OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

YOLO Vision Studio

YOLO Vision Studio is an open-source Python and Streamlit application for running computer-vision models on images and video, including object detection, instance segmentation, pose estimation, text-prompt detection and multi-object tracking.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

YOLO Vision Studio — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it to explore or review computer-vision results on images and video, especially when you need object IDs and running counts across footage rather than detections from a single frame.

Who it is for

  • People reviewing image or video content for objects, masks or human poses.
  • Users exploring text-prompt detection with YOLO World v2 or category-based YOLOE masks.
  • Developers and analysts who want to run a configurable computer-vision interface locally.

Documented uses

  • Annotate images with object detections and review counts and confidence values by class.
  • Track objects across video and compare current in-frame counts with confirmed tracked totals.
  • Inspect segmentation masks and pose keypoints on images or video.
  • Search video or images using text prompts or category names.
Before you choose

Requirements & limits

The project is open-source under the Apache-2.0 license and its README documents local setup with uv or pip. It requires Python 3.10 or later.

  • Video inputs documented include stored files, browser webcam, RTSP streams and YouTube URLs.
  • The app offers ByteTrack, BoT-SORT, Deep OC-SORT and TrackTrack; appearance ReID is available for BoT-SORT, Deep OC-SORT and TrackTrack.
  • A track is included in the confirmed total only after it appears in five processed frames.
  • YOLO World prompts work best as one object plus one attribute; YOLOE expects category names rather than descriptions.
  • CPU execution is supported by the README, while an NVIDIA GPU can improve video speed.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and start YOLO Vision Studio with uv

Set up the Streamlit app locally and open its interface.

Before you start

  • Python 3.10 or later
  • uv
  • Linux, macOS or Windows

Steps

  1. Clone the project repository and change into its directory.

  2. Run the command below to create the virtual environment with locked versions.

    Documented command
    uv sync

  3. Run the command below to start the app.

    Documented command
    uv run streamlit run app.py

Expected outcome

The Streamlit app starts locally at http://localhost:8501; model weights download automatically on first use.

Guide limitations

  • The README says the app runs on CPU, while an NVIDIA GPU can make video processing much faster.
  • YOLO World and YOLOE download additional encoders when first used.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
aparsoft/yolo-streamlit-detection-tracking · Official homepage title · retained in its source language
How we review sourcesSuggest a correction