A novel algorithm is proposed in this paper to detect dim moving point target with several pixels size in infrared image sequence, taken by line scan camera in high speed moving platform, with heavy background clutter...
详细信息
In this paper, we present a new algorithm for camera calibration using concentric circles, which is a linear approach. Different from previous methods, we take the projective equations of three-dimensional circles, wh...
详细信息
In this paper, we present a new algorithm for camera calibration using concentric circles, which is a linear approach. Different from previous methods, we take the projective equations of three-dimensional circles, which include the intrinsic parameter matrix of the camera, as the basis of our calibration approach. According to the special structure of the projective equations in algebra, we can get a linear equation system about the intrinsic parameters. After enough equations constructed, the calibration can be easily finished. Our method needs three images of the two concentric circles at least, and all the five intrinsic parameters can be recovered. Experiments using computer simulated data demonstrate the robustness and accuracy of our method.
Accurate traffic parameters such as traffic flow, travel speeds and occupancies, are crucial to effective management of intelligent transportation systems (ITS). Some traffic data from loop detectors settled in arteri...
详细信息
Accurate traffic parameters such as traffic flow, travel speeds and occupancies, are crucial to effective management of intelligent transportation systems (ITS). Some traffic data from loop detectors settled in arterial streets are incomplete, and the importance of effectively imputing the missing values emerges. In this paper, a technique called least squares support vector machines (LS-SVMs) is introduced to predict missing traffic flow based on spatio-temporal analysis in urban arterial streets. To the best of our knowledge, it is the first time to apply the rising computational intelligence (CI) technique incorporating with state space approach in missing traffic data imputation. Having good generalization ability and guaranteeing global minima ensure its well performance in the area. A baseline imputation technique, expectation maximization/data augmentation (EM/DA), is selected for comparison because of its proved effectiveness in missing data recovery. Through persuasive comparisons of the techniques, the proposed model is proved to be more applicable and performs better in stability and adaptability, which reveals that it is a promising approach in missing data prediction.
We consider the problem of 3D modeling under the environments where colors of the foreground objects are similar to the background, which poses a difficult problem of foreground and background classification. A purely...
详细信息
We consider the problem of 3D modeling under the environments where colors of the foreground objects are similar to the background, which poses a difficult problem of foreground and background classification. A purely image-based algorithm is adopted in this paper, with no prior information about the foreground objects. We classify foreground and background by fusing the information at the pixel and region levels to obtain the similarity probability map, followed by a Bayesian sensor fusion framework to infer the space occupancy grid. The estimation of the occupancy allows incremental updating once a new observation is available, and the contribution of each observation can be adjusted according to its reliability. Finally, three parameters in the algorithm are analyzed in detail and experiments show the effectiveness of this method.
A method for 3D shape reconstruction of deformable surfaces from consecutive frames was presented. In our method, the model of the surface is represented by a triangulated mesh. The constraints for the model, includin...
详细信息
A method for 3D shape reconstruction of deformable surfaces from consecutive frames was presented. In our method, the model of the surface is represented by a triangulated mesh. The constraints for the model, including keypoint correspondences and disallowing large changes of edge orientation between consecutive frames, are formulated as Linear Programming (LP) constraints. Therefore the deformable surface 3D tracking method turns into an LP problem that can be effectively solved. The robustness and efficiency of our approach are validated on synthetic and real data.
In this paper, we present a scheme of similarity measure learning based on kernel optimization. Employing a data-dependent kernel model, the proposed scheme optimizes the spatial distribution of the training data in t...
详细信息
In this paper, we present a scheme of similarity measure learning based on kernel optimization. Employing a data-dependent kernel model, the proposed scheme optimizes the spatial distribution of the training data in the feature space, aiming to maximize the class separability of the data in the feature space. The learned similarity measure, derived from the optimized kernel, exhibits a favorable feature to the task of pattern classification, that the spatial resolution of the embedding space is expanded around the boundary areas, and shrunk around the homogeneous areas. Experiments demonstrate that using the learned similarity measure can substantially improve the performances of the K-nearest-neighbor classifier.
In this paper, we propose to kernelize linear learning machines, e.g., PCA and LDA, in the empirical kernel feature space, a finite-dimensional embedding space, in which the distances of the data in the kernel feature...
详细信息
In this paper, we propose to kernelize linear learning machines, e.g., PCA and LDA, in the empirical kernel feature space, a finite-dimensional embedding space, in which the distances of the data in the kernel feature space are preserved. The empirical kernel feature space provides a unified framework for the kernelization of all kinds of linear machines: performing a linear machine in the finite-dimensional empirical feature space, its nonlinear kernel machine is then established in the original input data space. This method is different from the conventional kernel-trick based kernelization, and more importantly, the final nonlinear kernel machines, called empirical kernel machines, are shown to be more efficient in many real-world applications, such as face recognition and facial expression recognition, than the kernel-trick based kernel machines.
Scintigraphic imagery is an important data source since it provides morphological and functional clinical informations. However, scintigraphic images present very bad quality because of several degradation factors. In...
详细信息
Scintigraphic imagery is an important data source since it provides morphological and functional clinical informations. However, scintigraphic images present very bad quality because of several degradation factors. In fact, the recorded data are embedded in noise modelled as the realisation of Poisson process. The aim of this paper is to provide a framework able to enhance nuclear images quality by Poisson intensity estimation. This framework consists, in a first step, of performing variance-stabilizing step for the Poisson process thanks to the Anscombe transformation. So the obtained data can be considered as contaminated by a white Gaussian noise. In a second step, it uses a Bayesian technique inspired of Pizurica approach, known in the literature for exhibiting good results as for white Gaussian noise. In fact, the complex wavelet packets were exploited regarding to Pizurica algorithm.
This paper presents a high-speed video transfer scheme and a real-time infrared spots detection algorithm designed for field programmable gate array (FPGA) implementation. Rather than IEEE 1394a, two IEEE 1394b interf...
详细信息
This paper presents a high-speed video transfer scheme and a real-time infrared spots detection algorithm designed for field programmable gate array (FPGA) implementation. Rather than IEEE 1394a, two IEEE 1394b interfaces are alternatively used to ensure high-resolution image transfer in real time. In order to execute fast infrared spots detection, a parallel algorithm that processes four pixels per clock cycle is proposed. It detects infrared spots in a single pass over a frame and its implementation is only composed of combinatorial logic and registers. Furthermore, the execution time of the algorithm is independent of image content. A prototype system is implemented in an FPGA device. It is capable of transferring 1024 × 768 images smoothly at 60 fps and detecting infrared sports in a 1024 × 768 image within 1.966ms, demonstrating its superiority over the existing multi-pass algorithms and some other one-pass algorithms. Details of software and hardware architecture are discussed in this paper.
How does man's vision system work? In some cross research fields like neurobiology, psychology and robotics researchers have been work hard to answer the question for long time. Now on visual cortex neuroscience h...
详细信息
How does man's vision system work? In some cross research fields like neurobiology, psychology and robotics researchers have been work hard to answer the question for long time. Now on visual cortex neuroscience has accumulate much experimental data and some theories like information redundancy reduction, sparse coding have given their interpretation of experiments, but understanding information processing as a whole , especially to make a representation of image with basic conceptions of receptive field and direction column, is still a difficult task. In our work, together with consideration of psychology and sparse coding a multi-resolution statistics scheme is given, signal grads statistics is carried out according to resolution level, strength and direction in space respectively. By comparing the distribution of nerve cell on visual cortex with one of neural network which works follow multi-resolution statistics, the similarity of both tell the arithmetic meanings of receptive field and direction column. With modern neuroscience experimental means the validation of the point of view in this article may be done in principle.
暂无评论