ENTRANCE DETECTION FROM STREET-LEVEL IMAGERY

摘要

Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

主权项

1. A system, comprising:
an extraction component configured to extract entrance candidates from images of a facade and generate entrance hypotheses based on the entrance candidates; a classification component configured to classify the entrance candidates to differentiate facade entrances from non-entrances based on the entrance hypotheses; a multi-dimensional reasoning component configured to project the candidates into multi-dimensional space to resolve conflicts; and at least one microprocessor configured to execute computer-executable instructions in a memory associated with the extraction component, classification component, and multi-dimensional reasoning component.