The paper describes the method of development for the remote sensing data processing to speed up the digitizing workflow. The method is designed to digitize rectangular objects using their approximate spatial positions and provides an automatic estimation of the orientation and aspect ratio.
The paper contains a formal statement of the problem of digitizing an object with the desired geometric shape using it’s apriori known spatial position on a source image. The method creates polygonal representations of rectangular spatial objects from one or a few reference points set by an operator. It is based on source image’s pixels clustering using spectral bands as a feature space. The following Hough transform incorporates local direction of intensity gradient to estimate object’s orientation and reduce computational complexity together with low-pass filtering within an accumulation process to improve robustness. It is shown that the developed method can be modified to digitize objects of any analytically described shape.
The method is designed to allow easy user interaction without any significant delays and to provide transparent and predictable control of an output object’s polygon size.
To investigate the developed method a test dataset with more than 700 rectangular objects was used. The root-mean-square error of object’s points positioning, mean rotation error in polar coordinates and a Jaccard index were used to measure a precision of the digitized objects. The experiment results demonstrate that digitizing workflow is accelerated by 25–40% using the software implementing the developed method without a significant precision loss.
Vectorization of objects from an image is necessary in many areas. The existing methods of vectorization of satellite images do not provide the necessary quality of automation. Therefore, manual labor is required in this area, but the volume of incoming information usually exceeds the processing speed. New approaches are needed to solve such problems. The method of vectorization of objects in images using image decomposition into topological features is proposed in the article. It splits the image into separate related structures and relies on them for further work. As a result, already at this stage, the image is divided into a tree-like structure. This method is unique in its way of working and is fundamentally different from traditional methods of vectorization of images. Most methods work using threshold binarization, and the main task for them is to select a threshold coefficient. The main problem is the situation when there are several objects in the image that require a different threshold. The method departs from direct work with the brightness characteristic in the direction of analyzing the topological structure of each object. The proposed method has a correct mathematical description based on algebraic topology. On the basis of the method a geoinformation technology has been developed for automatic vectorization of raster images in order to search for objects located on it. Testing was carried out on satellite images from different scales. The developed method was compared with a special tool for vectorization R2V and showed a higher average accuracy. The average percentage of automatic vectorization of the proposed method was 81%, and the semi-automatic vectorizing module R2V was 73%.
1 - 2 of 2 items