GitHub / shukur-alom / Parking-Free-Space-Detection-Using-Computer-Vision
This project utilizes the custom object detection model to monitor parking spaces in a video feed. It identifies vehicles in the video and overlays polygons representing parking spaces on the frames. The program then calculates the number of occupied and free parking spaces based on the detected vehicles and the predefined parking space polygons.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shukur-alom%2FParking-Free-Space-Detection-Using-Computer-Vision
PURL: pkg:github/shukur-alom/Parking-Free-Space-Detection-Using-Computer-Vision
Stars: 9
Forks: 1
Open issues: 0
License: mit
Language: Python
Size: 535 MB
Dependencies parsed at: Pending
Created at: over 1 year ago
Updated at: 8 months ago
Pushed at: about 1 year ago
Last synced at: 5 months ago
Topics: artificial-intelligence, artificial-neural-networks, artificialintelligence, car-detection, carparking, carparkingsystem, computer-vision, deep-learning, machine-learning, object-detection, parking-lot, parking-management, parking-slot-detection, parking-space, parking-spots, python, python3, pytorch, yolov8
model
v1.0.0
Develop a deep learning model using the YOLOv8 architecture to accurately detect cars in aerial imagery captured by drones. This model will be trained on the VisDrone dataset, which offers a rich collection of drone-captured images with diverse scenarios and object annotations.
Benefits:
-
Enhanced Car Detection: The custom YOLOv8 model will be specifically tailored to identify cars in drone footage, potentially surpassing the performance of generic object detection models on this task.
-
Improved Performance in Drone-Specific Conditions: Training on the VisDrone dataset, which includes variations in lighting, weather, and object density, will help the model generalize better to real-world drone footage.
Download