Saeed Nadi

Saeed Nadi

Auto-generated profile, based on publicly available information

Saeed Nadi

Department of Geomatics Engineering, Faculty of Civil and Transportation Engineering, University of Isfahan, Isfahan, Iran

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2011 in International Journal of Applied Earth Observation and Geoinformation
Verified
Journal Article
Closed access
SNS. Nadi
S. Nadi
MDM.R. Delavar
M.R. Delavar

1 December 2020 in Building and Environment
Verified
Journal Article
Closed access
Omid GhaffarpasandOmid Ghaffarpasand
Omid Ghaffarpasand
SNSaeed Nadi
Saeed Nadi
ZSZahra Davari Shalamzari
Zahra Davari Shalamzari

4 February 2022 in International Journal of Digital Earth
Verified
Journal Article
Open access
HSHanieh Shojaei
Hanieh Shojaei
SNSaeed Nadi
Saeed Nadi
HSHossein Shafizadeh-Moghadam
Hossein Shafizadeh-Moghadam
ATAmin Tayyebi
Amin Tayyebi
JGJohn van Genderen
John van Genderen
This paper introduces an improved convolutional neural network based on the conventional U-Net for simulating built-up land expansion. The proposed method hires a pixel-wise semantic segmentation approach considering the spatial drivers affecting urbanization as data cubes. Independent variables including altitude, slope, and distance from barren, crop, greenery, roads, and urban areas for 1998, 2008, and 2018 were considered as covariates for the simulation of built-up land expansion in Tehran and Karaj regions in Iran. The proposed method was compared with the random forest (RF) algorithm as the baseline model. Evaluation using the area under the total operating characteristic indicated the superiority of our modified U-Net (0.87) over the RF (0.82) algorithm. Furthermore, evaluation using the percent correct metric indicated that our proposed model is capable of learning neighborhood effects effectively leading to simulate built-up land expansion accurately, independent from applying a cellular automata (CA) model. Therefore, the modified U-Net independent from the CA which can consider the neighborhood effects is recommended for the simulation of built-up land expansion precisely.

26 June 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MRMaryam Rahimzad
Maryam Rahimzad
Saeid HomayouniSaeid Homayouni
Saeid Homayouni
ANAmin Alizadeh Naeini
Amin Alizadeh Naeini
SNSaeed Nadi
Saeed Nadi
High-resolution urban image clustering has remained a challenging task. This is mainly because its performance strongly depends on the discrimination power of features. Recently, several studies focused on unsupervised learning methods by autoencoders to learn and extract more efficient features for clustering purposes. This paper proposes a Boosted Convolutional AutoEncoder (BCAE) method based on feature learning for efficient urban image clustering. The proposed method was applied to multi-sensor remote-sensing images through a multistep workflow. The optical data were first preprocessed by applying a Minimum Noise Fraction (MNF) transformation. Then, these MNF features, in addition to the normalized Digital Surface Model (nDSM) and vegetation indexes such as Normalized Difference Vegetation Index (NDVI) and Excess Green (ExG(2)), were used as the inputs of the BCAE model. Next, our proposed convolutional autoencoder was trained to automatically encode upgraded features and boost the hand-crafted features for producing more clustering-friendly ones. Then, we employed the Mini Batch K-Means algorithm to cluster deep features. Finally, the comparative feature sets were manually designed in three modes to prove the efficiency of the proposed method in extracting compelling features. Experiments on three datasets show the efficiency of BCAE for feature learning. According to the experimental results, by applying the proposed method, the ultimate features become more suitable for clustering, and spatial correlation among the pixels in the feature learning process is also considered.

1 January 2020 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
MSMohammad Sheikholeslami
Mohammad Sheikholeslami
SNSaeed Nadi
Saeed Nadi
ANAmin Alizadeh Naeini
Amin Alizadeh Naeini
Pedram GhamisiPedram Ghamisi
Pedram Ghamisi

1 February 2020 in Journal of Surveying Engineering
Verified
Journal Article
Closed access
SNSaeed Nadi
Saeed Nadi
DSDavood Shojaei
Davood Shojaei
Yusof GhiasiYusof Ghiasi
Yusof Ghiasi
One of the main concerns during digital elevation model (DEM) evaluation is the number of ground control points (GCP). Accordingly, in this paper, a new method is proposed for calculating the appropriate number of GCPs for DEM evaluation based on a confidence interval (CI) of the root-mean-square error (RMSE). This method was employed to determine the CI of the estimated vertical accuracy of Advanced Land Observing Satellite (ALOS) World 3D-30m (AW3D30), Shuttle Radar Topography Mission (SRTM), and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) Global Digital Elevation Model (GDEM) Free 30 m resolution global DEMs in mountainous, hilly, flat, and urban regions of two study areas. To provide a more reliable estimation of errors, robust statistical methods, including median, normalized median absolute deviation (NMAD), and Huber’s μ and σ were also investigated. Furthermore, a new formulation was developed to analyze the propagation of the errors in the slope and aspect products of DEM. The results showed that, to evaluate the accuracy of AW3D30, ASTER GDEM, and SRTM with a CI of ±1  m and the probability of 99%, in the study area, a minimum number of 2,110, 1,483 and 750 GCPs are required, respectively. The results also showed that, in the flat, hilly, and mountainous study areas, AW3D30 was the most accurate DEM. However, SRTM fit better to the urban study area. Finally, the results of the error propagation analysis illustrated that the slope and aspect errors bore a striking relation to the surface gradient.