Hierarchical 3D structural matching in aerospace photographs and indoor scenes

Abstract

The investigation presented in this article continues our long-term efforts directed towards the automatic structural matching of aerospace photographs. An efficient target independent hierarchical structural matching tool was described in our previous paper 1 , which, however, was aimed mostly for the analysis of 2D scenes. It applied the same geometric transformation model to the whole area of image, thus it was nice for the space photographs taken from rather high orbits, but it often failed in the cases when the sensors were positioned near the 3D scenes being observed. Different transformation models should be applied to different parts of images in the last case, and finding a correct separation of image into the areas of homogeneous geometric transformations was the main problem. Now we succeeded in separating the images of scenes into the surfaces of different objects on the base of their textural and spectral features, thus we have got a possibility of separate matching the sub-images corresponding to such objects applying different transformation model to each such sub-image. Some additional limitations were used in the course of such separation and matching. In particular, the a priory assumptions were applied in different cases about the possible geometry of scenes, rules of illumination and shadowing, thus the aerospace photographs, indoor scenes, or images of aircrafts were analyzed in slightly differing ways. However the additional limitations applied could be considered as very general and are worth to be used in a wide sphere of practical tasks. The automatic image analysis was successful in all considered practical cases.

Correlating images of three-dimensional scenes by clusterizing the correlated local attributes, using the Hough transform

“…In this way, an attempt is made to discriminate groups of key points that belong to separate objects. Lutsiv et al 2 use texture analysis for similar purposes. After clusterization, the key points (structural elements) can be correlated within separate subregions, and the final solution is made from the number of correlated regions of the images.…”

Investigation of the generalizing capabilities of convolutional neural networks in forming rotation-invariant attributes

“…[5][6][7] Attempts to apply traditional NNs to such problems have led to more limited solutions, 8 while it has not yet been demonstrated that they can be solved with deep-learning networks having automatic extraction of the corresponding invariants. In this connection, the question arises of whether deep-learning networks can be nontrivially generalized.…”