The Utilization of Image Texture Measures in Urban Change Detection
نویسندگان
چکیده
Image texture is increasingly being integrated into classification procedures using remotely sensed data. This research examined the utility of texture measures when integrated within established approaches for monitoring urban development. Landsat-7 satellite data for the years 1999 and 2002 were enhanced through a pansharpening process to provide 15 metre spatial resolution multispectral data. The images were acquired within the same approximate yearly time frame to help minimize seasonal vegetation differences and the effects of varying sun positions. Texture proved valuable in accounting for and distinguishing varying degrees of “greenness” in the imagery and the dissimilarity option was useful in locating recently excavated land. The measures were also helpful in separating agricultural fields from urban features. An increase of 3% in overall classification accuracy was realized when texture information was included as a classification variable. An integrated unsupervised classification/image differencing change detection process with a combination of inputs including texture, principal components, and the Normalized Difference Vegetation Index (NDVI) provided enhanced classification results and allowed for the estimation of urban expansion rates (4.62 square kilometres per year for the 1999-2002 period). Zusammenfassung: Die Verwendung von Image Texturwerten in der Stadtentwicklungsanalyse. Texturwerte werden zunehmend für SatellitenbildKlassifikationsverfahren verwendet. Dieser Artikel überprüft die Nützlichkeit von Texturwerten und integriert sie innerhalb einer herkömmlichen städtischen Entwicklungsüberwachungsanalyse. Landsat-7 Daten wurden für die Jahre 1999 und 2002 durch ein „pansharpening“ bearbeitet, um die Multispektraldaten auf 15 Meter in der räumlichen Auflösung zu verbessern. Die Bilder wurden etwa zur gleichen Jahreszeit aufgezeichnet, um saisonale Vegetationsunterschiede und die Effekte bei der Veränderung der Sonnenposition herabzusetzen. Die Textur von Objekten war wertvoll in der Erkennung unterschiedlicher Grün-Abstufungen in den Bildern, und die „dissimilarity“ Option war nützlich um kürzlich gerodetes Land zu lokalisieren. Die Maßnahmen waren auch hilfreich bei der Trennung von landwirtschaftlichen Flächen und städtischen Strukturen. Eine Zunahme von 3% der gesamten Klassifizierungsgenauigkeit konnte festgestellt werden, da Texturwerte in die Klassifikationsverfahren eingeschlossen wurden. Es wurde versucht, mehrere Parameter in die Klassifikation zu integrieren wie die Textur, die Hauptkomponenten und der normalisierte Vegetationsindex (NDVI), welche schlussendlich bessere Klassifizierungsergebnisse hervorgebracht haben. Die Untersuchungen führten zu dem Resultat, dass sich die Fläche der Stadt im Untersuchungszeitraum um jährlich 4,62 km
منابع مشابه
Change Detection in Urban Area Using Decision Level Fusion of Change Maps Extracted from Optic and SAR Images
The last few decades witnessed high urban growth rates in many countries. Urban growth can be mapped and measured by using remote sensing data and techniques along with several statistical measures. The purpose of this research is to detect the urban change that is used for urban planning. Change detection using remote sensing images can be classified into three methods: algebra-based, transfor...
متن کاملBuilding Change Detection Using 3-d Texture Model
Texture models are potentially very useful for automated urban data revision. We propose a ‘model-based change detection algorithm’ using three-dimensional urban data. In this algorithm, temporal images are projected on a common three-dimensional geometry model and the latest textures are compared with previous textures to detect an object’s change accurately. In addition, a shadow simulation w...
متن کاملUrban Change Detection Based on Edge Line Segments and Texture
In this paper, a novel approach based on edge line segments and texture is presented for urban change detection. First, we extract edge line segments based on Canny edge detector and line-support regions based on gradient orientation, Then changed edge line segments are found and grouped into clusters as potential changed regions which are finally validated using the difference of pixels and te...
متن کاملA Saliency Detection Model via Fusing Extracted Low-level and High-level Features from an Image
Saliency regions attract more human’s attention than other regions in an image. Low- level and high-level features are utilized in saliency region detection. Low-level features contain primitive information such as color or texture while high-level features usually consider visual systems. Recently, some salient region detection methods have been proposed based on only low-level features or hig...
متن کاملAutomatic road crack detection and classification using image processing techniques, machine learning and integrated models in urban areas: A novel image binarization technique
The quality of the road pavement has always been one of the major concerns for governments around the world. Cracks in the asphalt are one of the most common road tensions that generally threaten the safety of roads and highways. In recent years, automated inspection methods such as image and video processing have been considered due to the high cost and error of manual metho...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2013