This paper presents an imaging method for 360-degree panoramic view based on four wide angle cameras. In order to complete the image mosaic, all the parameters such as focal length, principal point and distortion coef...
详细信息
This paper presents an imaging method for 360-degree panoramic view based on four wide angle cameras. In order to complete the image mosaic, all the parameters such as focal length, principal point and distortion coefficients, etc are calibrated by our proposed calibration toolbox. Then, our approach does not adopt the scheme which stitching all the images to the surrounding view after distortion correction. The proposed method directly calculates the mapping relationship between the wide-angle lens images and cylindrical projection images to generate lookup tables which can greatly simplifies the computation and reduces the loss of information in each image. Finally, panoramic image is composed by image registration and image fusion. Experimental results show that this method is valid.
Convolutional neural network (CNN) has achieved great success in many vision tasks. A key to this success is its ability to powerful automatically learns both high-level and low-level features. In general, low-level f...
详细信息
ISBN:
(纸本)9781479958306
Convolutional neural network (CNN) has achieved great success in many vision tasks. A key to this success is its ability to powerful automatically learns both high-level and low-level features. In general, low-level features have a small size of receptive fields and appear multiple times in different locations of objects, while high-level semantic features have a relatively large size of receptive fields and only appear once in a specific location of objects. However, traditional CNN treats these two kinds of features in the same manner, i.e., learning them by the convolution operation, which can be approximately considered as cumulating the probabilities that a feature appears in different locations. This strategy is reasonable for low-level features but not for high-level semantic ones, especially in the case of pedestrian detection, where a local feature can be shared by different locations but a semantic part, e.g., a head, only appears once for a human. To jointly model the spatial structure and appearance of high-level semantic features, we propose a new module to learn spatially weighted max pooling in CNN. The proposed method is evaluated on several pedestrian detection databases and the experimental results show that it achieves much better performance than traditional CNN.
With the polynomial vector space decomposition by using Normal Form theory, the normalized analytical solutions of modal resonance are derived, which solves that the traditional Normal Form solution cannot be easily o...
详细信息
ISBN:
(纸本)9781479986422
With the polynomial vector space decomposition by using Normal Form theory, the normalized analytical solutions of modal resonance are derived, which solves that the traditional Normal Form solution cannot be easily obtained under resonant condition. Based on the solution, from the viewpoint of whether the modal interaction couples and resonates or not, the nonlinear terms are decomposed into four types, i.e., uncoupled nonresonant terms, coupled nonresonant terms, uncoupled resonant terms and coupled resonant terms. The corresponding modes are categorized into 5 types, i.e., single modes, uncoupled nonresonant modes, coupled nonresonant modes, uncoupled resonant modes and coupled resonant modes. A reduced-order mode reconstruction based on least square method to estimate the coefficients of higher-order interactional modes is proposed. This might be potentially a new approach to cope with the challenge from huge amount of higher-order modes in higher-order nonlinear analysis. Two case studies are presented to analyze the types and reconstructions of the nonlinear modes, 2nd- and 3rd- order terms, which verifies the effectiveness of the proposed approach.
Based on the recent success of Low-Rank matrix Representation(LRR),we propose a novel classification method for robust face recognition,named LRR-based Classification(LRRC).By the ideal that if each data class is line...
详细信息
ISBN:
(纸本)9781479947249
Based on the recent success of Low-Rank matrix Representation(LRR),we propose a novel classification method for robust face recognition,named LRR-based Classification(LRRC).By the ideal that if each data class is linearly spanned by a subspace of unknown dimensions and the data are noiseless,the lowest-rank representations of a set of test vector samples with respect to a set of training vector samples have the nature of being both dense for within-class affinity and almost zero for between-class ***,the LRR exactly reveals the classification of the *** experimental results demonstrate that LRRC has competitive with state-of-the-art classification methods.
In this paper, an adaptive approximation image reconstruction method based on orthogonal triangular with column pivoting (QRCP) decomposition algorithm is proposed for single sample problem in face recognition. By usi...
详细信息
In this paper, an adaptive approximation image reconstruction method based on orthogonal triangular with column pivoting (QRCP) decomposition algorithm is proposed for single sample problem in face recognition. By using QRCP the single sample and its transpose are decomposed to two sets of basis images. Then an adaptive approximation image reconstruction method is proposed to reconstruct two approximation images from the two basis image sets respectively. The single training sample and its two approximation images of each object form a new training set, which can make the fisher linear discriminant analysis (FLDA) be applied to single sample problem in face recognition. The performance of the proposed method is verified on Yale, FERET, and ORL face databases. The experimental results indicate that the proposed method is efficient and outperforms some existing methods which are proposed to overcome the single sample problem.
In this paper, the design and development of a Building Energy and Environment Monitoring system (BEEMS) for smart campus applications is proposed. The system is implemented based on distributed sensor nodes using Zig...
详细信息
The effectiveness evaluation problem of electronic warfare command and controlsystem (EWCCS) under complex electromagnetic environment is investigated by using the analytic hierarchy process (AHP) method. First, the ...
详细信息
Supervisory control reconfiguration can handle the uncertainties including resource failures and task changes in discrete event systems. It was not addressed to exploit the robustness of closed-loop systems to accommo...
详细信息
With the development of smart substations, much attention has been focused on the transient magnetic field (TMF) generated during switching operation in substations. In order to study the TMF, a portable integrated sy...
详细信息
暂无评论