Algorithm Development for Analysis of Statistical Accuracy of the Extraction of Cartographic Features in Digital Images

Abstract

Cartography uses large-scale digital images obtained by remote sensing. Such images are commonly used for the extraction and / or detection of cartographic features, which are the targets of interest in mapping. Extracting targets of interest from digital images streamlines the mapping, but the accuracy of this mapping depends on the characteristics of the features of interest present in the extracted image. Therefore, this paper proposes an automated way to calculate and display statistical values so that the extraction processes of any feature type mapping can be assessed considering its quality and quantity. With this purpose in mind, a computer program has been developed. This program applies an already established methodology to calculate statistical values concerning the results obtained by the automatic extraction process. The implemented program performs calculations in a quick and objective manner. In addition, it also generates resultant images that provide the user viewing of the errors obtained by the reported method. This paper presents the results obtained from the use of this computer program. Thus, the program developed accomplishes the proposed objectives, allowing the user to perform a consistent analysis of the automated extraction, since this evaluation is performed based on statistical calculations. Therefore, this program assists researchers and scholars of cartography to evaluate automatic extraction processes in the cartographic features of interest.

Statistical Evaluation and Analysis of Road Extraction Methodologies Using a Unique Dataset from Remote Sensing

“…Cardim et al [18] obtained the results of the methodology applied to one subimage of a Quickbird Satellite panchromatic band with spatial resolution of 0.6 m. Even though it was not presented in the paper, the authors mentioned that the methodology was tested using a set of remote sensing images. The results presented were statistically verified [13,14], achieving values of 95% for completeness and 94% for correctness for the image presented in that paper.…”

“…Those metrics perform comparisons based on the use of vector data of the main axis of the interest road. Another evaluation method, described by Cardim et al [14], is based on the first method cited [13] but adopted for high-resolution images performing the evaluation by comparing the pixels values instead of the vector data and using the roads edges instead of the main axis. In this way, since two of the evaluated methodologies return road segment areas, instead of the road edges, the edges of the segmented area were acquired applying the Laplacian filter.…”

“…The comparison is performed pixel-by-pixel using an acceptance buffer (tolerance), which is separately disposed for both images. To consider the pixel as a coincident one, it must be in the acceptance buffer of the other data during the comparison [13,14,27]. Figure 7 presents how this comparison is performed.…”

“…Completeness can be summarized as the percentage of the reference image that was correctly extracted by the proposed methodology, i.e., this metric describes how completely the roads were detected. The optimal value for this metric is 1 and it is calculated, as described in [13,14], using the following equation:…”

“…In addition, the dataset was incremented with sixteen images from a public dataset (Vaihingen dataset) [12] from the International Society for Photogrammetry and Remote Sensing (ISPRS), which totals ninety-one images in the dataset. Furthermore, three road extraction methodologies were selected from the literature, in accordance with their availability, to be processed and evaluated using well-known statistical metrics defined in the scientific literature for road extraction evaluation [13,14]. The experiment was performed in three steps.…”