thomas-cvpr06.zip - Paper "Towards Multi-View Object Class Detection".We present a novel system for generic object class detection. In contrast to most existing systems which focus on a single viewpoint or aspect, our approach can detect object
instances from arbitrary viewpoints. This is achieved by combining the Implicit Shape Model for object class detection proposed by Leibe and Schiele with the multi-view
specific object recognition system of Ferrari et al. After learning single-view codebooks, these are interconnected by so-called activation links, obtained through multi-view region tracks across different training views of individual object instances. During recognition, these integrated codebooks work together to determine the location
and pose of the object. Experimental results demonstrate the viability of the approach and compare it to a bank of independent single-view detectors.
,2009-11-13 05:25:04,下载20次
2009PatentSYSTEMFOR3DOBJECTRECOGNITION.zip - Patent:SYSTEM AND METHOD FOR 3D OBJECT RECOGNITION. The present invention provides a system and method for recognizing a 3D object in a single camera image and for determining the 3D pose of the object with respect to the camera coordinate system. In one typical application, the 3D pose is used to make a robot pick up the object. A view-based approach is presented that does not show the drawbacks of previous methods because it is robust to image noise, object occlusions, clutter, and contrast changes. Furthermore, the 3D pose is determined with a high accuracy. Finally, the presented method allows the recognition of the 3D object as well as the determination of its 3D pose in a very short computation time, making it also suitable for real-time applications. These improvements are achieved by the methods disclosed herein. ,2009-11-13 05:21:59,下载20次
gpusurf.zip - GPU Accelerating Speeded-Up Robust Features. Many computer vision tasks require interest point detection and description, such as real-time visual navigation. We present a GPU implementation of the recently proposed Speeded-Up Robust Feature extractor, currently the state of the art for
this task. Robust feature descriptors can give vast improvements
in the quality and speed of subsequent steps, but require intensive
computation up front that is well-suited to inexpensive graphics
hardware. We describe the algorithm’s translation to the GPU in
detail, with several novel optimizations, including a new method
of computing multi-dimensional parallel prefix sums. It operates
at over 30 Hz at HD resolutions with thousands of features and
in excess of 70 Hz at SD resolutions.,2009-11-13 05:14:55,下载18次
vcas_2009.zip - A method to detect new objects in a scene by
comparing an input query image and a movie database captured beforehand is proposed.
Our method is based on both feature point matching and edge matching. First, we select the most matched movie from the movie
database based on the number of matched feature points. In addition,
we can get unmatched points in the query by excluding the matched points from all the extracted feature points in the query. Next, the most matched frame is selected from the most matched movie. It has the most
matched points with an input query image. Canny edge detector is applied
to both the query and the most matched frame in order to find unmatched edges. By merging the results of unmatched points and unmatched
edges, new objects will be detected. Our method can be applied to various scenes such as indoor and outdoor. In experimental results, we represent that our proposed method achieves change detection in various scenes.,2009-11-13 05:13:11,下载13次
iav07-surf.zip - Detecting, identifying, and recognizing salient regions or feature points
in images is a very important and fundamental problem to the computer vision
and robotics community. Tasks like landmark detection and visual odometry,
but also object recognition benefit from stable and repeatable salient features
that are invariant to a variety of effects like rotation, scale changes, view point
changes, noise, or change in illumination conditions. Recently, two promising new
approaches, SIFT and SURF, have been published. In this paper we compare and
evaluate how well different available implementations of SIFT and SURF perform
in terms of invariancy and runtime efficiency.,2009-11-13 05:07:51,下载42次
eccv06.zip - In this paper, a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust
Features) is presented. It approximates or even outperforms previously proposed
schemes with respect to repeatability, distinctiveness, and robustness, yet
can be computed and compared much faster.
This is achieved by relying on integral images for image convolutions by building on the strengths of the leading existing detectors and descriptors (in casu, using a Hessian matrix-based measure for the detector, and a
distribution-based descriptor) and by simplifying these methods to the
essential. This leads to a combination of novel detection, description, and
matching steps. The paper presents experimental results on a standard
evaluation set, as well as on imagery obtained in the context of a real-life
object recognition application. Both show SURF’s strong performance.,2009-11-13 05:03:41,下载28次