---
tags:
- curb ramp detection
- accessibility
license: mit
datasets:
- projectsidewalk/rampnet-dataset
base_model:
- timm/convnextv2_base.fcmae_ft_in22k_in1k_384
pipeline_tag: object-detection
---

**RampNet** is a two-stage pipeline that addresses the scarcity of curb ramp detection datasets by using government location data to automatically generate over 210,000 annotated Google Street View panoramas. This new dataset is then used to train a state-of-the-art curb ramp detection model that significantly outperforms previous efforts. In this repo, we provide the checkpoint for our curb ramp detection model.



**Usage:**

*For a step-by-step walkthrough, see our [Google Colab notebook](https://colab.research.google.com/drive/1TOtScud5ac2McXJmg1n_YkOoZBchdn3w?usp=sharing), which includes a visualization in addition to the code below.*
```py
import torch
from transformers import AutoModel
from PIL import Image
import numpy as np
from torchvision import transforms
from skimage.feature import peak_local_max

IMAGE_PATH = "example.jpg"
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")

model = AutoModel.from_pretrained("projectsidewalk/rampnet-model", trust_remote_code=True).to(DEVICE).eval()

preprocess = transforms.Compose([
    transforms.Resize((2048, 4096), interpolation=transforms.InterpolationMode.BILINEAR),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

img = Image.open(IMAGE_PATH).convert("RGB")
img_tensor = preprocess(img).unsqueeze(0).to(DEVICE)

with torch.no_grad():
    heatmap = model(img_tensor).squeeze().cpu().numpy()

peaks = peak_local_max(np.clip(heatmap, 0, 1), min_distance=10, threshold_abs=0.5)
scale_w = img.width / heatmap.shape[1]
scale_h = img.height / heatmap.shape[0]
coordinates = [(int(c * scale_w), int(r * scale_h)) for r, c in peaks]

# Coordinates of detected curb ramps
print(coordinates)
```

![Example of Curb Ramp Points](https://i.postimg.cc/66fQm4m5/labeled.png)


If you get an error like this (see below), then you need to update your transformers library version.
```
>>> model = AutoModel.from_pretrained("projectsidewalk/rampnet-model", trust_remote_code=True)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/gscratch/scrubbed/jsomeara/envs/sidewalk-validator-ai/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 558, in from_pretrained
    model_class = add_generation_mixin_to_remote_model(model_class)
  File "/gscratch/scrubbed/jsomeara/envs/sidewalk-validator-ai/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 726, in add_generation_mixin_to_remote_model
    has_custom_generate = "GenerationMixin" not in str(getattr(model_class, "generate"))
AttributeError: type object 'KeypointModel' has no attribute 'generate'
>>>
```

Citation:

```bibtex
@inproceedings{omeara2025rampnet,
  author    = {John S. O'Meara and Jared Hwang and Zeyu Wang and Michael Saugstad and Jon E. Froehlich},
  title     = {{RampNet: A Two-Stage Pipeline for Bootstrapping Curb Ramp Detection in Streetscape Images from Open Government Metadata}},
  booktitle = {{ICCV'25 Workshop on Vision Foundation Models and Generative AI for Accessibility: Challenges and Opportunities (ICCV 2025 Workshop)}},
  year      = {2025},
  doi       = {https://doi.org/10.48550/arXiv.2508.09415},
  url       = {https://cv4a11y.github.io/ICCV2025/index.html},
  note      = {DOI: forthcoming}
}
```