mini-vision 0.2.0

YOLO segmentation utilities for video streams

mini_vision

Simple Python library for object segmentation in video streams using YOLO models.

The goal of this library is to provide a modular pipeline to:

• consume video streams
• perform object segmentation
• render contours or masks

The library follows data-oriented design and low coupling principles, allowing easy replacement of computer vision models.

---

Installation

pip install mini-vision

Usage

Example showing how to use vision-seg to consume a video stream, run YOLO segmentation, and render object contours.

Import the library

from vision_seg import (
    YoloSegmenter,
    SegmentationRenderer,
    WSFrameClient
)

Components:

Component	Description
YoloSegmenter	Runs object segmentation using a YOLO segmentation model
SegmentationRenderer	Draws segmentation contours on the frame
WSFrameClient	Connects to a WebSocket video stream and yields frames

YoloSegmenter

Runs object segmentation using a YOLO segmentation model.

segmenter = YoloSegmenter("yolov8n-seg.pt")
detections = segmenter.segment(frame)

SegmentationRenderer

Responsible for rendering segmentation contours on frames.

renderer = SegmentationRenderer()
frame = renderer.draw_contours(frame, detections)

WSFrameClient

Connects to a WebSocket video stream and yields frames.

client = WSFrameClient("ws://127.0.0.1:8000/ws/frames")
async for frame in client.frames():