We present an energy-based approach to visual odometry from RGB-D images of a Microsoft Kinect camera. To this end we propose an energy function which aims at finding the best rigid body motion to map one RGB-D image into another one, assuming a static scene filmed by a moving camera. We then propose a linearization of the energy function which leads to a 6 × 6 normal equation for the twist coordinates representing the rigid body motion. To allow for larger motions, we solve this equation in a coarse-to-fine scheme. Extensive quantitative analysis on recently proposed benchmark datasets shows that the proposed solution is faster than a state-of-the-art implementation of the iterative closest point (ICP) algorithm by two orders of magnitude. While ICP is more robust to large camera motion, the proposed method gives better results in the regime of small displacements which are often the case in camera tracking applications.

We propose a method to generate highly detailed, textured 3D models of large environments from RGB-D sequences. Our system runs in real-time on a standard desktop PC with a state-of-the-art graphics card. To reduce the memory consumption, we fuse the acquired depth maps and colors in a multi-scale octree representation of a signed distance function. To estimate the camera poses, we construct a pose graph and use dense image alignment to determine the relative pose between pairs of frames. We add edges between nodes when we detect loop-closures and optimize the pose graph to correct for long-term drift. Our implementation is highly parallelized on graphics hardware to achieve real-time performance. More specifically, we can reconstruct, store, and continuously update a colored 3D model of an entire corridor of nine rooms at high levels of detail in real-time on a single GPU with 2.5GB.

We

Convex relaxation techniques have become a popular approach to shape optimization as they allow to compute solutions independent of initialization to a variety of problems. In this chapter, we will show that shape priors in terms of moment constraints can be imposed within the convex optimization framework, since they give rise to convex constraints. In particular, the lower-order moments correspond to the overall area, the centroid, and the variance or covariance of the shape and can be easily imposed in interactive segmentation methods. Respective constraints can be imposed as hard constraints or soft constraints. Quantitative segmentation studies on a variety of images demonstrate that the user can impose such constraints with a few mouse clicks, leading to substantial improvements of the resulting segmentation, and reducing the average segmentation error from 12% to 0.35%. GPU-based computation times of around 1 second allow for interactive segmentation.

No abstract