https://github.com/etowahadams/leaf-colors

Analyzing leaf color of 10,950‬ iNaturalist observations of Red Maple (Acer rubrum)
https://github.com/etowahadams/leaf-colors

Last synced: about 2 months ago
JSON representation

Analyzing leaf color of 10,950‬ iNaturalist observations of Red Maple (Acer rubrum)

• Host: GitHub
• URL: https://github.com/etowahadams/leaf-colors
• Owner: etowahadams
• License: mit
• Created: 2019-12-29T01:32:48.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2020-01-12T19:01:58.000Z (almost 5 years ago)
• Last Synced: 2024-10-18T17:26:45.864Z (3 months ago)
• Language: Python
• Homepage:
• Size: 584 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.txt

Awesome Lists containing this project

README

        
# Leaf-colors

### Analyzing leaf color of 10,950‬ [iNaturalist](https://www.inaturalist.org/) observations of Red Maple (*Acer rubrum*)

Using a deep learning based object detector, [leaf-detector](https://github.com/etowahs/leaf-detector), leaf positions in each image were detected. From there, the foreground was removed from the detected leaf using GrabCut algorithm. Dominant color of the leaf was calculated using k-means clustering. 

![2019 data](all-2019-data.jpg)

Figure 1 (above): All the 2019 data plotted on the same map. The color of each observation marker corresponds to the dominant color of the leaves of the observation. 

## Usage 

``` python

from leafcolors.leafcolors import LeafColors

detector_output = 'output.txt'    # output of leaf-detector batch detection

img_folder = '2015/'             # folder of images that darknet detected 

my_analysis = LeafColors(detector_output, img_folder)

```

For the output of leaf-detector, be sure to remove the first few lines of metadata before passing it to LeafColors.