https://github.com/gregoritsch3/dl_yolo_cv
https://github.com/gregoritsch3/dl_yolo_cv
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/gregoritsch3/dl_yolo_cv
- Owner: Gregoritsch3
- Created: 2025-01-07T14:23:07.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2025-02-13T19:03:47.000Z (3 months ago)
- Last Synced: 2025-02-13T19:39:55.147Z (3 months ago)
- Language: Jupyter Notebook
- Size: 0 Bytes
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# DL_YOLO_CV
The repository contains two files containing code:
- The first is the notebook that is concerned with carrying out object detection inference on images and videos using the ```Ultralytics YOLOv8``` Python library.
- The second is the main.py script that carries out object detection in real time through a webcam to detect whether objects are present inside a zone - the right hand side of the screen dynamically defined by a red rectangle. The zone does not show the presence of the class 'person' amongst its detections. Additionally, an agnostic Non-Max-Suppression (a-NMS) algorithm is included so as to prevent superfluous bounding boxes from being applied to the same object, or objects very near to each other, regardless of class. The bounding boxes are realised through the ```supervision``` library, while the dynamic command-line level window specification is brought about through the ```argparse``` library.
Most of the exercise code is inspired by two Roboflow YOLOv8 YouTube tutorials that can be found at the following URLs:
1. https://www.youtube.com/watch?v=wuZtUMEiKWY&list=PLZCA39VpuaZZ1cjH4vEIdXIb0dCpZs3Y5
2. https://www.youtube.com/watch?v=wuZtUMEiKWY&list=PLZCA39VpuaZZ1cjH4vEIdXIb0dCpZs3Y5