29 August 2016 Generating dynamic street view images
Author Affiliations +
Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 100335M (2016); doi: 10.1117/12.2243605
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China
Abstract
In the contemporary age, usage of the street view systems like Google Street View is becoming increasingly common. These systems, make the visualization of the real street ambience easier on the Geographic Information System and also aids the users to effortlessly plan and determine their intended place of travel. However, such street view systems are generally not updated on a regular basis because the street view service provider requires numerous cars mounted with panoramic cameras to capture the real roadside surroundings. The main aim of this paper is to propose a novel model that can create image sequences of random street view at any place by employing the images acquired from automotive video recorders. The notion of this model is identical to the theory of dynamic street view frames preserved by the common handlers. The proposed model is employed to design a framework that can map any frame recorded by a video event data recorder to the already available databank consisting of several panoramic street view images. A new image warping technique has been proposed to reduce the geometric distortion present in the recreated street view frames.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Fay Huang, Kathiravan Srinivasan, Chih-Shan Cheng, "Generating dynamic street view images", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100335M (29 August 2016); doi: 10.1117/12.2243605; http://dx.doi.org/10.1117/12.2243605
PROCEEDINGS
4 PAGES


SHARE
KEYWORDS
Panoramic photography

Cameras

Image segmentation

Video

Image fusion

Image processing

Databases

Back to Top