| Paper: | WP-P5.3 |
| Session: | Image and Video Modeling III / Distributed Coding |
| Time: | Wednesday, September 19, 14:30 - 17:10 |
| Presentation: |
Poster
|
| Title: |
DISTANCE MEASUREMENT IN PANORAMA |
| Authors: |
Zhongding Jiang; Fudan University | | |
| | Nan Jiang; Fudan University | | |
| | Yijie Wang; Fudan University | | |
| | Binyu Zang; Fudan University | | |
| Abstract: |
Computing world distances of scene features from the captured images is a common task in image analysis and scene understanding. Previous projective geometry based methods focus on measuring distance from one single image. Hence, the scope of measurable scene is limited by the field-of-view (FOV) of one single camera. In this paper, we propose one method of measuring distances of line segments in real world scene using panorama representation. With a full view panorama, the scope of measurable scene is increased and can fully cover the sphere of 360x360 FOV. With panorama representation, distance of long-range features, which can not be fully captured by a single image, can be measured from the panoramic image. A prototype system called PanoMeasure is developed for enabling user to interactively measure the distances of line segments. Experiments with simulated data and real measurement results verify that the method offers high accuracy. |
