Unsupervised Object Pose Classification from Short Video Sequences

Liang, Mei; Sun, Min; Carter, Kevin M.; Hero, Alfred O.; Savarese, Silvio

doi:10.5244/c.23.89

Cited by 11 publications

(28 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of experimental results (on a public dataset [21] and on an extension of [21]) demonstrate that our methods increases discrimination power in pose classification even in presence of large intra-class variability, background clutter, and occlusions. We show that our method achieves superior pose classification rate than state-of-the art holistic approaches [21,28] as well as benchmark methods based on feature selection such as LDA/FDA [24].…”

Section: Introductionmentioning

confidence: 99%

“…Obviously, it is critical to simultaneously minimize the intra-class variability while maximizing the intra-pose distance for category-level pose estimation. Recent works have leveraged machine learning methods to classify object pose at categorical level from single images [32,7,19,29,31,12,23] or videos [21]. While most of these works mainly focus on the problem of minimizing intra-class variability (issue A), little attention has been put to simultaneously tackle both issue A and issue B.…”

Section: Introductionmentioning

confidence: 99%

“…We show that our method achieves superior pose classification rate than state-of-the art holistic approaches [21,28] as well as benchmark methods based on feature selection such as LDA/FDA [24].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…We use [21] as a starting point for our work. In [21] authors show that a more compact and descriptive statistical manifolds can be learnt from short video sequences rather than still images, and that these manifolds enable accurate pose classification of object categories. Unlike in [21], however, where an holistic object pose representation is used, we follow the intuition that a part based representation (or pictorial structure or constellation model) [9,18,10] is capable of delivering more design flexibility to handle intra-class variability, occlusion and background clutter.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Robust object pose estimation via statistical manifold modeling

Liang

Liu

Hero

et al. 2011

2011 International Conference on Computer Vision

Self Cite

View full text Add to dashboard Cite

We propose a novel statistical manifold modeling approach that is capable of classifying poses of object categories from video sequences by simultaneously minimizing the intra-class variability and maximizing inter-pose distance. Following the intuition that an object part based representation and a suitable part selection process may help achieve our purpose, we formulate the part selection problem from a statistical manifold modeling perspective and treat part selection as adjusting the manifold of the object (parameterized by pose) by means of the manifold "alignment" and "expansion" operations. We show that manifold alignment and expansion are equivalent to minimizing the intra-class distance given a pose while increasing the inter-pose distance given an object instance respectively. We formulate and solve this (otherwise intractable) part selection problem as a combinatorial optimization problem using graph analysis techniques. Quantitative and qualitative experimental analysis validates our theoretical claims.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Robust object pose estimation via statistical manifold modeling

Liang

Liu

Hero

et al. 2011

2011 International Conference on Computer Vision

Self Cite

View full text Add to dashboard Cite

show abstract

Multi-view Object Categorization and Pose Estimation

Savarese

2010

Studies in Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Abstract. Object and scene categorization has been a central topic of computer vision research in recent years. The problem is a highly challenging one. A single object may show tremendous variability in appearance and structure under various photometric and geometric conditions. In addition, members of the same class may differ from each other due to various degrees of intra-class variability. Recently, researchers have proposed new models towards the goal of: i) finding a suitable representation that can efficiently capture the intrinsic three-dimensional and multi-view nature of object categories; ii) taking advantage of this representation to help the recognition and categorization task. In this Chapter we will review recent approaches aimed at tackling this challenging problem and focus on the work by 55]. In [54, 55] multi-view object models are obtained by linking together diagnostic parts of the objects from different viewing point. Instead of recovering a full 3D geometry, parts are connected through their mutual homographic transformation. The resulting model is a compact summarization of both the appearance and geometry information of the object class. We show that such a model can be learnt via minimal supervision compared to competitive techniques. The model can be used to detect objects under arbitrary and/or unseen poses by means of a two-step algorithm. This algorithm, inspired by works in single object view synthesis (e.g., Seitz & Dyer [57]), has the ability to synthesize object appearance and shape properties at recognition time, and in turn estimate the object pose that best matches the observations. We conclude this Chapter by presenting experiments on detection, recognition and pose estimation results with respect to two datasets in [54,55] as well as to PASCAL Visual Object Classes (VOC) dataset [15]. Experiments indicate that representation and algorithms presented in [54,55] can be successfully employed in a number of generic object recognition tasks.

show abstract