To optimize fruit production, a portion of the flowers and fruitlets of apple trees must be removed early in the growing season. The proportion to be removed is determined by the bloom intensity, i.e., the number of flowers present in the orchard. Several automated computer vision systems have been proposed to estimate bloom intensity, but their overall performance is still far from satisfactory even in relatively controlled environments. With the goal of devising a technique for flower identification which is robust to clutter and to changes in illumination, this paper presents a method in which a pre-trained convolutional neural network (CNN) is fine-tuned to become specially sensitive to flowers. Experimental results on a challenging dataset demonstrate that our method significantly outperforms three approaches that represent the state of the art in flower detection, with recall and precision rates higher than 90%. Moreover, a performance assessment on three additional datasets previously unseen by the network, which consist of different flower species and were acquired under different conditions, reveals that the proposed method highly surpasses baseline approaches in terms of generalization capability. This dataset comprises mp4 video sequences illustrating each combination of datasets and methods.
- Supplementary data - Video mmc1 (7MB)Data
Dataset = AppleA.
Method on left-hand side: second baseline...
MD5:Explore Data6.58 MB - Supplementary data - Video mmc2 (7MB)Data
Dataset = AppleA.
Method on left-hand side: third baseline...
MD5:Explore Data6.58 MB - Supplementary data - Video mmc3 (7MB)Data
Dataset = AppleA.
Method on left-hand side: first baseline algorithm...
MD5:Explore Data6.56 MB - Supplementary data - Video mmc4 (3MB)Data
Dataset = AppleB.
Method on left-hand side: third baseline algorithm...
MD5:Explore Data2.68 MB - Supplementary data - Video mmc5 (3MB)Data
Dataset = AppleC.
Method on left-hand side: third baseline algorithm...
MD5:Explore Data2.66 MB - Supplementary data - Video mmc6 (3MB)Data
Dataset = Peach.
Method on left-hand side: third baseline algorithm...
MD5:Explore Data2.7 MB
Field | Value |
---|---|
Tags | |
Modified | 2020-02-07 |
Release Date | 2019-02-01 |
Identifier | 8e55a170-d35d-4369-94f5-5b8d8f7f9455 |
Publisher | Ag Data Commons |
License | |
Contact Name | Tabb, Amy |
Contact Email | |
Public Access Level | Public |
Program Code | 005:040 - Department of Agriculture - National Research |
Bureau Code | 005:18 - Agricultural Research Service |