A Deep Learning Approach to an Enhanced Building Footprint and Road Detection in High-Resolution Satellite Imagery

Ayala, Christian; Sesma, Rubén; Aranda, Carlos Monserrat; Galar, Mikel

doi:10.3390/rs13163135

Cited by 28 publications

(27 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past few years, U-Nets [22], and variants of region-based convolutional neural networks (R-CNNs) [23], have become popular DNN-based approaches for object detection and segmentation in the greater computer vision community, including within the computer vision remote sensing (CVRS) domain. Some examples of the use of U-Nets in CVRS include building detection from high-resolution multispectral imagery [24], and building footprint and road detection within OpenStreetMap (OSM) fused with Sentinel-1 and 2 imagery [25].…”

Section: Related Workmentioning

confidence: 99%

Tracking the industrial growth of modern China with high-resolution panchromatic imagery: A sequential convolutional approach

Brewer¹,

Lv²,

Runfola³

2023

Preprint

View full text Add to dashboard Cite

Due to insufficient or difficult to obtain data on development in inaccessible regions, remote sensing data is an important tool for interested stakeholders to collect information on economic growth. To date, no studies have utilized deep learning to estimate industrial growth at the level of individual sites. In this study, we harness high-resolution panchromatic imagery to estimate development over time at 419 industrial sites in the People's Republic of China using a multi-tier computer vision framework. We present two methods for approximating development: (1) structural area coverage estimated through a Mask R-CNN segmentation algorithm, and (2) imputing development directly with visible & infrared radiance from the Visible Infrared Imaging Radiometer Suite (VIIRS). Labels generated from these methods are comparatively evaluated and tested. On a dataset of 2,078 50 cm resolution images spanning 19 years, the results indicate that two dimensions of industrial development can be estimated using high-resolution daytime imagery, including (a) the total square meters of industrial development (average error of 0.021 km 2 ), and (b) the radiance of lights (average error of 9.8 nW cm 2 sr ). Trend analysis of the techniques reveal estimates from a Mask R-CNN-labeled CNN-LSTM track ground truth measurements most closely. The Mask R-CNN estimates positive growth at every site from the oldest image to the most recent, with an average change of 4,084 m 2 .Keywords remote sensing • computer vision • development • satellite imagery • econometrics

show abstract

Section: Related Workmentioning

confidence: 99%

Tracking the industrial growth of modern China with high-resolution panchromatic imagery: A sequential convolutional approach

Brewer¹,

Lv²,

Runfola³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, given the limited spatial resolution of S1 and S2 (10 m), multiple classes may coexist within the same pixel, drastically increasing the complexity since the separability of the classes is reduced. These difficulties were experienced in our previous work [24], which was focused on the extraction of buildings and roads from S1 and S2 imagery. Binary decomposition strategies, such as OVO and OVA, address multi-class problems learning multiple binary models.…”

Section: Problem Statementmentioning

confidence: 99%

“…Despite the lack of high-resolution satellite imagery datasets, there are freely available geodatabases that can be used to generate ground truth masks for training deep learning models. Therefore, in this work, we have followed the methodology described by Ayala et al [24]. Accordingly, we have used OpenStreetMap's (OSM) [47] building and road labels, in combination with S1 and S2 to generate training and testing areas.…”

Section: Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Class Strategies for Joint Building Footprint and Road Detection in Remote Sensing

2021

Self Cite

View full text Add to dashboard Cite

Building footprints and road networks are important inputs for a great deal of services. For instance, building maps are useful for urban planning, whereas road maps are essential for disaster response services. Traditionally, building and road maps are manually generated by remote sensing experts or land surveying, occasionally assisted by semi-automatic tools. In the last decade, deep learning-based approaches have demonstrated their capabilities to extract these elements automatically and accurately from remote sensing imagery. The building footprint and road network detection problem can be considered a multi-class semantic segmentation task, that is, a single model performs a pixel-wise classification on multiple classes, optimizing the overall performance. However, depending on the spatial resolution of the imagery used, both classes may coexist within the same pixel, drastically reducing their separability. In this regard, binary decomposition techniques, which have been widely studied in the machine learning literature, are proved useful for addressing multi-class problems. Accordingly, the multi-class problem can be split into multiple binary semantic segmentation sub-problems, specializing different models for each class. Nevertheless, in these cases, an aggregation step is required to obtain the final output labels. Additionally, other novel approaches, such as multi-task learning, may come in handy to further increase the performance of the binary semantic segmentation models. Since there is no certainty as to which strategy should be carried out to accurately tackle a multi-class remote sensing semantic segmentation problem, this paper performs an in-depth study to shed light on the issue. For this purpose, open-access Sentinel-1 and Sentinel-2 imagery (at 10 m) are considered for extracting buildings and roads, making use of the well-known U-Net convolutional neural network. It is worth stressing that building and road classes may coexist within the same pixel when working at such a low spatial resolution, setting a challenging problem scheme. Accordingly, a robust experimental study is developed to assess the benefits of the decomposition strategies and their combination with a multi-task learning scheme. The obtained results demonstrate that decomposing the considered multi-class remote sensing semantic segmentation problem into multiple binary ones using a One-vs-All binary decomposition technique leads to better results than the standard direct multi-class approach. Additionally, the benefits of using a multi-task learning scheme for pushing the performance of binary segmentation models are also shown.

show abstract

“…To assess the usefulness of the proposed approach both building and road semantic segmentation problems have been considered following the experimental framework in (Ayala et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Multi-Temporal Data Augmentation for High Frequency Satellite Imagery: A Case Study in Sentinel-1 and Sentinel-2 Building and Road Segmentation

Ayala

Aranda

Galar

2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Semantic segmentation of remote sensing images has many practical applications such as urban planning or disaster assessment. Deep learning-based approaches have shown their usefulness in automatically segmenting large remote sensing images, helping to automatize these tasks. However, deep learning models require large amounts of labeled data to generalize well to unseen scenarios. The generation of global-scale remote sensing datasets with high intraclass variability presents a major challenge. For this reason, data augmentation techniques have been widely applied to artificially increase the size of the datasets. Among them, photometric data augmentation techniques such as random brightness, contrast, saturation, and hue have been traditionally applied aiming at improving the generalization against color spectrum variations, but they can have a negative effect on the model due to their synthetic nature. To solve this issue, sensors with high revisit times such as Sentinel-1 and Sentinel-2 can be exploited to realistically augment the dataset. Accordingly, this paper sets out a novel realistic multi-temporal color data augmentation technique. The proposed methodology has been evaluated in the building and road semantic segmentation tasks, considering a dataset composed of 38 Spanish cities. As a result, the experimental study shows the usefulness of the proposed multi-temporal data augmentation technique, which can be further improved with traditional photometric transformations.

show abstract

A Deep Learning Approach to an Enhanced Building Footprint and Road Detection in High-Resolution Satellite Imagery

Cited by 28 publications

References 60 publications

Tracking the industrial growth of modern China with high-resolution panchromatic imagery: A sequential convolutional approach

Tracking the industrial growth of modern China with high-resolution panchromatic imagery: A sequential convolutional approach

Multi-Class Strategies for Joint Building Footprint and Road Detection in Remote Sensing

Multi-Temporal Data Augmentation for High Frequency Satellite Imagery: A Case Study in Sentinel-1 and Sentinel-2 Building and Road Segmentation

Contact Info

Product

Resources

About