PaRK-Detect: Towards Efficient Multi-Task Satellite Imagery Road Extraction via Patch-Wise Keypoints Detection
Shenwei Xie (Beijing University of Posts and Telecommunications),* Wanfeng Zheng (Beijing University of Posts and Telecommunications), Zhenglin Xian (Beijing University of Posts and Telecommunications), Junli Yang (Beijing University of Posts and Telecommunications), Chuang Zhang (Beijing University of Posts and Telecommunications), Ming Wu (Beijing University of Posts and Telecommunications)
The 33rd British Machine Vision Conference
Abstract
Automatically extracting roads from satellite imagery is a fundamental yet challenging computer vision task in the field of remote sensing. Pixel-wise semantic segmentation-based approaches and graph-based approaches are two prevailing schemes. However, prior works show the imperfections that semantic segmentation-based approaches yield road graphs with low connectivity, while graph-based methods with iterative exploring paradigms and smaller receptive fields focus more on local information and are also time-consuming. In this paper, we propose a new scheme for multi-task satellite imagery road extraction, Patch-wise Road Keypoints Detection (PaRK-Detect). Building on top of D-LinkNet architecture and adopting the structure of keypoint detection, our framework predicts the position of patch-wise road keypoints and the adjacent relationships between them to construct road graphs in a single pass. Meanwhile, the multi-task framework also performs pixel-wise semantic segmentation and generates road segmentation masks. We evaluate our approach against the existing state-of-the-art methods on DeepGlobe, Massachusetts Roads, and RoadTracer datasets and achieve competitive or better results. We also demonstrate a considerable outperformance in terms of inference speed.Video
Citation
@inproceedings{Xie_2022_BMVC,
author = {Shenwei Xie and Wanfeng Zheng and Zhenglin Xian and Junli Yang and Chuang Zhang and Ming Wu},
title = {PaRK-Detect: Towards Efficient Multi-Task Satellite Imagery Road Extraction via Patch-Wise Keypoints Detection},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0381.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by