Package detailsv3.0.2

flutter_vision

Plugin for managing Yolov5, Yolov8 and Yolov11 accessing with LiteRT (TensorFlow Lite) Support object detection and segmentation on Android. iOS, Working in progress.

AndroidiOS

pub.dev API documentation Source code

30-day downloads: 505
Likes: 116
Pub points: 160

Install package

flutter pub add flutter_vision

Package Overview

Package selection guidance compiled from public package information, community data, and project usage.

flutter_vision is a Flutter plugin that enables object detection and segmentation using YOLOv5, YOLOv8, and YOLOv11 models via LiteRT (TensorFlow Lite). It supports both Android and iOS platforms, offering efficient on-device inference for computer vision tasks. The plugin is designed for developers integrating real-time image analysis into mobile apps, with ongoing development to enhance functionality and performance. It's particularly useful for applications requiring fast, accurate object recognition and localization directly on the device.

Use cases

Real-time object detection in mobile apps
Image segmentation for augmented reality
On-device OCR and visual analysis
Mobile-based surveillance systems
AI-powered photo tagging

Key features

Supports YOLOv5, YOLOv8, and YOLOv11 models
Uses TensorFlow Lite via LiteRT for optimized performance
Cross-platform Android and iOS compatibility
Lightweight and suitable for mobile deployment
Built-in support for object detection and segmentation

Suitable for

Mobile app developers working with AI vision
Teams building on-device computer vision features
Projects requiring low-latency inference
Developers targeting Android and iOS with minimal setup
Prototyping AI-powered camera applications

Considerations

Still under active development
Limited documentation available
Performance depends on device hardware
Model size may affect app bundle size
iOS integration may require additional configuration

Original README

Original README snapshot from the linked source repository. Visit the repository for the latest content.

flutter_vision

A Flutter plugin for managing Yolov5, Yolov8, and Yolov11 accessing with LiteRT (TensorFlow Lite). Support object detection and segmentation on Android. iOS not updated, working in progress.

Installation

Add flutter_vision as a dependency in your pubspec.yaml file.

Android

In android/app/build.gradle, add the following setting in android block.

    android{
        aaptOptions {
            noCompress 'tflite'
            noCompress 'lite'
        }
    }

iOS

Coming soon ...

Usage

For YoloV5, YoloV8, and YoloV11 MODEL

Create a assets folder and place your labels file and model file in it. In pubspec.yaml add:

  assets:
   - assets/labels.txt
   - assets/yolovx.tflite

Import the library:

import 'package:flutter_vision/flutter_vision.dart';

Initialized the flutter_vision library:

 FlutterVision vision = FlutterVision();

Load the model and labels: modelVersion: yolov5 or yolov8 or yolov8seg or yolo11 or yolov11

await vision.loadYoloModel(
        labels: 'assets/labelss.txt',
        modelPath: 'assets/yolov5n.tflite',
        modelVersion: "yolov5",
        quantization: false,
        numThreads: 1,
        useGpu: false);

For camera live feed

Make your first detection: confThreshold work with yolov5 other case it is omited.

Make use of camera plugin

final result = await vision.yoloOnFrame(
        bytesList: cameraImage.planes.map((plane) => plane.bytes).toList(),
        imageHeight: cameraImage.height,
        imageWidth: cameraImage.width,
        iouThreshold: 0.4,
        confThreshold: 0.4,
        classThreshold: 0.5);

For static image

Make your first detection or segmentation:

final result = await vision.yoloOnImage(
        bytesList: byte,
        imageHeight: image.height,
        imageWidth: image.width,
        iouThreshold: 0.8,
        confThreshold: 0.4,
        classThreshold: 0.7);

Release resources:

await vision.closeYoloModel();

About results

For Yolo v5, v8, or v11 in detection task

result is a List<Map<String,dynamic>> where Map have the following keys:

   Map<String, dynamic>:{
    "box": [x1:left, y1:top, x2:right, y2:bottom, class_confidence]
    "tag": String: detected class
   }

For YoloV8 in segmentation task

result is a List<Map<String,dynamic>> where Map have the following keys:

   Map<String, dynamic>:{
    "box": [x1:left, y1:top, x2:right, y2:bottom, class_confidence]
    "tag": String: detected class
    "polygons": List<Map<String, double>>: [{x:coordx, y:coordy}]
   }