3d shape features are inherently scale-dependent. For instance, on a 3d model of a human body, the top of the head and a fingertip can both be detected as comer points, however, at entirely different scales. In this p...
详细信息
ISBN:
(纸本)9780769528250
3d shape features are inherently scale-dependent. For instance, on a 3d model of a human body, the top of the head and a fingertip can both be detected as comer points, however, at entirely different scales. In this paper, we present a method for extracting and integrating 3d shape features in the discrete scale-space of a triangular mesh model. We first parameterize the surface of the mesh model on a 2d plane and then construct a dense surface normal map. In general, the parametrization is not isometric. To account for this, we compute the relative stretch of the original edge lengths. Next, we compute a dense distortion map which is used to approximate the geodesic distances on the normal map. Then, we construct a discrete scale-space of the original 3d shape by successively convolving the normal map with distortion-adapted Gaussian kernels of increasing standarddeviation. We derive comer and edge detectors to extract 3d features at each scale in the discrete scale-space. Furthermore, we show how to combine the detector responses from different scales to form a unified representation of the 3d features.
A fully automatic 3d face recognition algorithm is presented. Several novelties are introduced to make the recognition robust to facial expressions and efficient. These novelties include: (1) Automatic 3d face detecti...
详细信息
ISBN:
(纸本)9780769528250
A fully automatic 3d face recognition algorithm is presented. Several novelties are introduced to make the recognition robust to facial expressions and efficient. These novelties include: (1) Automatic 3d face detection by detecting the nose;(2) Automatic pose correction and normalization of the 3d face as well as its corresponding 2d face using the Hotelling Transform;(3) A Spherical Face Representation and its use as a rejection classifier to quickly reject a large number of candidate faces for efficient recognition;and (4) Robustness to facial expressions by automatically segmenting the face into expression sensitive and insensitive regions. Experiments performed on the FRGC Ver 2.0 dataset (9,500 2d/3d faces) show that our algorithm outperforms existing 3d recognition algorithms. We achieved verification rates of 99.47% and 94.09% at 0.001 FAR and identification rates of 98.03% and 89.25% for probes with neutral and non-neutral expression respectively.
We present a novel method for detecting and quantifying 3d structure in stacks of microscopic images captured at incremental focal lengths. We express the image data as stochastically generated by an underlying model ...
详细信息
ISBN:
(纸本)9780769528250
We present a novel method for detecting and quantifying 3d structure in stacks of microscopic images captured at incremental focal lengths. We express the image data as stochastically generated by an underlying model for biological specimen and the effects of the imaging system. The method simultaneously fits a model for proposed structure and the imaging system's parameters, which include a model of the point spread function. We demonstrate our approach by detecting spores in image stacks of Alternaria, a microscopic genus of fungus. The spores are modeled as opaque ellipsoids and fit to the data using statistical inference. Since the number of spores in the data is not known, model selection is incorporated into the fitting process. Thus, we develop a reversible jump Markov chain Monte Carlo sampler to explore the parameter space. Our results show that simultaneous statistical inference of specimen and imaging models is useful for quantifying biological structures in 3d microscopic images. In addition, we show that inferring a model of the imaging system improves the overall fit of the specimen model to the data.
This paper introduces a new compression scheme, so-called Multi-Chart Geometry Video (MCGV), for 3ddynamic meshes with constant connectivity and time-varying geometry. The core of the proposed method is a piecewise a...
详细信息
ISBN:
(纸本)9780769528250
This paper introduces a new compression scheme, so-called Multi-Chart Geometry Video (MCGV), for 3ddynamic meshes with constant connectivity and time-varying geometry. The core of the proposed method is a piecewise affine predictor coupled with a Multi-Chart Geometry IMage (MCGIM) representation of the residual errors. The mesh is first partitioned into vertex clusters whose motion can be accurately described by a unique 3d affine transform. The prediction errors are represented as MCGIMs which are compressed by using standardized image encoders such as JPEG and MPEG-4. The performances of our encoder are objectively evaluated on a data set of six animation sequences with various sizes, geometries and topologies, and exhibiting both rigid and elastic motions. The experimental evaluation shows that the proposed MCGV achieves up to 60% lower compression distortions than the geometry video approach, while outperforming (with 30% to 94% lower distortions) the RT MPEG-4/AFX-IC, d3dMC, PCA anddynapack techniques.
As more and more human motion data are widely used to animate computer graphics figures in many applications, there is an imperative need to compress motion data for compact storage and fast transmission. We propose a...
详细信息
ISBN:
(纸本)9780769528250
As more and more human motion data are widely used to animate computer graphics figures in many applications, there is an imperative need to compress motion data for compact storage and fast transmission. We propose a data-driven method for efficient compression of human motion sequences by exploiting both spatial and temporal coherences of the data. We first segment a motion sequence into subsequences such that the poses within a subsequence lie near a low dimensional linear space. We then compress each segment using the principal component analysis. Further compression is achieved by storing only the key frames' projections to the principal component space and interpolating the other frames in-between the keyframes via spline functions. The experimental results show that our method can achieve significant compression rate with low reconstruction errors.
This paper demonstrates that, for axial non-central optical systems, the equation of a 3d line can be estimated using only four points extracted from a single image of the line. This result, which is a direct conseque...
详细信息
ISBN:
(纸本)9780769528250
This paper demonstrates that, for axial non-central optical systems, the equation of a 3d line can be estimated using only four points extracted from a single image of the line. This result, which is a direct consequence of the lack of vantage point, follows from a classic result in enumerative geometry: there are exactly two lines in 3-space which intersect four given lines in general position. We present a simple algorithm to reconstruct the equation of a 3d line from four image points. This algorithm is based on computing the Singular Value decomposition (SVd) of the matrix of Plucker coordinates of the four corresponding rays. We evaluate the conditions for which the reconstruction fails, such as when the four rays are nearly coplanar Preliminary experimental results using a spherical catadioptric camera are presented. We conclude by discussing the limitations imposed by poor calibration and numerical errors on the proposed reconstruction algorithm.
This paper presents a hybrid Id motion estimation algorithm which combines pixel-based and region-based approaches that can give depth images from translational video sequences with very high quality. Firstly, we comb...
详细信息
ISBN:
(纸本)9780769528250
This paper presents a hybrid Id motion estimation algorithm which combines pixel-based and region-based approaches that can give depth images from translational video sequences with very high quality. Firstly, we combine the motion information estimated by a variational regularization approach and by the Gabor transform through histogram analysis to identify those regions with zero motion (like for the sky). Then another round of region matching is carried out to refine the motion values for the other regions. Our algorithm can detect most of the sky regions segmented by foreground objects with complex geometry while keeping the boundaries of moving objects sharp and clear, which is an very important feature to obtain accurate 3d models. The high quality motion maps/depth images obtained by our algorithm are shown along with 3d reconstructions from novel viewpoints.
Multi-view stereo algorithms typically rely on same-exposure images as inputs due to the brightness constancy assumption. While state-of-the-art depth results are excellent, they do not produce high-dynamic range text...
详细信息
ISBN:
(纸本)9780769528250
Multi-view stereo algorithms typically rely on same-exposure images as inputs due to the brightness constancy assumption. While state-of-the-art depth results are excellent, they do not produce high-dynamic range textures required for high-quality view reconstruction. In this paper we propose a technique that adapts multi-view stereo for different exposure inputs to simultaneously recover reliable dense depth and high dynamic range textures. In. our technique, we use an exposure-invariant similarity statistic to establish correspondences, through which we robustly extract the camera radiometric response function and the image exposures. This enables us to then convert all images to radiance space and selectively use the radiance data for dense depth and high dynamic range texture recovery. We show results for synthetic and real scenes.
In this paper, a unified, segmentation-based approach is proposed to deal with both stereo reconstruction and moving objects detection problems using multiple stereo mosaics. Each set of parallel-perspective (pushbroo...
详细信息
ISBN:
(纸本)9780769528250
In this paper, a unified, segmentation-based approach is proposed to deal with both stereo reconstruction and moving objects detection problems using multiple stereo mosaics. Each set of parallel-perspective (pushbroom) stereo mosaics is generated from a video sequence captured by a single video camera. First a color-segmentation approach is used to extract the so-called natural matching primitives from a reference view of a pair of stereo mosaics to facilitate both 3d reconstruction of textureless urban scenes and man-made moving targets (e.g. vehicles). Multiple pairs of stereo mosaics are used to improve the accuracy and robustness in 3d recovery and occlusion handling. Moving targets are detected by inspecting their 3d anomalies, either violating the epipolar geometry of the pushbroom stereo or exhibiting abnormal 3d structure. Experimental results on both simulated and real video sequences are provided to show the effectiveness of our approach.
In this paper we propose a novel framework for efficiently extracting foreground objects in so called short-baseline image sequences. We apply the obtained segmentation to improve subsequent 3d reconstruction results....
详细信息
ISBN:
(纸本)9780769528250
In this paper we propose a novel framework for efficiently extracting foreground objects in so called short-baseline image sequences. We apply the obtained segmentation to improve subsequent 3d reconstruction results. Essentially, our framework combines a graph cut based optimization algorithm with an intuitive user interface. At first a meanshift segmentation algorithm partitions each image of the sequence into a certain number of regions. Additionally we provide an intelligent graphical user interface for easy specification of foreground as well as background regions across all images of the sequence. Within the graph cut optimization algorithm we define new energy terms to increase the robustness and to keep the segmentation of the foreground object coherent across all images of the sequence. Finally, a refined graph cut segmentation and several adjustment operations allow an accurate and effective foreground extraction. The obtained results are demonstrated on several real worlddata sets.
暂无评论