In cyber-physical systems, multidimensional data fusion is an important method to achieve comprehensive evaluation decisions and reduce data redundancy. In this paper, a data fusion algorithm based on fuzzy set theory...In cyber-physical systems, multidimensional data fusion is an important method to achieve comprehensive evaluation decisions and reduce data redundancy. In this paper, a data fusion algorithm based on fuzzy set theory and Dempster-Shafer(D-S) evidence theory is proposed to overcome the shortcomings of the existing decision-layer multidimensional data fusion algorithms. The basic probability distribution of evidence is determined based on fuzzy set theory and attribute weights, and the data fusion of attribute evidence is combined with the credibility of sensor nodes in a cyber-physical systems network. Experimental analysis shows that the proposed method has obvious advantages in the degree of the differentiation of the results.展开更多
To improve the robustness of visual tracking in complex environments such as: cluttered backgrounds, partial occlusions, similar distraction and pose variations, a novel tracking method based on adaptive fusion and pa...To improve the robustness of visual tracking in complex environments such as: cluttered backgrounds, partial occlusions, similar distraction and pose variations, a novel tracking method based on adaptive fusion and particle filter is proposed in this paper. In this method, the image color and shape cues are adaptively fused to represent the target observation; fuzzy logic is applied to dynamically adjust each cue weight according to its associated reliability in the past frame; particle filter is adopted to deal with non-linear and non-Gaussian problems in visual tracking. The method is demonstrated to be robust to illumination changes, pose variations, partial occlusions, cluttered backgrounds and camera motion for a test image sequence.展开更多
基金supported by the National Natural Science Foundation of China (No. 61462089)the Fundamental Research Funds for Beijing University of Civil Engineering and Architecture (No. X18002)
文摘In cyber-physical systems, multidimensional data fusion is an important method to achieve comprehensive evaluation decisions and reduce data redundancy. In this paper, a data fusion algorithm based on fuzzy set theory and Dempster-Shafer(D-S) evidence theory is proposed to overcome the shortcomings of the existing decision-layer multidimensional data fusion algorithms. The basic probability distribution of evidence is determined based on fuzzy set theory and attribute weights, and the data fusion of attribute evidence is combined with the credibility of sensor nodes in a cyber-physical systems network. Experimental analysis shows that the proposed method has obvious advantages in the degree of the differentiation of the results.
基金This work was jointly supported by the National Natural Science Foundation of China (No. 60375008)China PH.D Discipline Special Foundation (No. 20020248029)China Aviation Science Foundation (No. 02D57003)Aerospace Supporting Technology Foundation (No.2003-1.3 02), EXPO Technologies Special Project of National Key Technologies R&D Programme (No. 004BA908B07)Shanghai Key Technologies Preresearch Project (No. 035115009).
文摘To improve the robustness of visual tracking in complex environments such as: cluttered backgrounds, partial occlusions, similar distraction and pose variations, a novel tracking method based on adaptive fusion and particle filter is proposed in this paper. In this method, the image color and shape cues are adaptively fused to represent the target observation; fuzzy logic is applied to dynamically adjust each cue weight according to its associated reliability in the past frame; particle filter is adopted to deal with non-linear and non-Gaussian problems in visual tracking. The method is demonstrated to be robust to illumination changes, pose variations, partial occlusions, cluttered backgrounds and camera motion for a test image sequence.
