Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-4/W5, 205-209, 2015
https://doi.org/10.5194/isprsarchives-XL-4-W5-205-2015
© Author(s) 2015. This work is distributed under
the Creative Commons Attribution 3.0 License.
 
12 May 2015
IMAGE SELECTION FOR 3D MEASUREMENT BASED ON NETWORK DESIGN
T. Fuse and R. Harada Dept. of Civil Engineering, University of Tokyo, Hongo 7-3-1, Bunkyo-ku, Tokyo, 113-8656,Japan
Keywords: Image Selection, Bundle Adjustment, Network Design, Visualization, Graph cut Abstract. 3D models have been widely used by spread of many available free-software. On the other hand, enormous images can be easily acquired, and images are utilized for creating the 3D models recently. However, the creation of 3D models by using huge amount of images takes a lot of time and effort, and then efficiency for 3D measurement are required. In the efficiency strategy, the accuracy of the measurement is also required. This paper develops an image selection method based on network design that means surveying network construction. The proposed method uses image connectivity graph. By this, the image selection problem is regarded as combinatorial optimization problem and the graph cuts technique can be applied. Additionally, in the process of 3D reconstruction, low quality images and similarity images are extracted and removed. Through the experiments, the significance of the proposed method is confirmed. Potential to efficient and accurate 3D measurement is implied.
Conference paper (PDF, 1480 KB)


Citation: Fuse, T. and Harada, R.: IMAGE SELECTION FOR 3D MEASUREMENT BASED ON NETWORK DESIGN, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-4/W5, 205-209, https://doi.org/10.5194/isprsarchives-XL-4-W5-205-2015, 2015.

BibTeX EndNote Reference Manager XML