Name
Abstract | ||
|---|---|---|
Object parsing and segmentation from point clouds are challenging tasks because the relevant data is available only as thin structures along object boundaries or other features, and is corrupted by large amounts of noise. To handle this kind of data, flexible shape models are desired that can accurately follow the object boundaries. Popular models such as active shape and active appearance models (AAMs) lack the necessary flexibility for this task, while recent approaches such as the recursive compositional models make model simplifications to obtain computational guarantees. This paper investigates a hierarchical Bayesian model of shape and appearance in a generative setting. The input data is explained by an object parsing layer which is a deformation of a hidden principal component analysis (PCA) shape model with Gaussian prior. The paper also introduces a novel efficient inference algorithm that uses informed data-driven proposals to initialize local searches for the hidden variables. Applied to the problem of object parsing from structured point clouds such as edge detection images, the proposed approach obtains state-of-the-art parsing errors on two standard datasets without using any intensity information. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TPAMI.2012.262 | Pattern Analysis and Machine Intelligence, IEEE Transactions |
Keywords | Field | DocType |
Bayes methods,Gaussian processes,data handling,image denoising,image segmentation,inference mechanisms,object detection,principal component analysis,search problems,solid modelling,AAM,Gaussian prior,active appearance models,active shape models,data handling,flexible shape models,hidden PCA shape model deformation,hidden principal component analysis shape model,hidden variable search,hierarchical Bayesian model,hierarchical object parsing,inference algorithm,informed data-driven proposals,local search initialization,noise corrupted data,object boundaries,object segmentation,standard datasets,state-of-the-art parsing errors,structured noisy point clouds,Object parsing,active shape model,hierarchical models,markov random field optimization | Data modeling,Object detection,Computer vision,Active shape model,Bayesian inference,Pattern recognition,Computer science,Active appearance model,Image segmentation,Artificial intelligence,Parsing,Point cloud | Journal |
Volume | Issue | ISSN |
35 | 7 | 0162-8828 |
Citations | PageRank | References |
2 | 0.41 | 37 |
Authors | ||
1 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Adrian Barbu | 1 | 768 | 58.59 |