Fatemeh Ahmadi; yasser Ebrahimian Ghajari; Abbas Kiani
Abstract
Abstract: Remote sensing provides a powerful data source for mapping urban areas and monitoring urban dynamics on various scales. Among remote sensing data, images taken at night provide an effective way to monitor human activities on a global scale. Because the features and capabilities of these images ...
Read More
Abstract: Remote sensing provides a powerful data source for mapping urban areas and monitoring urban dynamics on various scales. Among remote sensing data, images taken at night provide an effective way to monitor human activities on a global scale. Because the features and capabilities of these images can enable separating urban areas and other human activities, the main feature of which is the use of light at night by accurately measuring the location, from the background without light. Via providing uninterrupted and continuous monitoring from the night world perspective, these images provide valuable source and results of human activities from the past to the present; the time series analysis of this data is highly valuable for discovering, estimating and monitoring social and economic dynamics in countries, especially sub-regions where there are no official statistics. With the development of night data satellite sensors in recent years and new research conducted in the field of night-time data, this study aims to review the advances in night-time sensors, introduce the existing data and products, review and express the advantages and disadvantages of each one and review methods and solutions presented in previous research for solving the existing problems and limitations in order to improve these images. Therefore, according to the reviews of 225 articles on night light from various credible journals, the results demonstrated that 65% of the available articles were from night light data in the urban field (59% related to urban dynamics extracting and studying and 6% for population surveys) and 35% for non-urban field (17% for energy consumption, 13% for economic issues and 5% for other issues such as pollution) in a more detailed look. Articles that have tried to provide methods for correcting night images can be categorized as follows: in the DMSP-OLS data, 44% of the articles were urban surveys, 14% were for economic purposes, 38% for the general purpose of correction and 4% for other purposes. Visible and infrared imaging radiometer suite (VIIRS) data were 57% for economic purposes, 36% for urban surveys and 7٪ for other purposes. The results and findings of this study can provide a general overview for researchers to familiarize and understand the trends of various studies in the use of night light data. It can also help researchers choose the right data and algorithm according to their purpose and study field.
Zohreh Roodsarabi; ali Sam Khaniani; Abbas Kiani
Abstract
Numerous studies on the phenomenon of fire over the past several decades have provided an extensive set of input data and implementation and evaluation methods. However, this vast array of results and research is structured to provide a roadmap to new users in the field and guidance on various applications ...
Read More
Numerous studies on the phenomenon of fire over the past several decades have provided an extensive set of input data and implementation and evaluation methods. However, this vast array of results and research is structured to provide a roadmap to new users in the field and guidance on various applications and conditions that have not yet been analyzed. In other words, the absence of coherent research on the relative performance of different remote sensing processes in the fire is felt to produce various products or the resulting utilities. To fill this gap, a relatively comprehensive analysis of fire studies in remote sensing publications has been performed in this study. Some of the general factors evaluated in the pre, during, post-fire studies were the manipulation of input data, the review of algorithms, and their development, as these are factors that can be controlled by analysts to improve the Final accuracy of analyzes and results. One of the important issues in the field of fire after the identification and discovery of fire, due to the permanent changes in the structure and composition of vegetation, is to study how vegetation is restored and its growth rate during the years after the fire. According to a study of fire studies in the country, about 48% of them are related to the identification and spread of fire and the remaining 52% are related to resuscitation and recovery. In a review of research related to identification studies, it was found that approximately 5% of its share was done using learning methods and the remaining 43% was done using traditional methods. At the same time, of the study-related share of Resuscitation studies approximately 21% to examine vegetation and 31% of the soil under the fire surface. The findings of this study can be useful in helping researchers to make decisions in the selection of data and algorithms used according to the purpose of study, in different branches of studies associated with fire. However, in addition to these general guidelines, an analyst can consider personal preferences or the benefits of a particular algorithm that may be relevant to a particular program.
Mina Hamidi; Hamid Ebadi; abbas kiani
Abstract
By improvement of the spatial resolution of remote sensing images, more accurate information are provided from the image scene such as texture structures. However, extraction of land cover information from these datas has become a challenging process due to the high spectral diversity and the heterogeneity ...
Read More
By improvement of the spatial resolution of remote sensing images, more accurate information are provided from the image scene such as texture structures. However, extraction of land cover information from these datas has become a challenging process due to the high spectral diversity and the heterogeneity of surface materials. Visual interpretation is costly and time consuming and automatic interpretation of images does not necessarily lead to high accuracy. Achieving optimal interpretation accuracy requires the design of automatic algorithms that are capable of dealing with the complexity of the image scene. To overcome this problem, object-based image analysis (OBIA) that is sensitive to the image scene morphology, can be particularly effective in an urban area where the density of man-made structures is high. In object-based classification, pixels of a segment are analyzed in combination with each other. So the dimensions of the problem space are reduced, in compared to the pixel-based method, which leads to increasing the computational speed. Meanwhile, due to the different sizes of image segments, supervised object-based classification faces challenges in creating an optimal training set. In this research, AdaBoost algorithm was selected for the object-based classification, to overcome the problem of feature space imbalance, due to the small number of training samples in comparison with the high dimensions of the feature space (including spectral, spatial and geometric features), two strategies were proposed. In the first approach an active learning mechanism was integrated with AdaBoost to produce optimal training data set (OTD) and in another approach based on the feature-to-feature correlation (redundancy) and the feature-to-class correlation (relevance), the candidate feature subset (CFS) was generated to reduce the size of the feature space. To evaluate the proposed method, the developed algorithm was performed on the standard dataset of Vaihingen in Germany and the results were compared with the pixel-based classification. In order to evaluate the signification of the results, the McNemar statistical test was used. The experimental results showed that the proposed object-based approach improved the overall accuracy by 6% and the kappa coefficient by 7% compared to the pixel-based approach. Also, the computational speed of proposed object-based AdaBoost was significantly increased compared to the pixel-based approach. These results indicate the superiority of the proposed approach both in terms of accuracy and processing speed.
nima farhadi; Abas Kiani; Hamid Ebadi
Abstract
Object detection is one of the fundamental issues in image interpretation process, especially from remote-sensing imagery. One of the most effective and efficient methods in this field is the use of deep learning algorithm for feature extraction and interpretation. An object is a collection of unique ...
Read More
Object detection is one of the fundamental issues in image interpretation process, especially from remote-sensing imagery. One of the most effective and efficient methods in this field is the use of deep learning algorithm for feature extraction and interpretation. An object is a collection of unique patterns that differ with own adjacent properties. This difference usually occurs in one or more features simultaneously, which can be indicated by the difference in shape, color, and gray values. In this regard, the use of deep learning as an efficient branch of machine learning can be useful in generating high-level concepts through learning in different layers. In this research, a database based on the environmental and geographical conditions from some Iranian airports was created. Additionally, an optimal learner model was developed with a convolutional neural network. For this purpose, in the raw data processing section, besides using the transfer learning method, some vectors were extracted to classify the objects and delivered to an SVM model. The output values were compared with the values obtained from the test image for each object, and they were analyzed in a repeatable process for structural matching. Precision of 98.21% and F1-Measure of 99.1% was achieved, for identification of the target objects
Abbas Kiani; Hamid Ebadi; Hekmat allah Khanlou
Volume 10, Issue 4 , February 2019, , Pages 27-54
Abstract
Land cover classification in remote sensing imagery is one of the most widely used spatial information extraction methods, which can facilitate generating object imagery classes of the ground surface in order to automate and accelerate meeting the basic needs of management, organization, and exploitation ...
Read More
Land cover classification in remote sensing imagery is one of the most widely used spatial information extraction methods, which can facilitate generating object imagery classes of the ground surface in order to automate and accelerate meeting the basic needs of management, organization, and exploitation of the environment. Due to the similar behavior of pixels, remote-sensing image classification using merely the spectral and textural information would lead to inefficiency in the classification. In fact, in classification process, objects are commonly identified using spectral properties of image pixels. If the spatial and conceptual properties are also considered, it causes to a better distinction between image classes and closes the machine process to human interpretation and adds to the system's performance. The present research is mainly focused on the use of interactive segmentation and interpretation processes with respect to the geometry of the image classes. The accuracy of the results have improved by introducing the knowledge-based rules to control and regulate the interactive process, taking into account the geometric properties of target classes. To evaluate the efficiency of the proposed method, the results were evaluated and compared with some of the other methods on IRS satellite images in an urban area. The results showed that geometric and conceptual features as a complementary information source, improve classification results in the urban area with heterogeneous spectral effects. Overall, the proposed hybrid technique improved overall accuracy and Kappa coefficient by 8% and 11.5%, respectively.
