נגישות
menu      
Advanced Search
Syntax
Search...
Volcani treasures
About
Terms of use
Manage
Community:
אסיף מאגר המחקר החקלאי
Powered by ClearMash Solutions Ltd -
Instance segmentation of partially occluded Medjool-date fruit bunches for robotic thinning
Year:
2023
Source of publication :
precision agriculture (source )
Authors :
Bechar, Avital
;
.
Cohen, Yuval
;
.
Volume :
Co-Authors:
  • May Regev, 
  • Avital Bechar, 
  • Yuval Cohen, 
  • Avraham Sadowsky 
  • Sigal Berman 
Facilitators :
From page:
0
To page:
0
(
Total pages:
1
)
Abstract:

Medjool date thinning automation is essential for reducing Medjool production labor and improving fruit quality. Thinning automation requires motion planning based on feature extraction from a segmented fruit bunch and its components. Previous research with focused bunch images attained high success in bunch component segmentation but less success in establishing correct association between the two components (a rachis and spikelets) that form one bunch. The current study presents an algorithm for improved component segmentation and association in the presence of occlusions based on integrating deep neural networks, traditional methods building on bunch geometry, and active vision. Following segmentation with Mask-R-CNN, segmented component images are converted to binary images with a Savitzky–Golay filter and an adapted Otsu threshold. Bunch orientation is calculated based on lines found in the binary image with the Hough transform. The orientation is used for associating a rachis with spikelets. If a suitable rachis is not found, bunch orientation is used for selecting a better viewpoint. The method was tested with two databases of bunches in an orchard, one with focused and one with non-focused images. In all images, the spikelets were correctly identified [intersection over union (IoU) 0.5: F1 0.9]. The average orientation errors were 18.15° (SD 12.77°) and 16.44° (SD 11.07°), respectively, for the focused and non-focused databases. For correct rachis selection, precision was very high when incorporating orientation, and when additionally incorporating active vision recall (and therefore F1) was high (IoU 0.5: orientation: precision 0.94, recall 0.44, F1 0.60; addition of active vision: precision 0.96, recall 0.61, F1 0.74). The developed method leads to highly accurate identification of fruit bunches and their spikelets and rachis, making it suitable for integration with a thinning automation system.

Note:
Related Files :
Active vision
Deep neural networks
Hough transform
Image processing
Medjool dates
Thinning automation
Show More
Related Content
More details
DOI :
10.1007/s11119-023-10086-w
Article number:
0
Affiliations:
Database:
Google Scholar
Publication Type:
article
;
.
Language:
English
Editors' remarks:
ID:
67635
Last updated date:
31/12/2023 14:11
Creation date:
31/12/2023 14:07
Scientific Publication
Instance segmentation of partially occluded Medjool-date fruit bunches for robotic thinning
  • May Regev, 
  • Avital Bechar, 
  • Yuval Cohen, 
  • Avraham Sadowsky 
  • Sigal Berman 
Instance segmentation of partially occluded Medjool-date fruit bunches for robotic thinning

Medjool date thinning automation is essential for reducing Medjool production labor and improving fruit quality. Thinning automation requires motion planning based on feature extraction from a segmented fruit bunch and its components. Previous research with focused bunch images attained high success in bunch component segmentation but less success in establishing correct association between the two components (a rachis and spikelets) that form one bunch. The current study presents an algorithm for improved component segmentation and association in the presence of occlusions based on integrating deep neural networks, traditional methods building on bunch geometry, and active vision. Following segmentation with Mask-R-CNN, segmented component images are converted to binary images with a Savitzky–Golay filter and an adapted Otsu threshold. Bunch orientation is calculated based on lines found in the binary image with the Hough transform. The orientation is used for associating a rachis with spikelets. If a suitable rachis is not found, bunch orientation is used for selecting a better viewpoint. The method was tested with two databases of bunches in an orchard, one with focused and one with non-focused images. In all images, the spikelets were correctly identified [intersection over union (IoU) 0.5: F1 0.9]. The average orientation errors were 18.15° (SD 12.77°) and 16.44° (SD 11.07°), respectively, for the focused and non-focused databases. For correct rachis selection, precision was very high when incorporating orientation, and when additionally incorporating active vision recall (and therefore F1) was high (IoU 0.5: orientation: precision 0.94, recall 0.44, F1 0.60; addition of active vision: precision 0.96, recall 0.61, F1 0.74). The developed method leads to highly accurate identification of fruit bunches and their spikelets and rachis, making it suitable for integration with a thinning automation system.

Scientific Publication
You may also be interested in