Comparison of Different U-Net Models for Building Extraction from High-Resolution Aerial Imagery

Erdem, Fırat; Avdan, Uğur

doi:10.30897/ijegeo.684951

Cited by 20 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this case, the recognition process does not require significant computing resources at the stage of using the model. Compared to [21], this model has a 3 % higher precision of object recognition in images. That was achieved by adding data layers, converting, normalizing data, error, calculating the mean error and parameters to complement the data, as well as FCN, and deleting layers of input/output data, and layer pooling.…”

Section: Discussion Of Results Of Studying the Recognition Of Objects In Images Using Convolutional Neural Networkmentioning

confidence: 95%

“…Therefore, the comparison was carried out according to the criterion for assessing mean accuracy estimate with some well-known GoogLeNet-based models, developed according to similar parameters, trained on the basis of images acquired from UAV cameras. GoogLeNet-like (Switzerland), In-ceptionResNetV2 (Turkey), U-Net Inception-ResNetV2 (Turkey) were chosen as such models [20,21]. The results of assessing the mean accuracy of the models are given in Table 8.…”

Section: Assessing the Inria-9 Trained Model For Object Recognition In Imagesmentioning

confidence: 99%

“…Table 8 shows that the highest mean accuracy estimate, namely 75 %, is demonstrated by the Inria-10 model, as others were trained based on images acquired from UAV cameras that were not part of the INRIA set. We estimated the adequacy, reliability, and convergence between the Inria-10 model and others [20,21]. To this end, the recognition of 100 manually marked images from the set NVidia Aerial Drone Dataset (USA) [22] was performed.…”

Section: Assessing the Inria-9 Trained Model For Object Recognition In Imagesmentioning

confidence: 99%

See 2 more Smart Citations

Improving a model of object recognition in images based on a convolutional neural network

Knysh

Kulyk

2021

EEJET

View full text Add to dashboard Cite

This paper considers a model of object recognition in images using convolutional neural networks; the efficiency of the model-based process involving the training of deep layers in convolutional neural networks has been studied. There are objective difficulties associated with determining the optimal characteristics of neural networks, so there is an issue related to retraining a neural network. Eliminating the retraining by determining only the optimal number of epochs is insufficient since it does not provide high accuracy. The requirements for the set of images for model training and verification have been defined. These requirements are better met by the INRIA image set (France). GoogLeNet (USA) has been established to be a trained model that can perform object recognition on images but the object recognition reliability is insufficient. Therefore, it becomes necessary to improve the effectiveness of object recognition in images. It is advisable to use the GoogLeNet architecture to build a specialized model that, by changing the parameters and retraining some layers, could allow for better recognition of objects in images. Ten models were trained using the following parameters: learning speed, the number of epochs, an optimization algorithm, the type of learning speed change, a gamma or power coefficient, a pre-trained model. A convolutional neural network has been developed to improve the precision and efficiency of object recognition in images. The optimal neural network training parameters were determined: training speed, 0.000025; the number of epochs, 100; a power coefficient, 0.25, etc. A 3 % increase in precision was obtained, which makes it possible to assert the proper choice of the architecture for the developed network and the selection of its parameters. That allows this network to be used for practical tasks of object recognition in images.

show abstract

Section: Discussion Of Results Of Studying the Recognition Of Objects In Images Using Convolutional Neural Networkmentioning

confidence: 95%

Section: Assessing the Inria-9 Trained Model For Object Recognition In Imagesmentioning

confidence: 99%

Section: Assessing the Inria-9 Trained Model For Object Recognition In Imagesmentioning

confidence: 99%

See 1 more Smart Citation

Improving a model of object recognition in images based on a convolutional neural network

Knysh

Kulyk

2021

EEJET

View full text Add to dashboard Cite

show abstract

“…Supervised classification is used more often due to its high accuracy and reliability (Kavzoglu and Colkesen, 2010). Nonparametric classification methods such as decision tree (Nagel Yuan, 2016;(Zhang et al, 2018), support vector machines (Kavzoglu and Colkesen, 2009;Zhang et al, 2018;Karimi et al, 2019) and artificial neural networks (Hu and Weng, 2009;Mohapatra and Wu, 2010) can be used to classify remotely sensed images (Lu, et al, 2007;Çelik and Gazioğlu, 2020;Tonbul and Kavzoğlu, 2020;Erdem and Avdan;2020;Ozturk et al, 2020;Karagöl et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Determination of Land Use Change using Support Vector Machines: A Case Study of Arnavutkoy, Istanbul

Reis

Yilanci

2021

International Journal of Environment and Geoinformatics

View full text Add to dashboard Cite

As a result of the development of cities and inclination towards urbanization, natural areas decreased while urban areas increased. In this respect, determination of impermeable surfaces is important for the problems covering; effects of urbanization on natural environment, global environmental variation, urban atmospheric process, human activities and the effects of urbanization on the environment. Remote sensing images are used to examine and classify land cover/uses. Traditional classification methods are mainly divided into supervised classification and unsupervised classification. The aim of this study is to classify land cover/use and to state temporal change using the Support Vector Machines (SVM) approach, which is a supervised classification method. Arnavutkoy district of Istanbul was chosen as the study area for land use and change detection analysis. Landsat 5/7/8 satellite images of Arnavutkoy district were obtained and SVM process was applied to obtain these images. Firstly, four classes were created for each image: urban areas, vegetation, bare soils and wetlands SVM was applied and accuracy analysis was performed to the images classes of which were created before. CAD software and GIS software were used for image processing. The classification accuracy for SVM was found to be 98.66%, 98.31%, 98.95%, 97.99%, 96.37%, 97.90% (from 1995 to 2019). In addition, ROC analysis was used for comparison of accuracy analysis. As a result of this study, land cover/use change of Arnavutkoy district in the last 20 years has been determined. The urban area of the district was 40.99 km 2 in 1995 and 93.76 km 2 in 2019. In addition, the impact of the Europe's largest airport on land cover / use has been examined. The results showed that the accuracy of using SVM to classify land use/cover is high. Therefore, it has been proposed that this algorithm is used as an optimal classifier for land use/cover maps.

show abstract

“…Remote sensing data and techniques have been successfully used for building information extraction [5], and post-earthquake evaluation of collapsed buildings [6]. Also, high-resolution imagery from Unmanned Aerial Vehicle (UAV) in combination with elevation models [7] for extracting building inventory information.…”

Section: Introductionmentioning

confidence: 99%

PlanetScope Imagery for Extracting Building Inventory Information

Kaplan¹,

Kaplan²

2020

Iecg 2020

View full text Add to dashboard Cite

In order to prevent serious damages from a possible earthquake and to determine the possible losses, in settlements under earthquake risk, it is very important to extract building inventory information for further determination of the performance of existing buildings. As conventional methods, such as field investigations, can be time-consuming and costly on an urban scale, approaches that are able to speed up these processes and reduce the costs are required. Determining at least some of the data required to determine the seismic performance of an existing building using alternative methods instead of conventional methods will provide a significant advantage. The study aims to investigate the potential of PlanetScope satellite imagery for extracting building inventory information. Thus, the main objectives of the study are; to extract buildings using deep learning methods, and to determine the height and the construction period of the buildings. For this purpose, two 3-m PlanetScope satellite images were used over the study area located in Eskisehir, Turkey. Over thirty buildings were located in the study area. The results showed that with PlanetScope Imagery detached buildings can be detected with high accuracy using deep learning methods, their heights can be calculated, and the construction period can be determined. For future studies, the obtained information is planned to further be processed in a Geographical Information System (GIS) for building inventory and to be used for seismic vulnerability assessment studies of existing buildings.

show abstract

Comparison of Different U-Net Models for Building Extraction from High-Resolution Aerial Imagery

Abstract: International Symposium on Applied Geoinformatics (ISAG2019) was held in Istanbul on 7-9 November 2019. The symposium is organized with the aim of promoting the advancements to explore the latest scientific and technological developments and opportunities in the field of Geoinformatics.

Cited by 20 publications

References 25 publications

Improving a model of object recognition in images based on a convolutional neural network

Improving a model of object recognition in images based on a convolutional neural network

Determination of Land Use Change using Support Vector Machines: A Case Study of Arnavutkoy, Istanbul

PlanetScope Imagery for Extracting Building Inventory Information

Contact Info

Product

Resources

About