Given a color image and depth map we match cuboidshaped objects in the scene. (a) and (b): The color image and aligned depth map from Kinect. (c): The cuboids detected by the proposed method and projected onto the color image. (d): The cuboids in the scene viewed from another perspective. These cuboids reveal important structures of the scene.
We propose a novel linear method to match cuboids in indoor scenes using RGBD images from Kinect. Beyond depth maps, these cuboids reveal important structures of a scene. Instead of directly fitting cuboids to 3D data, we first construct cuboid candidates using superpixel pairs on a RGBD image, and then we optimize the configuration of the cuboids to satisfy the global structure constraints. The optimal configuration has low local matching costs, small object intersection and occlusion, and the cuboids tend to project to a large region in the image; the number of cuboids is optimized simultaneously. We formulate the multiple cuboid matching problem as a mixed integer linear program and solve the optimization efficiently with a branch and bound method. The optimization guarantees the global optimal solution. Our experiments on the Kinect RGBD images of a variety of indoor scenes show that our proposed method is efficient, accurate and robust against object appearance variations, occlusions and strong clutter.
@inproceedings{RGBDcuboid,
Author = {Hao Jiang and Jianxiong Xiao},
Title = {A Linear Approach to Matching Cuboids in RGBD Images},
Booktitle = {26th IEEE Conference on Computer Vision and Pattern Recognition},
Year = {2013},
}
This research is supported by the U.S. NSF funding 1018641. Xiao is supported by Google U.S./Canada Ph.D. Fellowship.