Automatic online multiple pedestrian tracking is a rather important and challenging task in the field of machine vision. A new multiple pedestrian tracking system is proposed in this paper, which combines pedestrian detection, motion prediction, target matching and adaptive location adjustment methods. The clip-split strategy was adopted for optimization of the detected pedestrian candidates, which resulted in great improvement of the tracking accuracies, especially when the marginal areas of the detected target candidates contained background scenes. For each frame, the proposed adaptive location adjustment method was used to adjust the location and scale of the targets to deal with drifting problems where necessary, especially after severe occlusions. Experimental results on three challenging real-world datasets demonstrated that the proposed tracker has excellent performance over other state-of-the-art trackers based on MOT metrics.
相似文献![点击此处可从《计算机科学技术学报》网站下载免费的PDF全文](/ch/ext_images/free.gif)
In this paper, we propose an attention-based bipartite graph 3D model retrieval algorithm, where many-to-many matching method, the weighted bipartite graph matching, is employed for comparison between two 3D models. Considering the panoramic views can donate the spatial and structural information, in this work, we use panoramic views to represent each 3D model. Attention mechanism is used to generate the weight of all views of each model. And then, we construct a weighted bipartite graph with the views of those models and the weight of each view. According to the bipartite graph, the matching result is used to measure the similarity between two 3D models. We experiment our method on ModelNet, NTU and ETH datasets, and the experimental results and comparison with other methods show the effectiveness of our method.
相似文献Visual object tracking is of a great application value in video monitoring systems. Recent work on video tracking has taken into account spatial relationship between the targeted object and its background. In this paper, the spatial relationship is combined with the temporal relationship between features on different video frames so that a real-time tracker is designed based on a hash algorithm with spatio-temporal cues. Different from most of the existing work on video tracking, which is regarded as a mechanism for image matching or image classification alone, we propose a hierarchical framework and conduct both matching and classification tasks to generate a coarse-to-fine tracking system. We develop a generative model under a modified particle filter with hash fingerprints for the coarse matching by the maximum a posteriori and a discriminative model for the fine classification by maximizing a confidence map based on a context model. The confidence map reveals the spatio-temporal dynamics of the target. Because hash fingerprint is merely a binary vector and the modified particle filter uses only a small number of particles, our tracker has a low computation cost. By conducting experiments on eight challenging video sequences from a public benchmark, we demonstrate that our tracker outperforms eight state-of-the-art trackers in terms of both accuracy and speed.
相似文献In southeastern North America, Indigenous potters and woodworkers carved complex, primarily abstract, designs into wooden pottery paddles, which were subsequently used to thin the walls of hand-built, clay vessels. Original paddle designs carry rich historical and cultural information, but pottery paddles from ancient times have not survived. Archaeologists have studied design fragments stamped on sherds to reconstruct complete or nearly complete designs, which is extremely laborious and time-consuming. In Snowvision, we aim to develop computer vision methods to assist archaeologists to accomplish this goal more efficiently and effectively. For this purpose, we identify and study three computer vision tasks: (1) extracting curve structures stamped on pottery sherds; (2) matching sherds to known designs; (3) clustering sherds with unknown designs. Due to the noisy, highly fragmented, composite-curve patterns, each task poses unique challenges to existing methods. To solve them, we propose (1) a weakly-supervised CNN-based curve structure segmentation method that takes only curve skeleton labels to predict full curve masks; (2) a patch-based curve pattern matching method to address the problem of partial matching in terms of noisy binary images; (3) a curve pattern clustering method consisting of pairwise curve matching, graph partitioning and sherd stitching. We evaluate the proposed methods on a set of collected sherds and extensive experimental results show the effectiveness of the proposed algorithms.
相似文献With the popularity of storing large data graph in cloud, the emergence of subgraph pattern matching on a remote cloud has been inspired. Typically, subgraph pattern matching is defined in terms of subgraph isomorphism, which is an NP-complete problem and sometimes too strict to find useful matches in certain applications. And how to protect the privacy of data graphs in subgraph pattern matching without undermining matching results is an important concern. Thus, we propose a novel framework to achieve the privacy-preserving subgraph pattern matching in cloud. In order to protect the structural privacy in data graphs, we firstly develop a k-automorphism model based method. Additionally, we use a cost-model based label generalization method to protect label privacy in both data graphs and pattern graphs. During the generation of the k-automorphic graph, a large number of noise edges or vertices might be introduced to the original data graph. Thus, we use the outsourced graph, which is only a subset of a k-automorphic graph, to answer the subgraph pattern matching. The efficiency of the pattern matching process can be greatly improved in this way. Extensive experiments on real-world datasets demonstrate the high efficiency of our framework.
相似文献Text summarization presents several challenges such as considering semantic relationships among words, dealing with redundancy and information diversity issues. Seeking to overcome these problems, we propose in this paper a new graph-based Arabic summarization system that combines statistical and semantic analysis. The proposed approach utilizes ontology hierarchical structure and relations to provide a more accurate similarity measurement between terms in order to improve the quality of the summary. The proposed method is based on a two-dimensional graph model that makes uses statistical and semantic similarities. The statistical similarity is based on the content overlap between two sentences, while the semantic similarity is computed using the semantic information extracted from a lexical database whose use enables our system to apply reasoning by measuring semantic distance between real human concepts. The weighted ranking algorithm PageRank is performed on the graph to produce significant score for all document sentences. The score of each sentence is performed by adding other statistical features. In addition, we address redundancy and information diversity issues by using an adapted version of Maximal Marginal Relevance method. Experimental results on EASC and our own datasets showed the effectiveness of our proposed approach over existing summarization systems.
相似文献An increasing amount of media metadata are published by different organizations on the Web which leads to a fragmented dataset landscape. Identifying media metadata from disparate datasets and integrating heterogeneous datasets have many applications but also pose significant challenges. To tackle this problem, entity resolution methods are commonly used as an essential prerequisite for integrating media information from different sources and effectively foster the re-use of existing data sources. While the amount of media metadata published on the Web grows steadily, how to scale it well to large media knowledge bases while maintaining a high matching quality is a critical challenge. This article investigates the relationships between media entities. To that end, the media database is formulated as a knowledge graph with entities as nodes and the associations between related entities as edges. Thus, media entities are grouped into communities by how they share neighbors. Then, a structural clustering-based model is proposed to detect communities and discover anchor vertices as well as isolated vertices. Specifically, an initial seed set of matched anchor vertex pairs is obtained. Furthermore, an iterative propagation approach for identifying the matched entities in the whole graph is developed, where community similarity is introduced into the measure function to control the total measurement of candidate pairs. Therefore, starting with the elements of the initial seed set, the entity resolution algorithm updates the matching information over the whole network along with the neighbor relationships iteratively. Extensive experiments are conducted on real datasets to evaluate how the seed set impacts the matching process and performance. The experiment results show this model can achieve an excellent balance between accuracy and efficiency and is a clear improvement compared to state-of-the-art methods.
相似文献The measurement of the vessel pattern in fingers is a superior method for identifying individuals owing to its convenience and the security it offers. We introduce in this paper a new perspective to accomplish finger vein recognition. This method, which regards deformations as discriminative information, is distinct from existing methods that attempt to prevent the influence of deformations. The proposed technique is based on the observation that regular deformation, which corresponds to a posture change, can only exist in genuine vein patterns. In terms of methodology, we incorporate optimized matching to generate pixelbased 2D displacements that correspond to deformations. The texture of uniformity extracted from the displacement fields is taken as the final matching score. Evaluated on two publicly available databases, PolyU and SDU-MLA, extensive experiments demonstrated that the discriminability of the new feature derived from deformations is preferable. The equal error rate (EER) achieved is the lowest compared to that of state-of-the-art techniques.
相似文献Prior algorithms on graph simulation for distributed graphs are not scalable enough as they exhibit heavy message passing. Moreover, they are dependent on the graph partitioning quality that can be a bottleneck due to the natural skew present in real-world data. As a result, their degree of parallelism becomes limited. In this paper, we propose an efficient parallel edge-centric approach for distributed graph pattern matching. We design a novel distributed data structure called ST that allows a fine-grain parallelism, and hence guarantees linear scalability. Based on ST, we develop a parallel graph simulation algorithm called PGSim. Furthermore, we propose PDSim, an edge-centric algorithm that efficiently evaluates dual simulation in parallel. PDSim combines ST and PGSim in a Split-and-Combine approach to accelerate the computation stages. We prove the effectiveness and efficiency of these propositions through theoretical guarantees and extensive experiments on massive graphs. The achieved results confirm that our approach outperforms existing algorithms by more than an order of magnitude.
相似文献Skeleton-based action recognition has recently achieved much attention since they can robustly convey the action information. Recently, many studies have shown that graph convolutional networks (GCNs), which generalize CNNs to more generic non-Euclidean structures, are more exactly extracts spatial feature. Nevertheless, how to effectively extract global temporal features is still a challenge. In this work, firstly, a unique feature named temporal action graph is designed. It first attempts to express timing relationship with the form of graph. Secondly, temporal adaptive graph convolution structure (T-AGCN) are proposed. Through generating global adjacency matrix for temporal action graph, it can flexibly extract global temporal features in temporal dynamics. Thirdly, we further propose a novel model named spatial-temporal adaptive graph convolutional network (ST-AGCN) for skeletons-based action recognition to extract spatial-temporal feature and improve action recognition accuracy. ST-AGCN combines T-AGCN with spatial graph convolution to make up for the shortage of T-AGCN for spatial structure. Besides, ST-AGCN uses dual features to form a two-stream network which is able to further improve action recognition accuracy for hard-to-recognition sample. Finally, comparsive experiments on the two skeleton-based action recognition datasets, NTU-RGBD and SBU, demonstrate that T-AGCN and temporal action graph can effective explore global temporal information and ST-AGCN achieves certain improvement of recognition accuracy on both datasets.
相似文献Heterogeneous information networks, which consist of multi-typed vertices representing objects and multi-typed edges representing relations between objects, are ubiquitous in the real world. In this paper, we study the problem of entity matching for heterogeneous information networks based on distributed network embedding and multi-layer perceptron with a highway network, and we propose a new method named DEM short for Deep Entity Matching. In contrast to the traditional entity matching methods, DEM utilizes the multi-layer perceptron with a highway network to explore the hidden relations to improve the performance of matching. Importantly, we incorporate DEM with the network embedding methodology, enabling highly efficient computing in a vectorized manner. DEM’s generic modeling of both the network structure and the entity attributes enables it to model various heterogeneous information networks flexibly. To illustrate its functionality, we apply the DEM algorithm to two real-world entity matching applications: user linkage under the social network analysis scenario that predicts the same or matched users in different social platforms and record linkage that predicts the same or matched records in different citation networks. Extensive experiments on real-world datasets demonstrate DEM’s effectiveness and rationality.
相似文献