Year: 2015
Type: article
Abstract: Recently, low-cost and small RGB-D sensors appear massively at the entertainment market. These sensors can\nacquire colored 3D models using color images and depth data. However, a limitation of the RGB-D sensor is that\nsunlight interferes with the pattern projecting LED. The sensor is most suitable only for indoor scenes. Some RGBD\nsensors are available in outdoor scenes. However, the measurement range is limited because the light of LED\nspreads in all directions. In this research, we developed a novel measurement method for RGB-D sensors, which\ncan measure shapes in outdoor scenes. This method uses several measurement data from multiple viewpoints, and\nestimates the shape and the sensor poses using Structure from Motion (SfM). However, a conventional imagebased\nSfM cannot determine a correct scale. To determine the correct scale, our method uses the depth information\nthat is obtained from partially acquired area which is near to the viewpoints. Then, our method optimizes the\nshape and the poses by a modified bundle adjustment with the depth information. It minimizes the reprojection\nerror of the features in the acquired images and the depth error between the estimated model and the measurement\ndepth. At last, our method generates dense point cloud using a multi-view stereo algorithm. Using both the\nacquired images and depth data, our method reconstructs the shape which locates out of measurement range in\noutdoor environment. In our experiment, we show that our method can measure the range up to 20 meters away by\nmeasuring from several viewpoints in the range of 5 meters using a RGB-D sensor in outdoor scenes.
Authors: Keisuke Fujimoto, Takashi Watanabe
Language: English
Topic: Advanced Vision and Imaging
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2883885965