Almost all work on texture in the computervision and graphics communities has modeled the texture as tangential, i.e. lying in the tangent plane to the surface. This is equivalent to thinking of the texture as a patt...
详细信息
ISBN:
(纸本)0780342364
Almost all work on texture in the computervision and graphics communities has modeled the texture as tangential, i.e. lying in the tangent plane to the surface. This is equivalent to thinking of the texture as a pattern painted on the surface. Three-dimensional textures, where the elements may point out of the surface, have largely been ignored. We study a special class of 3D textures, perpendicular textures where we can model the elements as being normal to the surface. The perspective projection of perpendicularly textured surfaces results in several interesting phenomena, which do not occur in the much-studied tangential texture cease. These include occlusion, foreshortening and illumination. In this paper, we study the geometry of the problem, modeling the locations of the elements of the texture as being a realization of a spatial point process. Relations between slant and tilt of the surface, density and height of elements and occlusions are derived. Occlusions can now be used as a cue to infer shape, instead of being treated as a source of error.
Scaling up fine-grained recognition to all domains of fine-grained objects is a challenge the computervision community will need to face in order to realize its goal of recognizing all object categories. Current stat...
详细信息
ISBN:
(纸本)9781467369640
Scaling up fine-grained recognition to all domains of fine-grained objects is a challenge the computervision community will need to face in order to realize its goal of recognizing all object categories. Current state-of-the-art techniques rely heavily upon the use of keypoint or part annotations, but scaling up to hundreds or thousands of domains renders this annotation cost-prohibitive for all but the most important categories. In this work we propose a method for fine-grained recognition that uses no part annotations. Our method is based on generating parts using co-segmentation and alignment, which we combine in a discriminative mixture. Experimental results show its efficacy, demonstrating state-of-the-art results even when compared to methods that use part annotations during training.
We study the problem of estimating rigid motion from a sequence of monocular perspective images obtained by navigating around an object while fixating a particular feature point. We cast the problem in the framework o...
详细信息
ISBN:
(纸本)0818672587
We study the problem of estimating rigid motion from a sequence of monocular perspective images obtained by navigating around an object while fixating a particular feature point. We cast the problem in the framework of "epipolar geometry", and propose a filter based upon implicit dynamical model for recursively estimating motion under the fixation constraint. This allows us to compare the quality of the estimates directly against the ones obtained assuming a general rigid motion simply by changing the geometry of the parameter space, while maintaining the same structure of the recursive estimator. We also present a closed-form static solution from two views, and a recursive estimator of the relative pose between the viewer and the scene.
This paper presents a completely automated facial action and facial expression recognition system using 2D+3D images recorded in real-time by a structured light sensor. It is based on local feature tracking and rule-b...
详细信息
ISBN:
(纸本)9781424439942
This paper presents a completely automated facial action and facial expression recognition system using 2D+3D images recorded in real-time by a structured light sensor. It is based on local feature tracking and rule-based classification of geometric, appearance and surface curvature measurements. Good performance is achieved under relatively non-controlled conditions.
There exists an abundance of systems and algorithms for multiple target detection and tracking in video, and many measures for evaluating the quality of their output have been proposed. The contribution of this paper ...
详细信息
ISBN:
(纸本)9781467312288
There exists an abundance of systems and algorithms for multiple target detection and tracking in video, and many measures for evaluating the quality of their output have been proposed. The contribution of this paper lies in the following: first, it argues that such performance measures should have two fundamental properties - monotonicity and error type differentiability;second, it shows that the recently proposed measures do not have either of these properties and are thus less usable;third, it composes a set of simple measures, partly built on common practice, that does have these properties. The informativeness of the proposed set of performance measures is demonstrated through their application on face detection and tracking results.
In this paper we propose a new framework for point cloud instance segmentation. Our framework has two steps: an embedding step and a clustering step. In the embedding step, our main contribution is to propose a probab...
详细信息
ISBN:
(纸本)9781665445092
In this paper we propose a new framework for point cloud instance segmentation. Our framework has two steps: an embedding step and a clustering step. In the embedding step, our main contribution is to propose a probabilistic embedding space for point cloud embedding. Specifically, each point is represented as a tri-variate normal distribution. In the clustering step, we propose a novel loss function, which benefits both the semantic segmentation and the clustering. Our experimental results show important improvements to the SOTA, i.e., 3.1% increased average per-category mAP on the PartNet dataset.
We present a new approach to the tracking of very non rigid patterns of motion, such as water flowing down a stream. The algorithm is based on a ''disturbance map,'' which is obtained by linearly subtr...
详细信息
ISBN:
(纸本)0780342364
We present a new approach to the tracking of very non rigid patterns of motion, such as water flowing down a stream. The algorithm is based on a ''disturbance map,'' which is obtained by linearly subtracting the temporal average of the previous frames from the new frame. Every local motion creates a disturbance having the form of a wave, with a ''head'' at the present position of the motion and a historical ''tail'' that indicates the previous locations of that motion. These disturbances serve as loci of attraction for ''tracking particles'' that are scattered throughout the image. The algorithm is very fast and can be performed in real time. We provide excellent tracking results on various complex sequences, using both stabilized and moving cameras, showing: a busy ant column, waterfalls. rapids and. flowing streams, shoppers in a mall, and cars in a traffic intersection.
Automatic video browsing requires algorithms for detecting a variety of events, including production effects (e.g., scene breaks and captions) and moving objects. We present new methods that use edges and motion for d...
详细信息
ISBN:
(纸本)0818672587
Automatic video browsing requires algorithms for detecting a variety of events, including production effects (e.g., scene breaks and captions) and moving objects. We present new methods that use edges and motion for detecting production effects and computing motion segmentation. Production effects, such as cuts, dissolves, wipes and captions, can be detected by looking for new edges that are far from previous edges. A global motion computation is used to register consecutive images. We have also developed a method for motion segmentation, which does not require computing local optical flow. Our methods run at several frames per second on a Sparc workstation, and tolerate compression artifacts.
We demonstrate a concept of computervision as a secure, live service on the Internet. We show a platform to distribute a real lime vision algorithm using simple widely available web technologies, such as Adobe Flash....
详细信息
ISBN:
(纸本)9781424439942
We demonstrate a concept of computervision as a secure, live service on the Internet. We show a platform to distribute a real lime vision algorithm using simple widely available web technologies, such as Adobe Flash. We allow a user to access this service without downloading an executable or sharing the image stream with anyone. We support developers to publish without distribution complexity Finally the platform supports user-permitted aggregation of data for computervision research or analysis. We describe results a simple distributed motion detection algorithm. We discuss future scenarios for organically extending the horizon of computervision research.
暂无评论