https://github.com/mounishvatti/pothole_detection_yolov8

Pothole Detection using Image Segmentation by using a custom dataset with over 700+ images trained on Roboflow and predicting using the latest Ultralytics YOLOv8.
https://github.com/mounishvatti/pothole_detection_yolov8

image-segmentation machine-learning pothole-detection roboflow ultralytics yolov8

Last synced: 1 day ago
JSON representation

Pothole Detection using Image Segmentation by using a custom dataset with over 700+ images trained on Roboflow and predicting using the latest Ultralytics YOLOv8.

• Host: GitHub
• URL: https://github.com/mounishvatti/pothole_detection_yolov8
• Owner: mounishvatti
• License: mit
• Created: 2023-10-30T20:09:36.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-02-29T06:33:03.000Z (7 months ago)
• Last Synced: 2024-04-29T17:58:43.197Z (5 months ago)
• Topics: image-segmentation, machine-learning, pothole-detection, roboflow, ultralytics, yolov8
• Language: Jupyter Notebook
• Homepage:
• Size: 24.9 MB
• Stars: 6
• Watchers: 1
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-yolo-object-detection - mounishvatti/pothole_detection_yolov8
• awesome-yolo-object-detection - mounishvatti/pothole_detection_yolov8

README

        
![3](https://github.com/mounishvatti/pothole_detection_yolov8/assets/76279858/5e5a2ea1-c512-4c86-b0e6-b8128c997503)

Image Segmentation & Pothole Detection


## Google Colab File Link (A Single Click Solution)

The google colab file link for yolov8 segmentation and tracking is provided below, you can check the implementation in Google Colab, and its a single click implementation

,you just need to select the Run Time as GPU, and click on Run All.

[`Google Colab File`](https://colab.research.google.com/drive/17SLXw-wdHG2syQhLSHH5r5_rkZx5poo0)

## Tech stack

![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)

## Object Segmentation and Tracking (ID + Trails)  using YOLOv8 on Custom Data

Clone the repository


```bash

!git clone https://github.com/mounishvatti/pothole_detection_yolov8.git

```

Goto the cloned folder


```bash

cd pothole_detection_yolov8

```

Install the Dependencies


```bash

!pip install ultralytics

```

```bash

!pip install roboflow

```

```bash

!pip install fastapi kaleido python_multipart uvicorn

```

Importing YOLO and a roboflow workspace for Image Segmentation


```python

from roboflow import Roboflow

rf = Roboflow(api_key="{the api key}")

project = rf.workspace("{name of workspace}").project("name-of-project")

dataset = project.version(1).download("yolov8")

```

> [!NOTE]

> If you are unable to perform the commands after importing the dataset from roboflow, you can access the same dataset by downloading it, upload it to your personal drive and mount the drive to your Google Colab 

My roboflow workspace containing the pothole dataset


[`Roboflow Workspace`](https://app.roboflow.com/vit-76kid/pothole-detection-project-3yiqt/1)

Run the code with mentioned command below.

- For training the data

```python

!yolo task=detect mode=train model=yolov8m.pt data={dataset.location}/data.yaml epochs={number of epochs} imgsz=640

```

- For yolov8 segmentation + Tracking & prediction

```python

!yolo task=detect mode=predict model={HOME}/runs/detect/train/weights/best.pt conf=0.25 source='/content/drive/MyDrive/demo.mp4'

```