Compressive sensing (CS) is a new technique for data sampling and compression simultaneously. In this paper, we propose a novel distributed video coding algorithm with dynamic measurement rate allocation based on comp...
详细信息
Compressive sensing (CS) is a new technique for data sampling and compression simultaneously. In this paper, we propose a novel distributed video coding algorithm with dynamic measurement rate allocation based on compressive sensing principles, where almost all computation burdens can be shifted to the decoder, resulting in a very low-complexity encoder. So the proposed algorithm can be useful in those video applications that require very low complex encoders. At the decoder, the compressed video can be efficiently reconstructed with adaptive dictionary learning. The simulation results show that the proposed algorithm outperforms the distributed compressive video sensing with non-adaptive learning local dictionary and global dictionary.
A new prediction algorithm of tourists flow distribution based on transition probability matrix (TPM) is proposed in this paper. In order to analyze the visitor transition-behavior and the tourists distribution model,...
详细信息
ISBN:
(纸本)9781467312882
A new prediction algorithm of tourists flow distribution based on transition probability matrix (TPM) is proposed in this paper. In order to analyze the visitor transition-behavior and the tourists distribution model, the tourists flow distribution of 5 zones at Shanghai Expo site is predicted based on the TPM, which is estimated by use of multivariate linear regression in optimization. The extensive experimental results verify the efficiency and the correctness of the proposed algorithm over the wavelet neural network prediction method.
In this paper, an algorithm to detect the position of a basketball in a real time outdoor video is proposed. The problem of ball detection in sports video arises due to the occlusion of the ball with the players, the ...
详细信息
In this paper, we propose a simple but effective method for the design of M-channel uniform linearphase (LP) filter banks. We are mainly concerned with the significant aliasing caused by the two adjacent filters, lead...
详细信息
Efficient video transmission over unreliable channels may encounter huge challenge due to unavoidable bit error or packets loss. Error concealment (EC) techniques at the decoder side have been developed to recover the...
详细信息
Edges are of significant importance in visual resolution perception. In this paper, we propose a novel image super-resolution method by enhancing the edges in the low resolution image. We first define a new edge sharp...
详细信息
ISBN:
(纸本)9781467322164
Edges are of significant importance in visual resolution perception. In this paper, we propose a novel image super-resolution method by enhancing the edges in the low resolution image. We first define a new edge sharpness feature: gradient profile sharpness (GPS), which considers both the absolute magnitude and the spatial scattering of edge gradient profile. Then we learn the relationship between GPSs in high resolution images and low resolution images, and we formulate a linear GPS transform to provide gradient prior for image reconstruction. Our GPS can represent edge sharpness perceptually well. And our super-resolution method can output harmonious and faithful images with better reconstruction quality.
In recent years, while stereoscopic images were becoming widely applied and the corresponding technologies were substantially developed, very few stereoscopic image quality assessment metrics were proposed, especially...
详细信息
In recent years, while stereoscopic images were becoming widely applied and the corresponding technologies were substantially developed, very few stereoscopic image quality assessment metrics were proposed, especially under the condition that there is no reference image available. This paper proposes a new no-reference stereoscopic image quality assessment algorithm based on the ocular dominance theory and degree of parallax. All of our tests using the Toyama database draw two valuable conclusions. First, the performances of stereoscopic image quality assessment methods are significantly affected by difference of image qualities between the left and right images. Second, to offset the discriminations of different degrees of parallax caused by various 3D image contents is required indeed. Experiments and comparative studies are provided to confirm the effectiveness of our proposed new stereoscopic image quality metric.
This paper proposes a novel method for robust object tracking. The method consists of three different components: a short term tracker, an object detector, and an online object model. For the short term tracker, we us...
详细信息
This paper proposes a novel method for robust object tracking. The method consists of three different components: a short term tracker, an object detector, and an online object model. For the short term tracker, we use an advanced Lucas Kanade tracker with bidirectional corner matching to capture object frame by frame. Meanwhile, statistical filtering and matching algorithm combined with haar-like feature random fern play as a detector to extract all possible object candidates in the current frame. Making use of trajectory information, the online object model decides the best target match among the candidates. And the model also trains the random fern feature adaptively online to better guide consecutive tracking. We demonstrate our method is robust to track an object in a long term and under large variations of view angle and lighting conditions. Moreover, our method is efficient to re-detect the object and keep tracking even after it's out of view or recover from heavy occlusion. To achieve state-of-the-art performance, it is highlighted that our method can be extended to multiple objects tracking application. Finally, comparisons with other state-of-the-art trackers are presented to show the robustness of our tracker.
Human group behaviors are usually composed of several sub-groups. Considering the interaction between groups, this paper presents an algorithm to recognize human group behavior with multi-group causalities. It has two...
Human group behaviors are usually composed of several sub-groups. Considering the interaction between groups, this paper presents an algorithm to recognize human group behavior with multi-group causalities. It has two main contributions: (1) we introduce inter-group causality to reflect the interaction between human groups, (2) an improved coding scheme (i.e. Locality-constrained Linear Coding) is used for encoding the causality to go beyond Vector Quantization (VQ). Finally, a simple linear SVM is adopted to learn this model. Our experiment results demonstrate that inter-group causality feature and LLC methods can significantly boost behavior recognition performance.
As it is known that launch vehicle is facing a very harsh environment during the fight process. The challenge of various perturbations and uncertainties has lead to many traditional control methods' failure to mee...
详细信息
As it is known that launch vehicle is facing a very harsh environment during the fight process. The challenge of various perturbations and uncertainties has lead to many traditional control methods' failure to meet the requirements of attitude control system. Due to the main advantage of sliding mode control's robustness to the system uncertainties and disturbances in the so-called sliding mode, it has been widely used in engineering. In this paper, regarding particularly on chattering problem, the authors developed a novel dynamic integral sliding mode control scheme and the comparative simulation results carried out with traditional dynamic integral sliding mode demonstrates the superiority of the newly designed control law.
暂无评论