Universe

arthropod_segmentations Computer Vision Model

byYSTTask:
Instance Segmentation
License:CC BY 4.0

How to use the arthropod_segmentations Segmentation API

Try This Model

Drop an image here or click to upload

Or try a test image 

Code Snippets

from inference_sdk import InferenceHTTPClient

CLIENT = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key="API_KEY"
)

result = CLIENT.infer("YOUR_IMAGE.jpg", model_id="arthropod_segmentations/13")
Give your agent everything it needs

Or, Use Free Dirt, Aphytis and Arthropod Detection API

Powered by general detection model

Code
pip install inference-sdk
# 1. Import the library
from inference_sdk import InferenceHTTPClient

# 2. Connect to your workspace
client = InferenceHTTPClient(
  api_url="https://serverless.roboflow.com",
  api_key="API_KEY"
)

# 3. Run your workflow on an image
result = client.run_workflow(
  workspace_name="<YOUR_WORKSPACE>",
  workflow_id="<YOUR_WORKFLOW_ID>",
  images={
    "image": "YOUR_IMAGE.jpg"  # Path to your image file
  },
  parameters={
    "classes": "dirt, aphytis, arthropod, beetle, black_parasitoid"
  },
  use_cache=True  # cache workflow definition for 15 minutes
)

# 4. Get your results
print(result)

Run on custom image

Drop an image here or click to upload

Detecting classes:
Or try a test image 
See all 479 imagesarthropod_segmentations arthropod-dirt-leaf samplearthropod_segmentations arthropod-dirt-leaf samplearthropod_segmentations arthropod-dirt-leaf sample showing dirt, thrip_yellowarthropod_segmentations arthropod-dirt-leaf samplearthropod_segmentations arthropod-dirt-leaf samplearthropod_segmentations arthropod-dirt-leaf samplearthropod_segmentations arthropod-dirt-leaf samplearthropod_segmentations arthropod-dirt-leaf sample showing arthropodarthropod_segmentations arthropod-dirt-leaf samplearthropod_segmentations arthropod-dirt-leaf sample showing arthropodarthropod_segmentations arthropod-dirt-leaf samplearthropod_segmentations arthropod-dirt-leaf sample showing arthropod

About arthropod_segmentations Model

  1. Dataset Rules
  2. No overlapping images (image deletions are pending to comply with this rule)
  3. Same magnification on all images
  4. Double polarised ring light with the filters rotated to visually minimize reflections from water and glue.
  5. Ring light brightness is not standardised in the training dataset.
  6. All images are focus stacks composed of 30 frames from a 10fps video recording that covers 5-7mm depth.

  • Frames extracted from .h264 video file using ffpmeg for windows and saved as .jpeg files (maximum quality setting).

     cmd = [
 	ffmpeg_exe,
 	'-y',
 	'-i', str(video_path),
 	'-q:v', '1',
 	'-qmin', '1',
 	'-pix_fmt', 'yuvj444p',
 	'-threads', str(num_threads),
 	filename.jpg
 ]

  • Frames are focused stacked using Helicon Focus API via a python script and saved in .jpg format.

      cmd = [
      HELICON_PATH,
      "-silent",
      "-m:B", "-r:50", "-s:4",
      input_folder_path,
      f"-save:{filename.jpg}"
  ]

Cite This Project

LicenseCC BY 4.0

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{ arthropod_segmentations_dataset,
  title = { arthropod_segmentations Dataset },
  type = { Open Source Dataset },
  author = { YST },
  howpublished = { \url{ https://universe.roboflow.com/yst-guocz/arthropod_segmentations } },
  url = { https://universe.roboflow.com/yst-guocz/arthropod_segmentations },
  journal = { Roboflow Universe },
  publisher = { Roboflow },
  year = { 2026 },
  month = { jul },
  note = { visited on 2026-07-29 },
}

Similar Projects

See More