Results 1  10
of
164
Behavior recognition via sparse spatiotemporal features
 In VSPETS
, 2005
"... A common trend in object recognition is to detect and leverage the use of sparse, informative feature points. The use of such features makes the problem more manageable while providing increased robustness to noise and pose variation. In this work we develop an extension of these ideas to the spatio ..."
Abstract

Cited by 422 (4 self)
 Add to MetaCart
(Show Context)
A common trend in object recognition is to detect and leverage the use of sparse, informative feature points. The use of such features makes the problem more manageable while providing increased robustness to noise and pose variation. In this work we develop an extension of these ideas to the spatiotemporal case. For this purpose, we show that the direct 3D counterparts to commonly used 2D interest point detectors are inadequate, and we propose an alternative. Anchoring off of these interest points, we devise a recognition algorithm based on spatiotemporally windowed data. We present recognition results on a variety of datasets including both human and rodent behavior. 1.
Discriminative learning of Markov random fields for segmentation of 3d scan data
 In Proc. of the Conf. on Computer Vision and Pattern Recognition (CVPR
, 2005
"... We address the problem of segmenting 3D scan data into objects or object classes. Our segmentation framework is based on a subclass of Markov Random Fields (MRFs) which support efficient graphcut inference. The MRF models incorporate a large set of diverse features and enforce the preference that a ..."
Abstract

Cited by 116 (5 self)
 Add to MetaCart
(Show Context)
We address the problem of segmenting 3D scan data into objects or object classes. Our segmentation framework is based on a subclass of Markov Random Fields (MRFs) which support efficient graphcut inference. The MRF models incorporate a large set of diverse features and enforce the preference that adjacent scan points have the same classification label. We use a recently proposed maximummargin framework to discriminatively train the model from a set of labeled scans; as a result we automatically learn the relative importance of the features for the segmentation task. Performing graphcut inference in the trained MRF can then be used to segment new scenes very efficiently. We test our approach on three largescale datasets produced by different kinds of 3D sensors, showing its applicability to both outdoor and indoor environments containing diverse objects. 1.
Salient geometric features for partial shape matching and similarity
 jTOG
"... This article introduces a method for partial matching of surfaces represented by triangular meshes. Our method matches surface regions that are numerically and topologically dissimilar, but approximately similar regions. We introduce novel local surface descriptors which efficiently represent the ge ..."
Abstract

Cited by 116 (4 self)
 Add to MetaCart
This article introduces a method for partial matching of surfaces represented by triangular meshes. Our method matches surface regions that are numerically and topologically dissimilar, but approximately similar regions. We introduce novel local surface descriptors which efficiently represent the geometry of local regions of the surface. The descriptors are defined independently of the underlying triangulation, and form a compatible representation that allows matching of surfaces with different triangulations. To cope with the combinatorial complexity of partial matching of large meshes, we introduce the abstraction of salient geometric features and present a method to construct them. A salient geometric feature is a compound highlevel feature of nontrivial local shapes. We show that a relatively small number of such salient geometric features characterizes the surface well for various similarity applications. Matching salient geometric features is based on indexing rotationinvariant features and a voting scheme accelerated by geometric hashing. We demonstrate the effectiveness of our method with a number of applications, such as computing selfsimilarity, alignments, and subparts similarity.
Efficient shape matching using shape contexts
 IEEE TRANS. PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 2005
"... We demonstrate that shape contexts can be used to quickly prune a search for similar shapes. We present two algorithms for rapid shape retrieval: representative shape contexts, performing comparisons based on a small number of shape contexts, and shapemes, using vector quantization in the space of ..."
Abstract

Cited by 60 (2 self)
 Add to MetaCart
(Show Context)
We demonstrate that shape contexts can be used to quickly prune a search for similar shapes. We present two algorithms for rapid shape retrieval: representative shape contexts, performing comparisons based on a small number of shape contexts, and shapemes, using vector quantization in the space of shape contexts to obtain prototypical shape pieces.
Surface Feature Detection and Description with Applications to Mesh Matching
, 2009
"... In this paper we revisit local feature detectors/descriptors developed for 2D images and extend them to the more general framework of scalar fields defined on 2D manifolds. We provide methods and tools to detect and describe features on surfaces equiped with scalar functions, such as photometric inf ..."
Abstract

Cited by 45 (0 self)
 Add to MetaCart
In this paper we revisit local feature detectors/descriptors developed for 2D images and extend them to the more general framework of scalar fields defined on 2D manifolds. We provide methods and tools to detect and describe features on surfaces equiped with scalar functions, such as photometric information. This is motivated by the growing need for matching and tracking photometric surfaces over temporal sequences, due to recent advancements in multiple camera 3D reconstruction. We propose a 3D feature detector (MeshDOG) and a 3D feature descriptor (MeshHOG) for uniformly triangulated meshes, invariant to changes in rotation, translation, and scale. The descriptor is able to capture the local geometric and/or photometric properties in a succinct fashion. Moreover, the method is defined generically for any scalar function, e.g., local curvature. Results with matching rigid and nonrigid meshes demonstrate the interest of the proposed framework.
Matching with shape contexts
 IEEE Workshop on Contentbased access of Image and VideoLibraries
, 2000
"... Summary. We present a novel approach to measuring similarity between shapes and exploit it for object recognition. In our framework, the measurement of similarity is preceded by (1) solving for correspondences between points on the two shapes, (2) using the correspondences to estimate an aligning tr ..."
Abstract

Cited by 45 (2 self)
 Add to MetaCart
(Show Context)
Summary. We present a novel approach to measuring similarity between shapes and exploit it for object recognition. In our framework, the measurement of similarity is preceded by (1) solving for correspondences between points on the two shapes, (2) using the correspondences to estimate an aligning transform. In order to solve the correspondence problem, we attach a descriptor, the shape context, to each point. The shape context at a reference point captures the distribution of the remaining points relative to it, thus offering a globally discriminative characterization. Corresponding points on two similar shapes will have similar shape contexts, enabling us to solve for correspondences as an optimal assignment problem. Given the point correspondences, we estimate the transformation that best aligns the two shapes; regularized thin–plate splines provide a flexible class of transformation maps for this purpose. The dissimilarity between the two shapes is computed as a sum of matching errors between corresponding points, together with a term measuring the magnitude of the aligning transform. We treat recognition in a nearestneighbor classification framework as the problem of finding the stored prototype shape that is maximally similar to that in the image. We also demonstrate that shape contexts can be used to quickly prune a search for similar shapes. We present two algorithms for rapid shape retrieval: representative shape contexts, performing comparisons based on a small number of shape contexts, and shapemes, using vector quantization in the space of shape contexts to obtain prototypical shape pieces. Results are presented for silhouettes, handwritten digits and visual CAPTCHAs. 1
Partsbased 3D object classification
, 2004
"... This paper presents a partsbased method for classifying scenes of 3D objects into a set of predetermined object classes. Working at the part level, as opposed to the whole object level, enables a more flexible class representation and allows scenes in which the query object is significantly occlud ..."
Abstract

Cited by 35 (0 self)
 Add to MetaCart
This paper presents a partsbased method for classifying scenes of 3D objects into a set of predetermined object classes. Working at the part level, as opposed to the whole object level, enables a more flexible class representation and allows scenes in which the query object is significantly occluded to be classified. In our approach, parts are extracted from training objects and grouped into part classes using a hierarchical clustering algorithm. Each part class is represented as a collection of semilocal shape features and can be used to perform part class recognition. A mapping from part classes to object classes is derived from the learned part classes and known object classes. At runtime, a 3D query scene is sampled, local shape features are computed, and the object class is determined using the learned part classes and the parttoobject mapping. The approach is demonstrated by classifying novel 3D scenes of vehicles into eight classes.
Sparse points matching by combining 3D mesh saliency with statistical descriptors
, 2008
"... This paper proposes new methodology for the detection and matching of salient points over several views of an object. The process is composed by three main phases. In the first step, detection is carried out by adopting a new perceptuallyinspired 3D saliency measure. Such measure allows the detecti ..."
Abstract

Cited by 32 (4 self)
 Add to MetaCart
This paper proposes new methodology for the detection and matching of salient points over several views of an object. The process is composed by three main phases. In the first step, detection is carried out by adopting a new perceptuallyinspired 3D saliency measure. Such measure allows the detection of few sparse salient points that characterize distinctive portions of the surface. In the second step, a statistical learning approach is considered to describe salient points across different views. Each salient point is modelled by a Hidden Markov Model (HMM), which is trained in an unsupervised way by using contextual 3D neighborhood information, thus providing a robust and invariant point signature. Finally, in the third step, matching among points of different views is performed by evaluating a pairwise similarity measure among HMMs. An extensive and comparative experimental session has been carried out, considering real objects acquired by a 3D scanner from different points of view, where objects come from standard 3D databases. Results are promising, as the detection of salient points is reliable, and the matching is robust and accurate.
Fully automatic registration of 3d point clouds
 IN CVPR ’06: PROCEEDINGS OF THE 2006 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION
, 2006
"... We propose a novel technique for the registration of 3D point clouds which makes very few assumptions: we avoid any manual rough alignment or the use of landmarks, displacement can be arbitrarily large, and the two point sets can have very little overlap. Crude alignment is achieved by estimation of ..."
Abstract

Cited by 32 (0 self)
 Add to MetaCart
(Show Context)
We propose a novel technique for the registration of 3D point clouds which makes very few assumptions: we avoid any manual rough alignment or the use of landmarks, displacement can be arbitrarily large, and the two point sets can have very little overlap. Crude alignment is achieved by estimation of the 3Drotation from two Extended Gaussian Images even when the data sets inducing them have partial overlap. The technique is based on the correlation of the two EGIs in the Fourier domain and makes use of the spherical and rotational harmonic transforms. For pairs with low overlap which fail a critical verification step, the rotational alignment can be obtained by the alignment of constellation images generated from the EGIs. Rotationally aligned sets are matched by correlation using the Fourier transform of volumetric functions. A fine alignment is acquired in the final step by running Iterative Closest Points with just few iterations.
Shape topics: A compact representation and new algorithm for 3D partial shape retrieval
 In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’06
"... This paper develops an efficient new method for 3D partial shape retrieval. First, a Monte Carlo sampling strategy is employed to extract local shape signatures from each 3D model. After vector quantization, these features are represented by using a bagofwords model. The main contributions of this ..."
Abstract

Cited by 28 (2 self)
 Add to MetaCart
(Show Context)
This paper develops an efficient new method for 3D partial shape retrieval. First, a Monte Carlo sampling strategy is employed to extract local shape signatures from each 3D model. After vector quantization, these features are represented by using a bagofwords model. The main contributions of this paper are threefold as follows: 1) a partial shape dissimilarity measure is proposed to rank shapes according to their distances to the input query, without using any timeconsuming alignment procedure; 2) by applying the probabilistic text analysis technique, a highly compact representation "Shape Topics " and accompanying algorithms are developed for efficient 3D partial shape retrieval, the mapping from "Shape Topics " to "object categories " is established using multiclass SVMs; and 3) a method for evaluating the performance of partial shape retrieval is proposed and tested. To our best knowledge, very few existing methods are able to perform well online partial shape retrieval for large 3D shape repositories. Our experimental results are expected to validate the efficacy and effectiveness of our novel approach.