A CNN-Based Approach for Automatic Building Detection and Recognition of Roof Types Using a Single Aerial Image

Alidoost, F.; Arefi, Hossein

doi:10.1007/s41064-018-0060-5

Cited by 33 publications

(22 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Maximum number of fully connected layers was set to 1 in order to reduce the memory and computational cost of training the network during the evolutive design stage. The maximum number of neurons on those layers was kept small for the same reason (8,16,32).…”

Section: Methodsmentioning

confidence: 99%

“…Under this category of data, large-scale aerial image processed as orthophotography is a useful source of information for many domains. To give some examples of the broad array of applications we can find, there have been systems developed for the detection of coastline changes [2], snow avalanches [3], fires [4], bodies in disaster sites [5], trees [6], seedlings [7], roofs [8], transmission towers [9,10], vehicles [11,12], photovoltaic arrays [13,14], vegetation and buildings [15]. We focus on road detection on aerial images being it an important subject, among other things, due to the need to constantly update road maps.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Grammar Guided Genetic Programming for Network Architecture Search and Road Detection on Aerial Orthophotography

Castillo¹,

Díaz-Álvarez²,

Callejo³

et al. 2020

Preprint

View full text Add to dashboard Cite

Photogrammetry involves aerial photography of the earth’s surface and subsequently processing the images to provide a more accurate depiction of the area (Orthophotography). It’s used by the Spanish Instituto Geográfico Nacional to update road cartography but requires a significant amount of manual labor due to the need to perform visual inspection of all tiled images. Deep Learning techniques (artificial neural networks with more than one hidden layer) can perform road detection but it is still unclear how to find the optimal network architecture. Our system applies grammar guided genetic programming to the search of deep neural network architectures. In this kind of evolutive algorithm all the population individuals (here candidate network architectures) are constrained to rules specified by a grammar that defines valid and useful structural patterns to guide the search process. Grammar used includes well-known complex structures (e.g. Inception-like modules) combined with a custom designed mutation operator (dynamically links the mutation probability to structural diversity). Pilot results show that the system is able to design models for road detection that obtain test accuracies similar to that reached by state of the art models when evaluated over a dataset from the Spanish National Aerial Orthophotography Plan.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Grammar Guided Genetic Programming for Network Architecture Search and Road Detection on Aerial Orthophotography

Castillo¹,

Díaz-Álvarez²,

Callejo³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Another important area of research is related to the task of building detection and mapping using remote sensing imagery. In [12], a fine-tuned version of VGGNet is used to detect buildings and recognize the roof types, obtaining quality rates higher than 83.3%. The authors of [13] evaluated the performance of deep learning for roof segmentation on a dataset containing over 220,000 buildings tagged in remote sensing images with a spatial resolution of 7.5 cm and obtained F1-scores of maximum 0.947.…”

Section: Related Workmentioning

confidence: 99%

A Framework Based on Nesting of Convolutional Neural Networks to Classify Secondary Roads in High Resolution Aerial Orthoimages

et al. 2020

View full text Add to dashboard Cite

Remote sensing imagery combined with deep learning strategies is often regarded as an ideal solution for interpreting scenes and monitoring infrastructures with remarkable performance levels. In addition, the road network plays an important part in transportation, and currently one of the main related challenges is detecting and monitoring the occurring changes in order to update the existent cartography. This task is challenging due to the nature of the object (continuous and often with no clearly defined borders) and the nature of remotely sensed images (noise, obstructions). In this paper, we propose a novel framework based on convolutional neural networks (CNNs) to classify secondary roads in high-resolution aerial orthoimages divided in tiles of 256 × 256 pixels. We will evaluate the framework’s performance on unseen test data and compare the results with those obtained by other popular CNNs trained from scratch.

show abstract

“…Compared with satellite images applied to remote sensing applications, aerial images, acquired by both aircrafts and Unmanned Aerial Vehicles (UAVs), offer an affordable, fast and effective approach for acquisition of high resolution multi-view aerial images over small areas. However, because of spatial variation of buildings, including shape, size, materials, colour, structure, and interference of building shadows, building detection and extracting building boundaries from single aerial images are often challenging and need manual works (Alidoost and Arefi, 2018). Several methods are available for extracting buildings from a single image.…”

Section: Introductionmentioning

confidence: 99%

Building Outline Extraction From Aerial Images Using Convolutional Neural Networks

Alidoost

Arefi

Tombari

2019

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

View full text Add to dashboard Cite

Abstract. Automatic detection and extraction of buildings from aerial images are considerable challenges in many applications, including disaster management, navigation, urbanization monitoring, emergency responses, 3D city mapping and reconstruction. However, the most important problem is to precisely localize buildings from single aerial images where there is no additional information such as LiDAR point cloud data or high resolution Digital Surface Models (DSMs). In this paper, a Deep Learning (DL)-based approach is proposed to localize buildings, estimate the relative height information, and extract the buildings’ boundaries using a single aerial image. In order to detect buildings and extract the bounding boxes, a Fully Connected Convolutional Neural Network (FC-CNN) is trained to classify building and non-building objects. We also introduced a novel Multi-Scale Convolutional-Deconvolutional Network (MS-CDN) including skip connection layers to predict normalized DSMs (nDSMs) from a single image. The extracted bounding boxes as well as predicted nDSMs are then employed by an Active Contour Model (ACM) to provide precise boundaries of buildings. The experiments show that, even having noises in the predicted nDSMs, the proposed method performs well on single aerial images with different building shapes. The quality rate for building detection is about 86% and the RMSE for nDSM prediction is about 4 m. Also, the accuracy of boundary extraction is about 68%. Since the proposed framework is based on a single image, it could be employed for real time applications.

show abstract

A CNN-Based Approach for Automatic Building Detection and Recognition of Roof Types Using a Single Aerial Image

Cited by 33 publications

References 58 publications

Grammar Guided Genetic Programming for Network Architecture Search and Road Detection on Aerial Orthophotography

Grammar Guided Genetic Programming for Network Architecture Search and Road Detection on Aerial Orthophotography

A Framework Based on Nesting of Convolutional Neural Networks to Classify Secondary Roads in High Resolution Aerial Orthoimages

Building Outline Extraction From Aerial Images Using Convolutional Neural Networks

Contact Info

Product

Resources

About