Abstract
A city is a dynamic entity, which environment is continuously changing over time. Accordingly, its virtual city models also need to be regularly updated to support accurate model-based decisions for various applications, including urban planning, emergency response and autonomous navigation. A concept of continuous city modeling is to progressively reconstruct city models by accommodating their changes recognized in spatio-temporal domain, while preserving unchanged structures. A first critical step for continuous city modeling is to coherently register remotely sensed data taken at different epochs with existing building models. This paper presents a new model-to-image registration method using a context-based geometric hashing (CGH) method to align a single image with existing 3D building models. This model-to-image registration process consists of three steps: (1) feature extraction; (2) similarity measure; and matching, and (3) estimating exterior orientation parameters (EOPs) of a single image. For feature extraction, we propose two types of matching cues: edged corner features representing the saliency of building corner points with associated edges, and contextual relations among the edged corner features within an individual roof. A set of matched corners are found with given proximity measure through geometric hashing, and optimal matches are then finally determined by maximizing the matching cost encoding contextual similarity between matching candidates. Final matched corners are used for adjusting EOPs of the single airborne image by the least square method based on collinearity equations. The result shows that acceptable accuracy of EOPs of a single image can be achievable using the proposed registration approach as an alternative to a labor-intensive manual registration process.
Highlights
In recent years, a number of mega-cities such as New York and Toronto have built-up detailedA fundamental step to facilitate this task is to coherently register remotely sensed data taken at different epochs with existing 3D building models
The sole use of corner points from existing building data bases as local features can lead to matching ambiguities and to errors in the registration. To address this issue for the registration of single images with existing 3D building models, we propose to use two types of matching cues: (1) edged corner features that represent the saliency of building corner points with associated edges; and (2) context features that represent the relations between the edged corner features within an individual roof
Sensors 2016, 16, 932knowledge of building structures can reduce the matching ambiguities, 4 of 20and the Utilizing prior search space. 3D object recognition method from single image based on the notion of perceptual no strong disambiguating geometric constraint, whereas building models are reconstructed with grouping, which groups image lines based on proximity, parallelism and collinearity relations, certain regularities such as orthogonality, and parallelism
Summary
A number of mega-cities such as New York and Toronto have built-up detailed. A fundamental step to facilitate this task is to coherently register remotely sensed data taken at different epochs with existing 3D building models. The sole use of corner points from existing building data bases as local features can lead to matching ambiguities and to errors in the registration. To address this issue for the registration of single images with existing 3D building models, we propose to use two types of matching cues: (1) edged corner features that represent the saliency of building corner points with associated edges; and (2) context features that represent the relations between the edged corner features within an individual roof. We have tested our approach on large urban areas with over 1000 building models in total
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
