Abstract
Abstract. An automated model-image fitting algorithm is proposed in this paper for generating façade texture image from pictures taken by smartphones or tablet PCs. The façade texture generation requires tremendous labour work and thus, has been the bottleneck of 3D photo-realistic city modelling. With advanced developments of the micro electro mechanical system (MEMS), camera, global positioning system (GPS), and gyroscope (G-sensors) can all be integrated into a smartphone or a table PC. These sensors bring the possibility of direct-georeferencing for the pictures taken by smartphones or tablet PCs. Since the accuracy of these sensors cannot compared to the surveying instruments, the image position and orientation derived from these sensors are not capable of photogrammetric measurements. This paper adopted the least-squares model-image fitting (LSMIF) algorithm to iteratively improve the image's exterior orientation. The image position from GPS and the image orientation from gyroscope are treated as the initial values. By fitting the projection of the wireframe model to the extracted edge pixels on image, the image exterior orientation elements are solved when the optimal fitting achieved. With the exact exterior orientation elements, the wireframe model of the building can be correctly projected on the image and, therefore, the façade texture image can be extracted from the picture.
Highlights
A photo-realistic 3D building model does describe the geometric information about the building and represent its real appearance
The façade mapping relies on the manual operations to create texture images is still the bottle neck of the photo-realistic building modelling
This paper proposes a concept toward automated façade texture generation for the photorealistic 3D building modelling using smartphones or tablet PCs
Summary
A photo-realistic 3D building model does describe the geometric information about the building and represent its real appearance. The recent mobile computing devices, such as smartphones and tablet PCs, usually equip with highresolution camera and built-in GPS receiver and G-sensors These sensors can be used for the direct geo-referencing while taking pictures of buildings. This paper proposes a concept toward automated façade texture generation for the photorealistic 3D building modelling using smartphones or tablet PCs. When the picture is taken, the device’s 3D coordinates are recorded from the built-in GPS receiver and its three rotation angles are recorded from the G-sensors. There are still two procedures “model selection” and “approximately fitting” requires human interactions This is because manual image interpretation is more robust and more efficient than computer algorithms. The proposed procedure shall improve the efficiency from the full-manual methods, while remain robust than full-automated approaches
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
