Recently the Normalized cut (Ncut) has been introduced to salient object detection [1, 2]. In this paper we validate that instead of proposing new detection models that leverage the Ncut, the previous geodesic salienc...
详细信息
ISBN:
(纸本)9781479983407
Recently the Normalized cut (Ncut) has been introduced to salient object detection [1, 2]. In this paper we validate that instead of proposing new detection models that leverage the Ncut, the previous geodesic saliency detection model which computes shortest paths on a graph can be adapted to eigenvectors of the Ncut to produce superior performance. Since the Ncut partitions a graph in a normalized energy minimization fashion, resulting eigenvectors contain decent cluster information that can group visual contents. Combining it with the existing geodesic saliency detection is conducive to highlighting salient objects uniformly, yielding to improved detection accuracy. Experiments by comparing with 12 existing methods on four benchmark datasets show the proposed method significantly outperforms the original geodesic saliency model and achieves comparable performance to state-of-the-art methods.
Learning Using Privileged Information (LUPI) provides an effective framework to solve the learning problem under situation of the asymmetric distribution of information between training and test time. It has been succ...
详细信息
Learning Using Privileged Information (LUPI) provides an effective framework to solve the learning problem under situation of the asymmetric distribution of information between training and test time. It has been successfully applied in the category recognition, e.g., protein classification, hand-writing recognition, animal categorization, etc. However, in the existing methods, various semantic attributes, with the help of experts, were only simply translated into the feature vectors and considered as the privileged data, which restricts the LUPI to the simple applications since it is difficult to guarantee that the privileged data is similarly informative about the problem at hand as the original data. Therefore, this paper presents a novel approach based on an attribute-ranking learning algorithm to construct the example-oriented privileged data. The main idea is to provide an effective means to transfer the mid-level semantic attributes to the original training data. Namely, we first obtain a real-valued rank per attribute for each example indicating the relative strength of the attribute presence in all examples, and then the resulting attribute ranking results are used to generate the privileged data. The experimental results show that the proposed approach provides a promising means to apply the privileged ranking attributes, and further demonstrate significant improvements in classification accuracy on three typical databases: PubFig, OSR and AwA.
This paper presents a novel object tracking method based on approximated Locality-constrained Linear Coding (LLC). Rather than using a non-negativity constraint on encoding coefficients to guarantee these elements non...
详细信息
ISBN:
(纸本)9781467397124
This paper presents a novel object tracking method based on approximated Locality-constrained Linear Coding (LLC). Rather than using a non-negativity constraint on encoding coefficients to guarantee these elements nonnegative, in this paper, the non-negativity constraint is substituted for a conventional l2 norm regularization term in approximated LLC to obtain the similar nonnegative effect. And we provide a detailed and adequate explanation in theoretical analysis to clarify the rationality of this replacement. Instead of specifying fixed K nearest neighbors to construct the local dictionary, a series of different dictionaries with pre-defined numbers of nearest neighbors are selected. Weights of these various dictionaries are also learned from approximated LLC in the similar framework. In order to alleviate tracking drifts, we propose a simple and efficient occlusion detection method. The occlusion detection criterion mainly depends on whether negative templates are selected to represent the severe occluded target. Both qualitative and quantitative evaluations on several challenging sequences show that the proposed tracking algorithm achieves favorable performance compared with other state-of-the-art methods.
This paper investigates the application of space geometry method for actuator fault detection and isolation(FDI) with disturbance inputs and measurement noises. To achieve the input signals, disturbances and noises ar...
详细信息
ISBN:
(纸本)9781479947249
This paper investigates the application of space geometry method for actuator fault detection and isolation(FDI) with disturbance inputs and measurement noises. To achieve the input signals, disturbances and noises are decoupled from residuals. Then the residual generator is designed and the relevant parameters are solved for it. When there are residuals exceed the threshold value, we can detect the faults. It can obtain single and multiple actuators FDI because of the method which we proposed satisfies the one-to-one corresponding relationship between faults and residuals. Simulation results demonstrate effectiveness of our proposed algorithm.
Aiming at the effective realization of particle filter for maneuvering target tracking in multi-sensor measurements,a novel multi-sensor multiple model particle filtering algorithm with correlated noises is *** with t...
详细信息
Aiming at the effective realization of particle filter for maneuvering target tracking in multi-sensor measurements,a novel multi-sensor multiple model particle filtering algorithm with correlated noises is *** with the kinetic evolution equation of target state,a multi-sensor multiple model particle filter is firstly constructed,which is also used as the basic framework of a new *** the new algorithm,in order to weaken the adverse influence from random measurement noises in the measuring process of particle weight,a weight optimization strategy is introduced to improve the reliability and stability of particle *** addition,considering the correlated noise existing in the practical engineering,a decoupling method of correlated noise is given by the rearrangement and transformation of the state transition equation and measurement *** the weight optimization strategy and noise decoupling method adopt respectively the center fusion structure and the off-line way,it improves the adverse effect effectively on computational complexity for increasing state dimension and sensor ***,the theoretical analysis and experimental results show the feasibility and efficiency of the proposed algorithm.
The aim of this work is to propose the fully automated pathological area extraction from multi-parametric 2D MR images of brain. The proposed method is based on multi-resolution symmetry analysis and automatic thresho...
详细信息
At present, in the field of pixel-level image fusion, researchers tend to treat each pixel independently, which destroys the relationship between the images to be fused. In view of this defects, this paper aims to pro...
详细信息
In this paper, a novel approach for image visual saliency detection is proposed from both the salient object (foreground) and the background perspective. To better highlight the salient object, we start from what is a...
详细信息
The visualization of calcifications could be obscured in mammograms because of overlapping of tissue structures. Dual-energy digital mammography (DEDM) can generate tissue-subtracted image for improving the detectabil...
详细信息
This paper presents a novel approach for finding more accurate feature pairs which is not only invariant to affine transformation, but also deals with images with repetitive shapes. First, the more accurate and robust...
详细信息
暂无评论