Hierarchical Object Parsing from Noisy Point Clouds

Details Hierarchical Object Parsing from Noisy Point Clouds Hierarchical Object Parsing from Noisy Point Clouds

2011-08-18

arxiv.org/abs/1108.3605v1

Computer Science

Computer Vision and Pattern Recognition

12 pages, 16 figures

Scientific paper

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 object features and is corrupted by large amounts of noise. One way to handle this kind of data is by employing shape models that can accurately follow the object boundaries. Popular models such as Active Shape and Active Appearance models lack the necessary flexibility for this task. While more flexible models such as Recursive Compositional Models have been proposed, this paper builds on the Active Shape models and makes three contributions. First, it presents a flexible, mid-entropy, hierarchical generative model of object shape and appearance in images. The input data is explained by an object parsing layer, which is a deformation of a hidden PCA shape model with Gaussian prior. Second, it presents a novel efficient inference algorithm that uses a set of informed data-driven proposals to initialize local searches for the hidden variables. Third, it applies the proposed model and algorithm to object parsing from point clouds such as edge detection images, obtaining state of the art parsing errors on two out of three standard datasets without using any intensity information.

Affiliated with

Also associated with

No associations

Rating

Hierarchical Object Parsing from Noisy Point Clouds does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Hierarchical Object Parsing from Noisy Point Clouds, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Hierarchical Object Parsing from Noisy Point Clouds will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-180490