Awesome

TGRS preprint paper

We have two contributions:

we first introduced the "Offset Token" concept and its decode-encode methods. This is a very big contribution, which brings the former method in BFE into the era of the Transformer and Foundation Models.
We newly discovered a common pattern of predicting offsets.

<br /> <div align="center"> <a href="https://github.com"> <img src="images/logo2.png" alt="Logo" width="256" height="256"> </a> <h3 align="center">Extract Building Footprint from Aerial Images with Offset-Building Model (OBM)</h3> <p align="center"> Extract building footprint like a human <br /> <a href="https://github.com/"><strong>Explore the docs »</strong></a> <br /> <br /> <a href="https://github.com/">View Demo</a> · <a href="https://github.com/issues">Report Bug</a> · <a href="https://github.com/issues">Request Feature</a> </p> </div>  <details> <summary>Table of Contents</summary> <ol> <li> <a href="#What is OBM?">What is OBM?</a> <ul> <li><a href="#built-with">Built With</a></li> </ul> </li> <li> <a href="#getting-started">Getting Started</a> <ul> <li><a href="#prerequisites">Prerequisites</a></li> <li><a href="#installation">Installation</a></li> </ul> </li> <li><a href="#usage">Usage</a></li> <li><a href="#Workflow and Results">Results</a></li> <li><a href="#license">License</a></li> <li><a href="#contact">Contact</a></li> </ol> </details>

What is OBM?


(a) OBM Model	(b) ROAM module

We first proposed a novel interactive model for footprint extraction and designed a series of Distance NMS algorithms tailored for the Building Footprint Extraction (BFE) problem. We also designed new metrics to measure the interactive BFE model.

Based on our accurate extraction of the roof and root-to-footprint offset. We can rebuild buildings' relative height maps.

(a) illustrates our structure which inherits from the Segment Anything Model (SAM).

(b) gives out the structure of our core module, Reference Offset Adaptive Module (ROAM). During inference, based on the results of the base offset head, each building will classified by its length and then roam to the adaptive head. The final result is determined by the Basehead and adaptive head.

Our model reaches new SOTA:

A clear drop of offset error by 16.99%, increase roof boundary iou by 13.15%, on open dataset BONAI.
Without extra training, we tested all models on a newly annotated dataset for generalization, improving 20.29% in vector and 76.36% in offset angle.
DNMS series can bring extra gain in all situations.

Built With

Our work is based on the following:

<p align="right">(<a href="#readme-top">back to top</a>)</p> Our weight of OBM is available at <a href="https://1drv.ms/u/c/4714078bb90d0216/EbVLDOlRwlZHr5h60nC3HuoBk1QrRFc6QqY_oXPCz-_3nA?e=Xbe1Qc" title="OBM_weight">OBM weight</a>.

Getting Started

This is a quick start of OBM.

Prerequisites

The code is built on the old version of mmdetection, and trained with a server that has 6x RTX3090.

ensure you have the correct CUDA and compatible torch version
```
nvidia-smi
```

Our runnable environments: pytorch 1.7.0, CUDA 11.1

Dataset

Downloads training images and test images from BONAI. We newly added building segementation label in our newly launched dataset which are avaliable with Huizhou together.

Installation

NOTE: Please follow the installation of BONAI and the early edition of MMdetection.

Usage

Train on your own dataset:

bash tools/dist_train.sh configs/obm_seg_fintune/smlcdr_obm_pretrain.py 6 # train with ROAM
bash tools/dist_train.sh configs/obm_seg/obm_seg_b.py 6 # train without ROAM

Inference your dataset:

python tools/test_offset.py --config configs/obm_seg/obm_seg_b.py

WARNING: OUR TRAINING DOES NOT SUPPORT FINETUNE LIKE LORA, BACKBONE IS INCLUDED, PLEASE SET `samples_per_gpu = 1` !!!

WARNING: PLEASE SET `samples_per_gpu = 1` WHILE INFERENCING !!!

Improve offset quality:

# using function fixangle()
## parameter: model = 'max' represents DNMS
## parameter: model = 'guassia_std' represents soft-DNMS

python tools/postprocess_offset.py

Visualize your results:


# we provide two kinds of visualizing functions: 
## 1: vis_3d() for relative height maps. 
## 2:  vis_boundary_offset: for roof and footprint boundary. 
python tools/visual_offset.py 

# if you want to visualize the results of LOFT in BONAI
python tools/visual_instance_seg.py

Workflow and Results

Our model simulates the process of how a human annotates a footprint.

1. At the `first` stage, we input an image with some prompts to imply buildings' rough location, using box prompts as an example:

2. `Then` Our OBM will give out roof segmentation and a roof-to-footprint offset for each prompt.

3. `Finally`, we drag the roof to its footprint via the offset.

We provide two kinds of operation: one is to directly get footprints, and the other is to get the relative height maps.

License

Distributed under the MIT License. See LICENSE.txt for more information.

Contact

<p align="right">(<a href="#readme-top">back to top</a>)</p> Offset tokens are hard to train; they are very sensitive to the settings. If you have any problems training the offset tokens, please contact me by likai211#mails.ucas.ac.cn or kaili37-c#my.cityu.edu.hk. I think my experience of failure in training will help you train your model. You can also contact me for any building-related problem or collaboration.

Citing

@ARTICLE{obm,
  author={Li, Kai and Deng, Yupeng and Kong, Yunlong and Liu, Diyou and Chen, Jingbo and Meng, Yu and Ma, Junxian and Wang, Chenhao},
  journal={IEEE Transactions on Geoscience and Remote Sensing}, 
  title={Prompt-Driven Building Footprint Extraction in Aerial Images with Offset-Building Model}, 
  year={2024},
  volume={},
  number={},
  pages={1-1},
  keywords={Buildings;Prediction algorithms;Production;Data models;Data mining;Remote sensing;Instance segmentation;Feature extraction;Training;Three-dimensional displays;Building footprint extraction;Roof segmentation;Roof-to-footprint offset extraction;Segment Anything Model (SAM);Non-Maximum Suppression(NMS)},
  doi={10.1109/TGRS.2024.3487652}}