DeepRoadMapper: Extracting Road Topology from Aerial Images

By Gellért Máttyus, Wenjie Luo, Raquel Urtasun. IEEE International Conference on Computer Vision, 2017

489 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Environmental Engineering, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/11d4bac69cf940cb13c2cac9a5b1e3af64960fce

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ling Shao
2. Deng-Ping Fan
3. Ming-Ming Cheng
4. Luc Van Gool
5. Jianbing Shen
6. Ming-Hsuan Yang
7. Junwei Han
8. Wenguan Wang

In Environmental Engineering

1. Jan Dirk Wegner
2. Zuoyue Li
3. Aurélien Lucchi
4. Chuang Zhang
5. Ming Wu
6. Lichen Zhou
7. Ling Shao
8. Sergio Casas

In Ocean Engineering

1. Chuang Zhang
2. Ming Wu
3. Lichen Zhou
4. Zuoyue Li
5. Aurélien Lucchi
6. Jan Dirk Wegner
7. Hari Balakrishnan
8. Raquel Urtasun

Citations in the corpus

• MP3: A Unified Model to Map, Perceive, Predict and Plan (2021, background): “Online Mapping: While there are many offline mapping approaches [4, 22, 33], these rely on satellite imagery or multiple passes through the same scene with a data collection vehicle to gather dense information, and often involve a human-in-the-loop.”
• D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction (2018, methodology): “Most of these methods can be seperated into three categories: generating pixel-level labeling of roads [1, 2], detecting skeletons of roads [3, 4] and a combination of both [5, 6].”
• Topological Map Extraction From Overhead Images (2018, methodology): “We compare the results of our method to the state-of-the-art methods DeepRoadMapper [32] and RoadTracer [4].”
• DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images (2018, methodology): “Following the example-based generation idea, another approach is to use already existing data resources, such as aerial images [37, 38], or geostationary satellite images [26, 58].”
• Salient Object Detection via Integrity Learning (2021, methodology): “In this work, in addition to the BCE loss, we also use the IoU loss [52], [74].”
• RoadTracer: Automatic Extraction of Road Networks from Aerial Images (2018, methodology): “1 In fact, even obtaining “ground truth” maps in well-traveled areas may be difficult; recent work [10] reported that the discrepancy between OpenStreetMap (OSM) and the TorontoCity dataset was 14% (the recall according to a certain metric for OSM was 0.”