Correlation Filters for Object Alignment

Vishnu Naresh Boddeti; Takeo Kanade; B. V. K. Vijaya Kumar

doi:10.1109/cvpr.2013.297

Abstract

Alignment of 3D objects from 2D images is one of the most important and well studied problems in computer vision. A typical object alignment system consists of a landmark appearance model which is used to obtain an initial shape and a shape model which refines this initial shape by correcting the initialization errors. Since errors in landmark initialization from the appearance model propagate through the shape model, it is critical to have a robust landmark appearance model. While there has been much progress in designing sophisticated and robust shape models, there has been relatively less progress in designing robust landmark detection models. In this paper we present an efficient and robust landmark detection model which is designed specifically to minimize localization errors thereby leading to state-of-the-art object alignment performance. We demonstrate the efficacy and speed of the proposed approach on the challenging task of multi-view car alignment.

Keywords

LandmarkInitializationComputer scienceArtificial intelligenceComputer visionObject (grammar)Active appearance modelActive shape modelObject detectionRobustness (evolution)Pattern recognition (psychology)Image (mathematics)

Affiliated Institutions

Carnegie Mellon University US

Related Publications

Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model

Spyros Gidaris , Nikos Komodakis

We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting...

2015 799 citations

Building and using flexible models incorporating grey-level information

T.F. Cootes , Chris Taylor , Andreas Lanitis +2 more

This paper describes a technique for building compact models of the shape and appearance of flexible objects seen in 2-D images. The models are derived from the statistics of se...

2002 94 citations

Active appearance models

T.F. Cootes , G. Edwards , Chris Taylor

We describe a new method of matching statistical models of appearance to images. A set of model parameters control modes of shape and gray-level variation learned from a trainin...

2001 IEEE Transactions on Pattern Analysis... 5431 citations

Pictorial structures revisited: People detection and articulated pose estimation

Mykhaylo Andriluka , Stefan Roth , Bernt Schiele

Non-rigid object detection and articulated pose estimation are two related and challenging problems in computer vision. Numerous models have been proposed over the years and oft...

2009 2009 IEEE Conference on Computer Visi... 805 citations

Layered object detection for multi-class segmentation

Yi Yang , Sam Hallman , Deva Ramanan +1 more

We formulate a layered model for object detection and multi-class segmentation. Our system uses the output of a bank of object detectors in order to define shape priors for supp...

2010 98 citations

Publication Info

Year: 2013
Type: article
Pages: 2291-2298
Citations: 127
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Correlation Filters for Object Alignment

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

127

OpenAlex

Cite This

APA Style

                            
                                    Vishnu Naresh Boddeti, 
                                
                                    Takeo Kanade, 
                                
                                    B. V. K. Vijaya Kumar
                                
                            (2013). 
                            Correlation Filters for Object Alignment. 
                            
                            , 2291-2298.
                            https://doi.org/10.1109/cvpr.2013.297

Identifiers

DOI: 10.1109/cvpr.2013.297