Review ArticleChange detection from remotely sensed images: From pixel-based to object-based approaches
Introduction
In remote sensing (RS) applications, changes are considered as surface component alterations with varying rates. Land-cover (LC) and land-use (LU) change information is important because of its practical uses in various applications, including deforestation, damage assessment, disasters monitoring, urban expansion, planning, and land management. Singh (1989) defined change detection (CD) as “the process of identifying differences in the state of an object or phenomenon by observing it at different times”. The CD frameworks use multi-temporal datasets to qualitatively analyze the temporal effects of phenomena and quantify the changes. The RS data has become a major source for CD studies because of its high temporal frequency, digital format suitable for computation, synoptic view, and wider selection of spatial and spectral resolutions (Chen et al., 2012a, Coops et al., 2006, Lunetta et al., 2004). The general objectives of CD in RS include identifying the geographical location and type of changes, quantifying the changes, and assessing the accuracy of CD results (Coppin et al., 2004, Im and Jensen, 2005, Macleod and Congalon, 1998).
Developing CD methods in RS is an ongoing research agenda. The principle behind using RS data for CD is that changes in the object of interest will alter the spectral behavior (reflectance value or local texture) that is separable from changes caused by other factors (e.g. atmospheric conditions, illumination and viewing angles, and soil moistures) (Deer, 1995, Green et al., 1994, Jensen, 1983, Singh, 1989). The CD from RS data is affected by various elements including spatial, spectral, thematic and temporal constraints, radiometric resolution, atmospheric conditions, and soil moisture conditions (Jensen, 2005). Different CD techniques have been developed in the past, depending on the requirements and conditions. However, the selection of the most suitable method or algorithm for change detection is not easy in practice (Lu et al., 2004). Researchers have made enormous efforts in developing various change detection methodologies including both the traditional pixel-based (Mas, 1999) and more recently, the object-based (Araya and Hergarten, 2008).
Various CD reviews based on pixel-based analysis of RS data have been published (see e.g. Coppin et al., 2004, Deer, 1995, Jianyaa et al., 2008, Lu et al., 2004, Mouat et al., 1993, Singh, 1989) which have summarized and categorized CD techniques based on different viewpoints. A common one is grouping them into pre-classification and post-classification CD techniques (Chen et al., 2012c). Chan et al. (2001) categorized them as change enhancement techniques and nature-of-change techniques. Lu et al. (2004) presented a comprehensive review and grouped CD techniques into seven categories. They categorized an exhaustive list of CD studies with respect to the change domain or applications aspects. Most of these reviews cover CD techniques for coarse and relatively fine spatial resolution data such as MODIS, Landsat (MSS, TM), SPOT, and radar. However, these reviews do not extensively examine techniques and methods suitable for data from very-high-resolution (VHR) optical satellites such as IKONOS, QuickBird, GeoEye, RapidEye, EROS A and B. The object-based imaged analysis techniques are considered more suitable for VHR image data and some discussion can be found in (Blaschke, 2010, Chen et al., 2012a, Jianyaa et al., 2008, Lang, 2008).
In this paper we place the CD methodologies into two discrete groups based on the unit of image analysis. The first is the traditional/classical pixel-based, employing an image pixel as fundamental unit of analysis. The second group is the object-based method, emphasizing, first, creating image objects and then using them for further analysis. This paper is broadly organized into three parts. First pixel-based change detection (PBCD) methods are discussed followed by object-based change detection (OBCD) techniques. Also, the spatial data mining techniques are discussed for their potential for analyzing changes from RS data. The focus of this paper is to provide a review of commonly used CD methods and techniques in RS, their applications, and related issues.
Section snippets
General considerations in change detection from RS
The most generic CD schema in RS comprises, broadly speaking, (a) feature extraction (e.g. difference or ratio), and (b) decision function (operation to produce decision i.e. change vs. no-change). However, not all the methods follow it (Dreschler-Fischer et al., 1993). The CD process can broadly be split into: (a) pre-processing (b) selecting CD technique, and (c) accuracy assessment.
The pre-processing stage handles the issues related to radiometric, atmospheric, and topographic corrections,
Pixel-based change detection (PBCD) in remote sensing
A pixel has been the basic unit of image analysis and CD techniques since the early use of RS data. An image pixel is the atomic analytical unit in these techniques whose spectral characteristics are exploited to detect and measure changes mostly without considering the spatial context. Most often statistical operators are used for evaluating the individual pixel. Researchers have reviewed the pixel-based approaches, in greater depth, summarizing functionalities, advantages and disadvantages
Issues with traditional techniques
The decision function is the key element that identifies change from no-change in CD algorithms. One common approach, the application of a threshold value to differentiate change from no-change, is used in most of the CD algorithms. This technique, however, often suffers from mis- or over- detection, and selecting a suitable threshold value to identify change is difficult (Jensen, 2005, Lu et al., 2004, Xian et al., 2009, Zuur et al., 2007). Too low a threshold will exclude areas of change, and
Object-Based Change Detection (OBCD)
The emergence of VHR multispectral imagery and the rapid increase in computational capabilities over the last decade have challenged the traditional pixel-based image analysis (Chen et al., 2012a). It was recognized earlier (Fisher, 1997) that a pixel is not a true geographical object; rather, it is a cell representation of spectral values in a grid whose boundaries lack real-world correspondence. Addink et al. (2012) supported this idea by arguing that a pixel is not the optimal spatial unit
Challenges for objects-based approaches
Contrary to pixel-based approaches, OBIA uses spectral, textural, spatial, topological, and hierarchical object characteristics to model reality. There are, however, concerns about validation, as Radoux et al. (2010) argued that point-based sampling does not rely on the same concept of objects. Error matrix is still used in most OBCD studies, and Hernando et al. (2012) argued that this is established for pixel-based approach, and that a state-of-the-art approach for object-based accuracy
Data mining technique and change detection
The analytical framework in RS change detection is becoming more data driven because of a rapid increase in the availability of RS data especially at very high resolution, and increased computational power with more sophisticated algorithms. Huge repositories of image data, which cover larger areas and larger spans of time, are becoming available. The situation has changed from a data and computational-poor scenario to a data-rich and information-poor scenario (Lijuan et al., 2010). The ability
Future remote sensing change detection
Change detection, including both the bitemporal or multitemporal, is one of main applications of remotely sensed data (Campbell and Wynne, 2011). With the development of RS technology and data, the RS-based change detection has witnessed a substantial evolution from traditional pixel-based spectral and statistical analysis to advanced and pioneering techniques, which are still in progress. One may consider three aspects of RS-based change detection – application domain, data, and the techniques
Summary
In this paper we have presented a review of the traditional pixel-based change detection methods and highlighted their functionalities and limitations. This was succeeded by a discussion of object-based change detection from images. Finally we briefly discussed data mining techniques for image analysis and their use in change detection. Change detection from remotely sensed data is a topic of ever-growing interest. Change detection from remotely sensed data is a complicated process, with no
Acknowledgement
This research is supported by a grant from the Natural Sciences and Engineering Research Council (NSERC) of Canada.
References (224)
- et al.
Change detection using adaptive fuzzy neural networks: environmental damage assessment after the Gulf war
Remote Sensing of Environment
(1999) - et al.
Introduction to the GEOBIA 2010 special issue: from pixels to geographic objects in remote sensing image analysis
International Journal of Applied Earth Observation and Geoinformation
(2012) - et al.
Optimizing land cover classification accuracy for change detection, a combined pixel-based and object-based approach in a mountainous area in Mexico
Applied Geography
(2012) - et al.
A comparative study of NOAA–AVHRR derived drought indices using change vector analysis
Remote Sensing of Environment
(2006) - et al.
Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information
ISPRS Journal of Photogrammetry and Remote Sensing
(2004) Object based image analysis for remote sensing
ISPRS Journal of Photogrammetry and Remote Sensing
(2010)- et al.
Object-oriented methods for habitat mapping at multiple scales – case studies from Northern Germany and Wye Downs, UK
Journal for Nature Conservation
(2005) - et al.
An object-based change detection method accounting for temporal dependences in time series with medium to coarse spatial resolution
Remote Sensing of Environment
(2008) - et al.
A data mining based approach to predict spatiotemporal changes in satellite images
International Journal of Applied Earth Observation and Geoinformation
(2011) - et al.
Automatic change detection of buildings in urban environment from very high spatial resolution images using existing geodatabase and prior knowledge
ISPRS Journal of Photogrammetry and Remote Sensing
(2010)
An overview of recent remote sensing and GIS based research in ecological informatics
Ecological Informatics
Monitoring land-cover change by principal component analysis of multitemporal landsat data
Remote Sensing of Environment
An improved dark-object subtraction technique for atmospheric scattering correction of multispectral data
Remote Sensing of Environment
A simple and effective radiometric correction method to improve landscape change detection across sensors and across time
Remote Sensing of Environment
A GEOBIA framework to estimate forest parameters from lidar transects, Quickbird imagery and machine learning: a case study in Quebec, Canada
International Journal of Applied Earth Observation and Geoinformation
An automated approach for updating land cover maps based on integrated change detection and classification methods
ISPRS Journal of Photogrammetry and Remote Sensing
Change detection using the Gramm-Schmidt transformation applied to mapping forest mortality
Remote Sensing of Environment
An assessment of several linear change detection techniques for mapping forest mortality using multitemporal landsat TM data
Remote Sensing of Environment
An object-based method for mapping and change analysis in mangrove ecosystems
ISPRS Journal of Photogrammetry and Remote Sensing
A TM tasseled cap equivalent transformation for reflectance factor data
Remote Sensing of Environment
Forest change detection by statistical object-based method
Remote Sensing of Environment
Radiometric normalization of multitemporal high-resolution satellite images with quality control for land cover change detection
Remote Sensing of Environment
A method for monitoring building construction in urban sprawl areas using object-based analysis of Spot 5 images and existing GIS data
ISPRS Journal of Photogrammetry and Remote Sensing
Deforestation in Central Africa: estimates at regional, national and landscape levels by advanced processing of systematically-distributed Landsat extracts
Remote Sensing of Environment
Detecting change in vague interpretations of landscapes
Ecological Informatics
Object-oriented change detection for the city of Harare, Zimbabwe
Expert Systems with Applications
Fuzzy clustering algorithms for unsupervised change detection in remote sensing images
Information Sciences
Mapping megacity growth with multi-sensor data
Remote Sensing of Environment
A multiscale object-specific approach to digital change detection
International Journal of Applied Earth Observation and Geoinformation
Image segmentation techniques
Computer Vision, Graphics, and Image Processing
Spatial thresholds, image-objects, and upscaling: a multiscale evaluation
Remote Sensing of Environment
An automated object-based approach for the multiscale image segmentation of forest scenes
International Journal of Applied Earth Observation and Geoinformation
Texture features based on texture spectrum
Pattern Recognition
Spatial and thematic assessment of object-based forest stand delineation using an OFA-matrix
International Journal of Applied Earth Observation and Geoinformation
Use of a dark object concept and support vector machines to automate forest cover change analysis
Remote Sensing of Environment
A change detection model based on neighborhood correlation image analysis and decision tree classification
Remote Sensing of Environment
An automated binary change detection model using a calibration approach
Remote Sensing of Environment
Optimizing the binary discriminant function in change detection applications
Remote Sensing of Environment
Structural damage assessments from Ikonos data using change detection, object-oriented segmentation, and classification techniques
Photogrammetric Engineering & Remote Sensing
On scales and dynamics in observing the environment
International Journal of Remote Sensing
Multiresolution segmentation: an optimization approach for high quality multiscale image segmentation
Hurricane disaster assessments with image-driven data mining in high-resolution satellite imagery
IEEE Transactions on Geoscience and Remote Sensing
Unsupervised change detection in multispectral remotely sensed imagery with level set methods
IEEE Transactions on Geoscience and Remote Sensing
Towards a framework for change detection based on image objects
Göttinger Geographische Abhandlungen
Image segmentation methods for object-based analysis and classification
Cited by (1217)
Forest disturbance characterization in the era of earth observation big data: A mapping review
2024, International Journal of Applied Earth Observation and GeoinformationSatellite-based change detection in multi-objective scenarios: A comprehensive review
2024, Remote Sensing Applications: Society and EnvironmentVectorized dataset of silted land formed by check dams on the Chinese Loess Plateau
2024, Scientific Data