18 August 2014 in International Journal of Remote Sensing
This article proposes STEP, a novel object-based similarity matrix, for assessing both geometric and thematic accuracies of remote-sensing image classification. In contrast to the traditional error matrix, STEP uses samples of classified and reference objects rather than counts of pixels. Moreover, STEP provides four (4) similarity metrics for characterization of classified objects compared with reference objects: (i) shape similarity (S); (ii) theme similarity (T); (iii) edge similarity (E); and (iv) position similarity (P). Individual objects’ similarity metrics are grouped by thematic class and expressed in the integrated STEP similarity matrix. The proposed approach is illustrated using both a hypothetical classification and a real urban land-cover classification obtained from high spatial resolution orthoimagery. Results show that the STEP indices and matrices are able to express meaningful information about thematic and geometric accuracies of object-based image classifications. It also yields area weighted aggregated-by-class error matrices that allow for calculating overall accuracy metrics.
7 November 2008 in International Journal of Remote Sensing
Support Vector Machines (SVM) is becoming a popular alternative to traditional image classification methods because it makes possible accurate classification from small training samples. Nevertheless, concerns regarding SVM parameterization and computational effort have arisen. This Letter is an evaluation of an automated SVM‐based method for image classification. The method is applied to a land‐cover classification experiment using a hyperspectral dataset. The results suggest that SVM can be parameterized to obtain accurate results while being computationally efficient. However, automation of parameter tuning does not solve all SVM problems. Interestingly, the method produces fuzzy image‐regions whose contextual properties may be potentially useful for improving the image classification process.
14 November 2022 in Smart Agricultural Technology
31 January 2017 in International Journal of Remote Sensing
This article proposes an automated method for detection and mapping of land surface elevation changes from unmanned aerial vehicle (UAV)-based imagery. In contrast to conventional methods, which require a significant human effort to succeed, the novel approach, based on multi-temporal digital terrain model analysis, detects and outlines zones of mass deposition or mass remotion with no manual input. Main components of the proposed method are: (i) a normalized difference elevation index and (ii) an automated edge-detection procedure. Performance of method is evaluated for topographic change detection in a quarry zone using a multi-temporal UAV-based imagery dataset. It is demonstrated that the proposed method allows for a rapid and automatic elevation change mapping and that results are as accurate as conventional methods based on time-consuming thresholding and visual interpretation.
1 March 2009 in International Journal of Remote Sensing
This Letter proposes an object‐based image classification procedure which is based on fuzzy image‐regions instead of crisp image‐objects. The approach has three stages: (a) fuzzification in which fuzzy image‐regions are developed, resulting in a set of images whose digital values express the degree of membership of each pixel to target land‐cover classes; (b) feature analysis in which contextual properties of fuzzy image‐regions are quantified; and (c) defuzzification in which fuzzy image‐regions are allocated to target land‐cover classes. The proposed procedure is implemented using automated statistical techniques that require very little user interaction. The results indicate that fuzzy segmentation‐based methods produce acceptable thematic accuracy and could represent a viable alternative to current crisp image segmentation approaches.
1 February 2010 in Photogrammetric Engineering & Remote Sensing