🚀 遥感屋顶检测模型
本模型专为遥感任务中的屋顶检测而设计,能够高效准确地识别卫星图像中的屋顶目标,为相关领域的研究和应用提供有力支持。
🚀 快速开始
使用以下代码开始使用该模型:
from transformers import AutoModelForObjectDetection, AutoImageProcessor
import torch
import cv2
image_path=YOUR_IMAGE_PATH
image = cv2.imread(image_path)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoModelForObjectDetection.from_pretrained("Yifeng-Liu/rt-detr-finetuned-for-satellite-image-roofs-detection")
image_processor = AutoImageProcessor.from_pretrained("Yifeng-Liu/rt-detr-finetuned-for-satellite-image-roofs-detection")
CONFIDENCE_TRESHOLD = 0.5
with torch.no_grad():
model.to(device)
inputs = image_processor(images=image, return_tensors='pt').to(device)
outputs = model(**inputs)
target_sizes = torch.tensor([image.shape[:2]]).to(device)
results = image_processor.post_process_object_detection(
outputs=outputs,
threshold=CONFIDENCE_TRESHOLD,
target_sizes=target_sizes
)[0]
✨ 主要特性
- 适用任务:针对遥感任务的目标检测。
- 开源许可:采用MIT许可证。
📚 详细文档
模型详情
模型描述
属性 |
详情 |
模型类型 |
用于遥感任务的目标检测模型 |
许可证 |
MIT |
模型来源
模型局限性
⚠️ 重要提示
模型的直接和下游用户都应了解该模型存在的风险、偏差和局限性。
评估指标
任务类型 |
数据集 |
指标类型 |
指标值 |
指标名称 |
目标检测 |
keremberke/satellite-building-segmentation |
AP (IoU=0.50:0.95) |
0.434 |
AP @ IoU=0.50:0.95 | area=all | maxDets=100 |
目标检测 |
keremberke/satellite-building-segmentation |
AP (IoU=0.50) |
0.652 |
AP @ IoU=0.50 | area=all | maxDets=100 |
目标检测 |
keremberke/satellite-building-segmentation |
AP (IoU=0.75) |
0.464 |
AP @ IoU=0.75 | area=all | maxDets=100 |
目标检测 |
keremberke/satellite-building-segmentation |
AP (IoU=0.50:0.95) 小目标 |
0.248 |
AP @ IoU=0.50:0.95 | area=small | maxDets=100 |
目标检测 |
keremberke/satellite-building-segmentation |
AP (IoU=0.50:0.95) 中等目标 |
0.510 |
AP @ IoU=0.50:0.95 | area=medium | maxDets=100 |
目标检测 |
keremberke/satellite-building-segmentation |
AP (IoU=0.50:0.95) 大目标 |
0.632 |
AP @ IoU=0.50:0.95 | area=large | maxDets=100 |
目标检测 |
keremberke/satellite-building-segmentation |
AR (IoU=0.50:0.95) maxDets=1 |
0.056 |
AR @ IoU=0.50:0.95 | area=all | maxDets=1 |
目标检测 |
keremberke/satellite-building-segmentation |
AR (IoU=0.50:0.95) maxDets=10 |
0.328 |
AR @ IoU=0.50:0.95 | area=all | maxDets=10 |
目标检测 |
keremberke/satellite-building-segmentation |
AR (IoU=0.50:0.95) maxDets=100 |
0.519 |
AR @ IoU=0.50:0.95 | area=all | maxDets=100 |
目标检测 |
keremberke/satellite-building-segmentation |
AR (IoU=0.50:0.95) 小目标 |
0.337 |
AR @ IoU=0.50:0.95 | area=small | maxDets=100 |
目标检测 |
keremberke/satellite-building-segmentation |
AR (IoU=0.50:0.95) 中等目标 |
0.601 |
AR @ IoU=0.50:0.95 | area=medium | maxDets=100 |
目标检测 |
keremberke/satellite-building-segmentation |
AR (IoU=0.50:0.95) 大目标 |
0.714 |
AR @ IoU=0.50:0.95 | area=large | maxDets=100 |
📄 许可证
本模型采用MIT许可证。