Showing 5 results for Change Detection
Volume 9, Issue 1 (3-2005)
Abstract
Land use/cover change map production is one of the basic needs for environmental monitoring and management. Since the change maps are usually used in planning and decision-making, certainty and reliability of these maps can be very important in many applications. Unfortunately in many studies only probability values as obtained from MLC approach have been used for uncertainty estimation.
Here a new approach has been developed which is based on the probability information as well as spatial parameters including distance, neighborhood, extent and the type of change.
In this study, two Landsat TM images of Isfahan urban area provided in 1990 and 1998 have been co-registered using first order polynomial and nearest neighbor resampling approach. The registered images have been then classified to ten different land use/land cover classes using Maximum Likelihood Classification algorithm. Probabilistic measures generated by the MLC have been used for modeling uncertainty. Using different spatial analysis functions for modeling the change of agricultural areas to residential areas, the relevant spatial parameters have been extracted. Based on logistic regression approach, probabilistic parameters and spatial parameters have been integrated to generate a layer, which shows uncertainty of change of agricultural areas to residential areas. The Relative Operating Characteristics (ROC) index has been used for validation of the model and it has been estimated to be 0.9944, which is an indicative of very good model fitting. As a final conclusion, development of this model is suggested for quantitative evaluation of uncertainty in change detection.
Volume 9, Issue 2 (3-2006)
Abstract
Detection of land use/cover changes in many different studies is one of the basic needs for environmental monitoring and management. Conversion of agricultural lands is one of the main issues related to urban planning. In this study an attempt has been made to study land use/cover changes through image processing techniques. Two landsat TM images of Isfahan area provided in 1990 and 1998 were atmospherically rectified and registered on each other. Images were then classified to ten different land use/cover classes using Bayesian classification algorithm. Training sites were generated using fuzzy logic approach. A post classification comparison approach was then used to create a change map. The results show a dramatic change on agricultural lands in this area during this period.
Volume 10, Issue 3 (10-2022)
Abstract
Aims: Understanding the patterns of land use and land cover (LULC) change is important for efficient environmental restoration. This study focused on changes in LULC patterns of the Koupal watershed in Khouzestan Province over 22 years.
Materials and Methods: Multi temporal satellite imagery of the Landsat series (1998 and 2020) were preprocessed and used to extract LULC maps by bayes discriminant and Maximum likelihood rule. Reliability of classified maps were checked using confusion matrix.Transition matrix and change rate were computed by Change detection analysis.
Findings: The results of the change detection analysis shows that vegetation cover witness of dramatic decrease and changed from 27.6% to 0.06%, followed by water body reduction from 8.59% to 0.79% and bare land decrease from 57.9% to 51% of whole area. The results indicates a rapid expansion of cropland from 5.44% to 41.25% of total area. Sand dune increased from 1.08% of total area in 1998 to 2.75% in 2020 and build up area shows a growth from0.27% of total area. Change matrix revealed that 93% of cropland remained unchanged, followed by bare land (71%), built up (53%), water body (7%), sand dune (6%) and vegetation (0.05%). This indicates that vegetation experienced the most significant loss and highest conversion during this period, with almost 73% of its total area converted to cropland and bare land (22%) and the rest to other land uses.
Conclusion: These results establish LULC trends in past 22 years and provide crucial data useful for planning and sustainable land use management.
M. Minaei, W. Kainz,
Volume 20, Issue 5 (7-2018)
Abstract
This research investigates the transitions among the main Land Cover (LC)/Land Use (LU) categories in the upstream part of Gorganrood Watershed (GW) as a highly populated agricultural region that is reported to be facing considerable environmental changes in the form of deforestation, natural hazards, erosion, cultivation, and manufactured structures. Land cover maps for 1972, 1986, 2000 and 2014 were prepared, which included six LC classes: rangeland, forest, built-up, farmland, water, and bare land. Analyzing dynamics was conducted using multi-level intensity analysis followed by gain, loss, persistence, and transition exploration. Results shows that 1972-1986 interval was a fast period but changes were not stationary over the whole interval analysis level. At category level, bare land, built-up, farmland, and water categories were active gainers and changes were stationary. At transition level analysis, the transitions to built-up, bare land, forest, and water categories were stationary, from the rangeland and farmland categories. Generally, the surface occupied by farmlands increased at the detriment of rangelands and forests, and that it is the dominant LC/LU type in the watershed nowadays. In addition, the surface covered by built-up areas increased 11 times between 1972 and 2014. The results indicate that, LC/LU changes are associated with the overall population and economic growth and impact natural resources of the area, like similar regions in other developing countries.
Volume 24, Issue 4 (12-2020)
Abstract
Introduction: Multi temporal changes in built up areas are mainly caused by natural disasters (such as floods and earthquakes) or urban sprawl. Detecting these changes which consist of construction, destruction and renovation of buildings can play an important role in updating three dimensional city models. Multi-temporal remote sensing data are one the powerful tools for detecting urban changes due to the increasing growth and then, for updating the three dimensional city models. Urban changes detection methods using various types of remotely sensed data have been proposed by many researchers to meet a wide range of applications (Singh, 1989). Considering the procedure of algorithms and the utilized multi-temporal remote sensing data, change detection algorithms can be divided into two dimensional and three dimensional categories (Qin et al., 2016). Many of the proposed urban change detection methodologies have utilized only the multi-spectral remote sensing data without considering digital elevation models, which caused some problems in buildings identification (Bouziani et al., 2010; Brunner et al., 2010; Huang et al., 2014; Vakalopoulou et al., 2015). Two dimensional changes detection methods have some serious problems such as high computational cost and inaccessible volumetric information due to the absence of altitude data. Moreover, as digital elevation models can be easily produced recently, the three dimensional changes detection methods are more concerned (Martha et al., 2010; Tian et al., 2014; Waser et al., 2008; Daniel & Doran, 2013; Gruen, 2013). Three dimensional change detection methods are suitable for identifying the changes of high altitude objects such as buildings and their results are more close to reality. Three dimensional change detection methods can be considered in one of the spectral-geometric analysis methods or geometric comparison (Qin et al., 2016).
Methodology: The objective of this study is to provide an effective method for three dimensional changes detection of buildings in urban areas based on Digital Elevation Models (DEMs). The proposed three dimensional building change detection algorithm in this research is considered for estimating the construction of new buildings in flat areas and renovation of low-rise buildings (up to three floors) in order to make high-rise ones (more than three floors). The proposed method in this paper consists of three main steps; 1) generating Digital Surface Model (DSM), Digital Terrain Model (DTM) and normalized DSM for two epochs, 2) performing object based image analysis consists of segmentation and structural classification of DEMs in order to generate multi temporal classification maps, 3) producing the change maps and analyzing the change percentages between various object classes.
Resullts & Discussion: The ability of the proposed algorithm is evaluated in a rapid developing urban area in Tehran, Iran in a 9-years interval. The obtained results represent that the ground and bare soil decreased for about -1.37% and low-rise buildings also decreased for about -9.7%. Moreover, the class of high-rise buildings increased for about +16.4% which conforms making new constructions in addition to renovation of low-rise buildings. As the objective of this research was to investigate the three aspects of changes in built up areas containing new constructions, destruction and renovation of buildings, some interesting results are obtained. The main changes occurred in this region are in the new construction category with 4.8% growth which is occurred to about 132680 square meters of the study area. Moreover, the renovation of low-rise buildings to high-rise ones is 3.05% of land use equivalent to 83889.5 square meters. The obtained results showed 3.89% destructions in the buildings which is occurred to 106896.25 square meters of this study area. Most of the destructions are in the low-rise building class which confirms decreasing the worn texture of the city and urban passages sweating.
Conclusion: According to the results, the construction of new buildings is faster than the vertical growth of the city and its destruction in this 9-years period. As it is clear from the results of this study, change detection in urban environment can help urban planners to manage land resources and prevent the growth of irregular constructions. As high-rise buildings prevent wind, disrupt the urban ecosystem and increase air pollution, it is important to control and manage the vertical growth of the cities.
Kay words: Three dimensional change detection, Building, Object Based Image Analysis, Segmentation, Normalized DSM