Published October 18, 2019
| Version v1
Conference paper
Open
Weakly Supervised Fruit Counting for Yield Estimation using Spatial Consistency
Description
Fruit counting is a fundamental component for yield estimation.Most of the SotA approaches address the problem using fruit models or by explicitly learning to count. In this paper, we tackle the problem by proposing a framework that learns to count fruits without the need for task-specific supervision labels. The experiments on different varieties of fruits show that our approach reaches performances that are comparable with SotA approaches based on the supervised paradigm.
Notes
Files
video_pitch-Weakly Supervised Fruit Counting for Yield Estimation using Spatial Consistency (Pitch Video)-p4F3PGE9Lks.mp4
Files
(33.1 MB)
Name | Size | Download all |
---|---|---|
md5:04a4aafba82a659c5d31b671e2f8e1dd
|
32.9 MB | Preview Download |
md5:ada7bf60cb026d32cee3f6b0021ff7a1
|
113.9 kB | Preview Download |