural network (CNN) and a deep neural network (DNN). Instance segmentation results were accurate, especially for spikelets, for low intersection over union (IoU) (0.3 IoU, fruit determined for thinning identification, spikelets: 98%, rachises: 73%). However, only 66% of the rachises were correctly matched to spikelets. The segmentation of all spikelets and rachises in the images was of medium quality for low IoU (0.3 IoU, F1, spikelets: 0.67, rachis: 0.77), where both precision and recall dropped for higher IoUs. RCP and rachis orientation angle were accurately estimated (0.3 IoU, error, RCP: 2.2 cm, rachis orientation angle: 5.0°). Spikelets remaining length estimation using CNN resulted in better performance than DNN (0.3 IoU, error, CNN: 19.7%, DNN: 24.6%). Spikelets segmentation results are suitable for thinning automation. However, rachis segmentation and matching the rachis and spikelets may still require human intervention during run-time. RCP and rachis orientation angle estimation errors are acceptable, while spikelets remaining length estimation errors are acceptable only for preliminary motion planning and mandate additional tuning during motion execution.
Laborious fruit thinning is required for attaining high-quality Medjoul dates. Thinning automation can significantly reduce labor and improve efficiency. An image processing apparatus developed for robotic Medjoul thinning is presented. Instance segmentation based on Mask R-CNN was applied to identify the fruit bunch components: spikelets and rachis. Motion planning parameters were extracted using the derived masks: rachis center point (RCP), rachis orientation angle, and spikelets remaining length. RCP and rachis orientation angle were computed geometrically, spikelets remaining length was estimated with a convolutional neural network (CNN) and a deep neural network (DNN). Instance segmentation results were accurate, especially for spikelets, for low intersection over union (IoU) (0.3 IoU, fruit determined for thinning identification, spikelets: 98%, rachises: 73%). However, only 66% of the rachises were correctly matched to spikelets. The segmentation of all spikelets and rachises in the images was of medium quality for low IoU (0.3 IoU, F1, spikelets: 0.67, rachis: 0.77), where both precision and recall dropped for higher IoUs. RCP and rachis orientation angle were accurately estimated (0.3 IoU, error, RCP: 2.2 cm, rachis orientation angle: 5.0°). Spikelets remaining length estimation using CNN resulted in better performance than DNN (0.3 IoU, error, CNN: 19.7%, DNN: 24.6%). Spikelets segmentation results are suitable for thinning automation. However, rachis segmentation and matching the rachis and spikelets may still require human intervention during run-time. RCP and rachis orientation angle estimation errors are acceptable, while spikelets remaining length estimation errors are acceptable only for preliminary motion planning and mandate additional tuning during motion execution.
