Person re-identification (RE-ID) aims at associating the same pedestrian over non-overlapping surveillance scenes. A large number of approaches have emerged in recent years, and they mainly focus on designing middle o...
详细信息
ISBN:
(纸本)9781479983407
Person re-identification (RE-ID) aims at associating the same pedestrian over non-overlapping surveillance scenes. A large number of approaches have emerged in recent years, and they mainly focus on designing middle or high level features to highlight the most discriminative aspects of pedestrians. Due to the nonrigid structure of pedestrians, it is difficult to reidentify pedestrians by low-level features. We investigate the results of conventional person RE-ID approaches, and find that the inadequate utilization of low-level features lead to the poor performance. In this work, we propose a novel framework to utilize the low-level visual features in a more effective way. Given a result obtained from the conventional person RE-ID method, the framework returns a more reasonable result. The framework is extended from the manifold ranking method, and several adjustments are made taking the requirements of person RE-ID into consideration. Our framework is validated through experiments on two person RE-ID datasets (VIPeR and ETHZ), and results from four different conventional approaches show significant improvement.
Small target detection is a critical problem in the Infrared Search And Track (IRST) system. Although it has been studied for years, there are some challenges remained, e.g. cloud edges and horizontal lines are likely...
详细信息
Video stabilization is an important video enhancement technology which aims at removing undesired shaking from input videos. A challenging task in stabilization is to inpaint the missing pixels of undefined areas in t...
详细信息
Visual saliency detection has gained its popularity in computer vision in recent years. Depth information is proven as a fundamental element of human vision while it is underutilized in existing saliency detection app...
详细信息
Visual saliency detection has gained its popularity in computer vision in recent years. Depth information is proven as a fundamental element of human vision while it is underutilized in existing saliency detection approaches. In this paper, an effective visual object saliency detection model via RGB and depth cues mutual guided manifold ranking is proposed. The depth features are extracted to guide the saliency ranking of RGB image while the RGB saliency is used as the guide of depth map ranking as well. We obtain the final result by fusing the RGB and depth saliency maps. The experimental result on a benchmark dataset which contains 1000 RGB-D images demonstrates the effectiveness and superior performance compared with several state-of-art methods.
Blind image restoration is a typically ill-posed problem, many methods tend to construct the loss function using the latent image and blur kernel priors. In this paper, we propose a MAP framework for single image moti...
详细信息
Blind image restoration is a typically ill-posed problem, many methods tend to construct the loss function using the latent image and blur kernel priors. In this paper, we propose a MAP framework for single image motion deblurring by introducing a constrained regularization of approximate L0 and L1 sparsity respectively for latent image and motion kernel, and the optimization is conducted by fast numerical approaches. The proposed scheme is shown to be robust and effective by the experiments on both synthesized and real images. The results and comparisons to the state-of-the-art methods will be displayed.
In this paper, we present a method for discovering the common salient objects from a set of images. We treat co-saliency detection as a pairwise saliency propagation problem, which utilizes the similarity between each...
详细信息
ISBN:
(纸本)9781479983407
In this paper, we present a method for discovering the common salient objects from a set of images. We treat co-saliency detection as a pairwise saliency propagation problem, which utilizes the similarity between each pair of images to measure the common property with the guidance of a single saliency map image. Given the pairwise co-salient foreground maps, pairwise saliency is optimized by combining the initial background cues. Pairwise co-salient maps are then fused according to a novel fusion strategy based on the focus of human attention. Finally we adopt an integrated multi-scale scheme to obtain the pixel-level saliency map. Our proposed model makes the existing single saliency model perform well in co-saliency detection and is not overly sensitive to the initial saliency model selected. Extensive experiments on two benchmark databases show the superiority of our co-saliency model against the state-of-the-art methods both subjectively and objectively.
With the increasing volume of business the civil aviation data processing system, the data processing efficiency requirements become higher and higher. In order to improve the speed of data processing, we design a par...
详细信息
With the increasing volume of business the civil aviation data processing system, the data processing efficiency requirements become higher and higher. In order to improve the speed of data processing, we design a parallel scheme of GRIB according to the GRIB data processing flow. We achieved the parallel processing of GRIB data reading and decoding process, and carried out the related test. It is significantly improve the speed of data loading.
The reasonable measuring of particle weight and effective sampling of particle state are consid- ered as two important aspects to obtain better estimation precision in particle filter. Aiming at the comprehensive trea...
详细信息
The reasonable measuring of particle weight and effective sampling of particle state are consid- ered as two important aspects to obtain better estimation precision in particle filter. Aiming at the comprehensive treatment of above problems, a novel two-stage prediction and update particle filte- ring algorithm based on particle weight optimization in multi-sensor observation is proposed. Firstly, combined with the construction of muhi-senor observation likelihood function and the weight fusion principle, a new particle weight optimization strategy in multi-sensor observation is presented, and the reliability and stability of particle weight are improved by decreasing weight variance. In addi- tion, according to the prediction and update mechanism of particle filter and unscented Kalman fil- ter, a new realization of particle filter with two-stage prediction and update is given. The filter gain containing the latest observation information is used to directly optimize state estimation in the frame- work, which avoids a large calculation amount and the lack of universality in proposal distribution optimization way. The theoretical analysis and experimental results show the feasibility and efficiency of the proposed algorithm.
In this paper, we address the problem of human action recognition by representing image sequences as a sparse collection of patch-level spatiotemporal events that are salient in both space and time domain. Our method ...
详细信息
ISBN:
(纸本)9781479983407
In this paper, we address the problem of human action recognition by representing image sequences as a sparse collection of patch-level spatiotemporal events that are salient in both space and time domain. Our method uses a multi-scale volumetric representation of video and adaptively selects an optimal space-time scale under which the saliency of a patch is most significant. The input image sequences are first partitioned into non-overlapping patches. Then, each patch is represented by a vector of coefficients that can linearly reconstruct the patch from a learned dictionary of basis patches. We propose to measure the spatiotemporal saliency of patches using Shannon's self-information entropy, where a patch's saliency is determined by information variation in the contents of the patch's spatiotemporal neighborhood. Experimental results on two benchmark datasets demonstrate the effectiveness of our proposed method.
With the increasing volume of business the civil aviation data processing system,the data processing efficiency requirements become higher and *** order to improve the speed of data processing,we design a parallel sch...
详细信息
With the increasing volume of business the civil aviation data processing system,the data processing efficiency requirements become higher and *** order to improve the speed of data processing,we design a parallel scheme of GRIB according to the GRIB data processing *** achieved the parallel processing of GRIB data reading and decoding process,and carried out the related *** is significantly improve the speed of data loading.
暂无评论