S

Segformer B3 Finetuned UAVid

Developed by chribark
This model is an image segmentation model fine-tuned on drone image datasets based on nvidia/segformer-b3-finetuned-ade-512-512, suitable for scene parsing tasks.
Downloads 276
Release Time : 5/3/2024

Model Overview

SegFormer-B3 is an efficient image segmentation model, fine-tuned specifically for processing scene segmentation tasks in images captured by drones. It can identify and segment multiple objects and scene elements in images.

Model Features

Efficient Scene Parsing
Capable of accurately identifying and segmenting multiple scene elements in drone images.
High-Precision Segmentation
Demonstrates high segmentation accuracy for key elements such as buildings, roads, and trees.
Lightweight Architecture
Based on the SegFormer-B3 architecture, it maintains high efficiency while preserving performance.

Model Capabilities

Image Segmentation
Scene Understanding
Object Recognition
Drone Image Processing

Use Cases

Urban Planning
Urban Landscape Analysis
Analyze drone-captured urban images to identify infrastructure such as buildings and roads.
Building accuracy 95.35%, road accuracy 89.48%
Environmental Monitoring
Vegetation Coverage Analysis
Assess tree coverage in specific areas.
Tree accuracy 94.15%
Traffic Monitoring
Vehicle Detection
Identify and count vehicles on roads.
Car accuracy 70.86%
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase