Fig 1 - uploaded by Prakash Pilinja Subrahmnaya
Content may be subject to copyright.
Source publication
Major redevelopment or utility projects requires classified information about building maps of cities. Remote sensing and satellite imagery has become good alternative source of data generation technology in recent years. In this study, our attempt is to validate SVM (Support Vector Machine) method of classification to extract buildings from the co...
Context in source publication
Context 1
... are acquired with a ground sample distance of 3.8 cm, across three bands: blue, green, and red having 8 bits data radiometry. Figure 1 shows four such images captured using the drone as examples. A subset of the entire campus measuring an area of 24.8 acres is clipped from generated orthophoto and DSM to perform classification. ...
Similar publications
In this paper, in order to measure the customer churn rate in the Iranian banks, a new approach is introduced. First, using data preparation, the data is normalized. Then, using a k-medoids method, data clustering is formed. To assess the clustering performance, Davies-Bouldin index is applied. To detect the patterns available in the data, differen...
Citations
... Moreover, conventional road extraction from remotely sensed imagery could be made more efficient and practical; present methods do not meet the demands for real-time processing [3][4]. Traditional methods are based on pixel-level information such as support vector machine, random forest, and maximum likelihood; because they are limited to the subject of colour phenomena, these methods use only the spectral information of images [5][6]. These methods use colour reflectance to classify images, which leads to a loss of information with regions of similar colour and backgrounds [7]. ...
Extraction of features is a unique approach that has several real-time applications. In remote sensing, road feature extraction includes recognising and extracting essential information about roads from high-resolution remote sensing photos. This data may include the shape, size, direction, and connection of roadways and their surroundings we can increase the accuracy and efficiency of road recognition algorithms and better comprehend the geographical distribution of roads in metropolitan settings. Nevertheless, traditional techniques of road recognition sometimes rely on manual labour or hand-crafted characteristics, which may be costly and time-consuming. Convolutional neural networks (CNNs) have been frequently employed for road detection due to their capacity to automatically learn characteristics from data. In this research, we provide Modified LinkNet for the extraction of road features from high-resolution remote-sensing images. The proposed model incorporates several variables resulting in superior performance compared to current cutting-edge road detection techniques. SpaceNet road detection dataset yields 0.81 mIoU, which is approximately 0.1, 0.11, and 0.03 mIoU greater than U-net, DeeplabV3+, and LinkNet, respectively (base architecture). In addition, the training of the model enables more efficient inference making our method applicable to real-time applications and are therefore a more effective and efficient solution for the extraction of road features from remote sensing images.
... Several other automated algorithms retrieved building attributes from remote sensing images before deep learning-based segmentation. To classify building pixels from remote sensing images, San and Turker (2006), Soumya et al. (2018) and Prakash et al. (2018) employed methods such as maximum likelihood classifier (MLC), random forest (RF), and support vector machine (SVM). Although these strategies enhanced the accuracy of segmentation, they remained insufficient for dealing with complicated metropolitan situations. ...
Building footprint datasets are valuable for a variety of uses in urban settings. For a number of urban applications, polygonal building outlines with regularised bounds are required and are extremely challenging to prepare. We propose a deep learning strategy based on convolutional neural networks for retrieving building footprints. The model was trained using images from a variety of places across the metropolis, highlighting differences in land use patterns and the built environment. The evaluation measures indicate how the accuracy characteristics of distinct built-up settings differ. The results of the model are equivalent to cutting-edge building extraction methods. © 2022 Mapping Science Institute, Australia and Surveying and Spatial Science Institute.
... Beljaars and Holtslag (1991) 2019; Prakash et al., 2018;Raket et al., 2020;Varadharajan et al., 2015;Yoon et al., 2020). The training dataset was used to train the model and the validation dataset was used to evaluate the model accuracy. ...
Aerodynamic roughness length (z0m) is a key parameter in the characterization of land surface turbulent heat fluxes and widely used in many surface and climate-related process models. The global products of time series of z0m at finer spatio-temporal resolution, however, have never been publicly available. Here we presented a practical method for global estimates of 500 m daily z0m with a combination of machine learning techniques, wind profile equation, observations from 273 sites and MODIS remote sensing data. Results showed that the random forest (RF) model outperformed the deep neural network (DNN) and convolutional neural network (CNN) models, and it could well reproduce the magnitude and temporal variability of daily z0m at almost all sites for all land cover types. In the validation of the RF-estimated daily z0m with the in-situ observations, the root mean square error (RMSE) varied between 0.02 m and 0.09 m, the mean absolute error (MAE) varied between 0.01 m and 0.05 m and the coefficient of determination (R2) was 1 for medium-to-high canopy shrublands, savannas and forests; for short-canopy croplands, grasslands and wetlands, the RMSE and MAE were 0.02 m and 0.01 m, respectively, and the R2 varied between 0.94 and 1. Compared to the Climate Forecast System Version 2 (CFSv2, 0.3°/monthly) and ECMWF Reanalysis v5 (ERA5, 0.25°/monthly) products in 2019, the RF-estimated z0m was found to have the similar global spatial pattern but significantly larger temporal variability, and it also showed a higher and lower global mean of z0m over forests and non-forests, respectively. The RF-estimated z0m displayed a higher temporal variability but a similar global spatial pattern of this variability compared to the CFSv2, whereas the ERA5 z0m product exhibited almost no temporal variability except for grasslands and croplands. This study is beneficial for improving the simulation of the momentum, water and energy transfer between land and atmosphere and helping boost the development of high-resolution land surface models and Earth system models.
... Cortes and Vapnik 1995 developed this method based on the concept of maximizing the margins between the hyperplane and closest data points. SVM has been used in the classification of remote sensing data in several earlier works (Dixon and Candade 2008;Benarchid et al 2013;Prakash et al. 2018). The mathematical formulation of the SVM method is given in the literature (Foody and Mathur 2004;, and SVM classifier gives the flexibility of using four variety of kernels, namely sigmoid, radial basis function, linear and polynomial. ...
The rapid growth of major cities across the counties demands accurate building extraction techniques. Unmanned Aerial
Vehicles (UAV) help in obtaining terrain information that can be used to extract urban features. Recent advancement has
led to the capture of aerial images of the earth's surface in micro-detail using UAV. These aerial images enable us to perform
classification, feature extraction, and height estimation at a finer scale. In this work, aerial images of the university campus
were captured using a quadcopter drone equipped with a high-resolution camera and satellite navigation system. Approximately 500 images were captured in the study area with necessary overlap and side lap. Captured images were subjected to
aerial triangulation, dense image matching, and point cloud generation to produce Digital Surface Models (DSM) and
orthophoto. Various machine learning algorithms—random forest (RF), support vector machine (SVM), naı¨ve Bayes (NB)
and artificial neural networks (ANN)—have been used to extract building rooftops from derivatives of UAV-captured
imageries and accuracies were compared. Algorithms were trained using both spectral and elevation information to extract
building rooftops, and improvements shown due to the addition of elevation data in training the model are observed. The
proposed method is aimed at improving building-level information extraction and providing accurate building information
to aid authorities for better planning and management.
ABSTRACT
In recent times, automatic number plate recognition and extraction of characters have become widely used in the safety of human beings. But automatic systems are not efficient in foggy places. Many accidents are reported in foggy places, and police officials face difficulty finding them at the very beginning of such incidents. Researchers used different methods to get high accuracy in order to retrieve the characters correctly. This paper utilized a fused approach of different weight maps, mainly used for vehicle number plate localization in any foggy environment and character extraction from the localized image. In addition, it again proposed an improved method in character extraction based on the pre-trained AlexNet deep learning algorithm. In this chapter, the following work has been done:
To propose a design methodology for vehicle number plate forgery detection.
To propose a design methodology for fog image classification.
To propose an ML method for Indian vehicle number plate detection.
To propose a deep learning method for Indian vehicle number plate detection.
Finally, we concluded our proposed system based on the number of epochs and splits. Exploratory outcomes show the adequacy of our methodology in the examination of the critical journal results.
