The quantitative evaluation of disparity maps is based on error measures. Among the existing measures, the percentage of Bad Matched Pixels (BMP) is widely adopted. Nevertheless, the BMP does not consider the magnitud...
详细信息
ISBN:
(纸本)9783642250842
The quantitative evaluation of disparity maps is based on error measures. Among the existing measures, the percentage of Bad Matched Pixels (BMP) is widely adopted. Nevertheless, the BMP does not consider the magnitude of the errors and the inherent error of stereo systems, in regard to the inverse relation between depth and disparity. Consequently, different disparity maps, with quite similar percentages of BMP, may produce 3D reconstructions of largely different qualities. In this paper, a ground-truth based measure of errors in estimated disparity maps is presented. It offers advantages over the BMP, since it takes into account the magnitude of the errors and the inverse relation between depth and disparity. Experimental validations of the proposed measure are conducted by using two state-of-the-art quantitative evaluation methodologies. Obtained results show that the proposed measure is more suited than BMP to evaluate the depth accuracy of the estimated disparity map.
This paper presents a method for vote-based 3D shape recognition and registration, in particular using mean shift on 3D pose votes in the space of direct similarity transforms for the first time. We introduce a new di...
详细信息
This paper presents a novel compact description of a pattern based on the interference of circular waves. The proposed approach, called "interference description", leads to a representation of the pattern, w...
详细信息
ISBN:
(纸本)9783642193088
This paper presents a novel compact description of a pattern based on the interference of circular waves. The proposed approach, called "interference description", leads to a representation of the pattern, where the spatial relations of its constituent parts are intrinsically taken into account. Due to the intrinsic characteristics of the interference phenomenon, this description includes more information than a simple sum of individual parts. Therefore it is suitable for representing the interrelations of different pattern components. We illustrate that the proposed description satisfies some of the key Gestalt properties of human perception such as invariance, emergence and reification, which are also desirable for efficient pattern description. We further present a method for matching the proposed interference descriptions of different patterns. In a series of experiments, we demonstrate the effectiveness of our description for several computervision tasks such as patternrecognition, shape matching. and retrieval.
This paper proposes a novel method for human action recognition. Different from many action recognition methods which consider an action sequence along the time axis, the proposed method views an action sequence along...
详细信息
ISBN:
(纸本)9781467300636
This paper proposes a novel method for human action recognition. Different from many action recognition methods which consider an action sequence along the time axis, the proposed method views an action sequence along the space axis. This brings two advantages: the human body structures in all frames are encoded in the feature;the time information is completely used. The process of feature extraction is as follows: first an action sequence is cut into slices parallel to the X-T plane. Every slice, we call X-T slice, is transformed to a mean histogram and a variance histogram along the T axis. Then all mean histograms and all variance histograms are concatenated separately to two vectors, and finally encoded with Mel Frequency Cepstrum Coefficient (MFCC). MFCC, a feature commonly used in speech recognition, can effectively capture changes of 1-D signals over time. The encoded values are sent to classifier for action recognition. Our system achieves very efficient result: it needs only 0.02 second to deal with a frame on average with Matlab.
The early development of computervision at Department of computer Science at University of Copenhagen (DIKU) is briefly described. The different disciplines in computervision are introduced, and the principles for t...
详细信息
ISBN:
(纸本)9783642233159;9783642233142
The early development of computervision at Department of computer Science at University of Copenhagen (DIKU) is briefly described. The different disciplines in computervision are introduced, and the principles for teaching two courses, an image analysis course, and a robot lab class are outlined.
Three-dimensional metrology problems are traditionally the domain of expensive devices like Laser-stripe sensors and custom-made projector-camera systems. The launch of Microsoft's Kinect sensor solved many of the...
详细信息
In this paper, we propose a human-tracking robot that can be used in commercial establishments such as airports and factories. The human-tracking process involves three main steps. The first is robust person identific...
详细信息
In this paper, a hybrid fingerprint matching algorithm based on phase correlation and minutiae points is proposed to improve the matching accuracy in fingerprint verification system. The phase correlation function whi...
详细信息
This paper presents a method aimed at classification of the environmental sounds in the visual domain by using the scale and translation invariance. We present a new approach that extracts visual features from sound s...
详细信息
ISBN:
(纸本)9783642250842
This paper presents a method aimed at classification of the environmental sounds in the visual domain by using the scale and translation invariance. We present a new approach that extracts visual features from sound spectrograms. We suggest to apply support vector machines (SVM's) in order to address sound classification. Indeed, in the proposed method we explore sound spectrograms as texture images, and extracts the time-frequency structures by using a translation-invariant wavelet transform and a patch transform alternated with local maximum and global maximum to pursuit scale and translation invariance. We illustrate the performance of this method on an audio database, which composed of 10 sounds classes. The obtained recognition rate is of the order 91.82 % with the multiclass decomposition method: One-Against-One.
Affine moment invariants are important shape descriptors in patternrecognition and computervision. Existing affine invariants methods are based on geometric and complex moments. In this paper, we propose a set of af...
详细信息
ISBN:
(纸本)9781457713033
Affine moment invariants are important shape descriptors in patternrecognition and computervision. Existing affine invariants methods are based on geometric and complex moments. In this paper, we propose a set of affine invariants extracted from Legendre moments. These invariants are derived by the relationship between the Legendre moment of the affine transformed image and that of the original image. The performance of the proposed descriptor is evaluated with a set of binary and gray images. Experimental results show that the proposed method behaves better than existing methods in terms of patternrecognition accuracy.
暂无评论