Skip to main content

pixpick ๐ŸŽฏ

Interactive coordinate picker for Computer Vision โ€” no external tools needed.

PyPI version Downloads Python 3.8+ License: MIT


The problem

Every major CV framework needs coordinates before it can run.

regioncounter = RegionCounter(region=[120, 80, 640, 480])    # YOLO   โ€” where does this region come from?
predictor.predict(box=np.array([120, 80, 640, 480]))         # SAM2   โ€” same problem

The standard workflow: open CVAT or Roboflow โ†’ grab coordinates โ†’ paste them back into code. Every. Single. Time.

The fix

import pixpick

region = pixpick.box("frame.jpg")      # drag a box on the image
zone   = pixpick.polygon("frame.jpg")  # click polygon vertices

# coordinates are ready โ€” unpack directly into any framework
# YOLO:
regioncounter = RegionCounter(
     region=region.yolo_region,  # pass region points
     model="yolo26n.pt",
 )

# same for YOLOE
model.predict("frame.jpg", visual_prompt= region.yolo_prompt())

# SAM1/SAM2:
predictor.predict(box=region.sam())

A window opens on your image. You interact. You get framework-ready coordinates back in Python. No round-trips.


Install

pip install pixpick

Selectors

Selector How to use Returns
pixpick.box() Left-click + drag Box
pixpick.polygon() Click vertices โ†’ Enter to confirm Polygon

Box controls โ€” drag to draw ยท R to reset ยท Esc to cancel

Polygon controls โ€” LMB add point ยท RMB undo ยท Z clear ยท Enter confirm ยท Esc cancel


Output formats

Every selection object carries all the formats you'll ever need.

# โ”€โ”€ Box โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
region = pixpick.box("frame.jpg")

region.xyxy              # [x1, y1, x2, y2]            absolute pixels
region.xywh              # [x, y, w, h]                absolute pixels
region.norm_xywh         # [x, y, w, h]                0.0 โ€“ 1.0  โ† YOLO label format
region.center            # (cx, cy)
region.area              # pixelsยฒ


# โ”€โ”€ Polygon โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
zone = pixpick.polygon("frame.jpg")

zone.points              # [(x0,y0), (x1,y1), ...]     absolute pixels
zone.as_numpy            # np.array shape (N, 2)
zone.norm                # [(x0n,y0n), ...]             0.0 โ€“ 1.0
zone.bbox                # โ†’ Box   tight bbox around the polygon
zone.npoints             # int

For more details, see Selectors.


Framework integration

Framework Selector Method
Ultralytics YOLOE โ€” visual prompt Box region.yolo_prompt()
Ultralytics YOLO โ€” region Box region.yolo_region()
SAM / SAM2 โ€” box prompt Box region.sam()
Any other format Box / Polygon region.to_raw()

Persistence

Pick once, reuse forever.

region.save("zone.json")
region = pixpick.load("zone.json")   # Box and Polygon both work

Production pattern โ€” pick interactively the first time, load on every subsequent run:

from pathlib import Path
import pixpick

ZONE = "config/count_zone.json"

zone = pixpick.load(ZONE) if Path(ZONE).exists() else pixpick.polygon("frame.jpg")
zone.save(ZONE)

Docs

๐Ÿš€ Getting Started Installation, first selection, controls
๐ŸŽฏ Selectors All properties and methods for Box and Polygon
๐Ÿ”Œ Framework Integration YOLO, SAM2 and more
๐Ÿ’พ Persistence Save, load, JSON schema
๐Ÿ—๏ธ Architecture How it's built and how to extend it
๐Ÿ—บ๏ธ Roadmap What's coming next

Contributing

We welcome contributions! Please open a GitHub issue or submit a pull request. For more information, see CONTRIBUTING.md.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pixpick-0.1.2.tar.gz (17.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pixpick-0.1.2-py3-none-any.whl (16.0 kB view details)

Uploaded Python 3

File details

Details for the file pixpick-0.1.2.tar.gz.

File metadata

  • Download URL: pixpick-0.1.2.tar.gz
  • Upload date:
  • Size: 17.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.18

File hashes

Hashes for pixpick-0.1.2.tar.gz
Algorithm Hash digest
SHA256 9caa1cc30fdae10cecfd93b08316b37bd46693feba55a86339dc866f68b66ad2
MD5 aef08ac395a327e0098f5333d84fa342
BLAKE2b-256 ccf9fe325c4886f1252a1606e503270a5534efbfb584b6b054e67ce2e9d413ce

See more details on using hashes here.

File details

Details for the file pixpick-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: pixpick-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 16.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.18

File hashes

Hashes for pixpick-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 d353beed83d5743014c9b96c5b708bf8a276c98ea66504e7ac4a90fe8b192e1d
MD5 00cb511cf2f3bb03d7c72acc6c22d878
BLAKE2b-256 9ef2130eaf04366ed2a8ec65498b306daa89113e422dc2180e6d71b1014f844c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page