A generative model for 3D urban scene understanding from movable platforms Supplementary Material
نویسندگان
چکیده
Bayesian inference often requires the calculation of posterior distributions. Unfortunately, only in special cases (e. g., conjugate priors) it is possible to compute analytically the posterior. Typical approximations to this computation are Laplace approximations and sampling. In sampling-based approaches the integral is approximated numerically. Markov chain Monte Carlo methods (MCMC) can be used to generate samples from a complex graphical model efficiently. The basic idea is to create an artificial ergodic Markov chain so that the posterior distribution of interest becomes a stationary distribution of the Markov chain. Hence, after a burn-in period sampling from the Markov chain yields samples from the posterior distribution [1]. The main challenge in MCMC methods is to create an adequate transition kernel for the Markov chain. Two major strategies have been developed, Metropolis-Hastings and Gibbs sampling. Metropolis-Hastings [4] uses an arbitrary proposal distribution q(x′|x) to sample a new candidate state x′ from the current state x of the Markov chain. x′ is accepted as the new state of the Markov chain with a certain probability A(x, x′), otherwise the current state x is replicated. The acceptance probabilityA(x, x′) is designed in such a way that the stochastic transition kernel T (·|x) defined by this procedure meets the detailed balance condition for Markov chains, i. e.,
منابع مشابه
Probabilistic Models for 3D Urban Scene Understanding from Movable Platforms
Visual 3D scene understanding is an important component in autonomous driving and robot navigation. Intelligent vehicles for example often base their decisions on observations obtained from video cameras as they are cheap and easy to employ. Inner-city intersections represent an interesting but also very challenging scenario in this context: The road layout may be very complex and observations ...
متن کاملA Generative Model of Indoor Scenes
In this Master thesis project, we tackle the problem of 3D indoor scene understanding from a single image. Following existing approaches, we parameterize the problem as one of estimating the faces of a 3D cuboid. Towards this goal, we propose a generative model of the scene, which takes advantage of sophisticated image features while utilizing a simple prior learned from the statistics of room ...
متن کاملUsing Articulated Scene Models for Dynamic 3D Scene Analysis in Vista Spaces
In this paper we describe an efficient but detailed new approach to analyze complex dynamic scenes directly in 3D. The arising information is important for mobile robots to solve tasks in the area of household robotics. In our work a mobile robot builds an articulated scene model by observing the environment in the visual field or rather in the so-called vista space. The articulated scene model...
متن کاملStructural Symmetries from Motion for Scene Reconstruction and Understanding
The identification and description of partial symmetries in man-made structures is a powerful tool to improve the quality of 3D reconstruction from unordered images and to enable high-level understanding of scene geometry. In this work we propose an approach to identify symmetries and exploit them in Structure from Motion (SfM). Our first contribution is a symmetry detection approach that uses ...
متن کاملTowards Automatic Large-Scale 3D Building Reconstruction: Primitive Decomposition and Assembly
In this paper we propose a pipeline for highly automatic building reconstruction based on 3D point clouds. 3D building models are of great interest for many applications including city planning, navigation, emergency response and tourism and their reconstruction has been intensively studied. It is, however, still a challenge to minimize manual intervention and to achieve highly automated proces...
متن کامل