Search

Abstract Similarity queries, including range queries and k nearest neighbor (kNN) queries, in metric spaces have applications in many areas such as multimedia retrieval, computational biology and location-based services. With the growing volumes of data, a distributed method is required. In this paper, we propose an Asynchronous Metric Distributed System (AMDS), to support efficient metric similarity queries in the distributed environment. AMDS uniformly partitions the data with the pivot-mapping technique to ensure the load balancing, and employs publish/subscribe communication model to asynchronous process large scale of queries. The employment of asynchronous processing model also improves robustness and efficiency of AMDS. In addition, we develop efficient similarity search algorithms using AMDS. Extensive experiments using real and synthetic data demonstrate the performance of metric similarity queries using AMDS. Moreover, the AMDS scales sublinearly with the growing data size.

With the advent of a large number of spatial-textual data, collective spatial keyword queries have been widely studied in recent years. However, the collective spatial keyword query studied so far usually looks for only a set of objects. In addition, the existing collective spatial keyword query algorithms are all based on index structure, which requires excessive additional memory overhead. In this paper, we study the Top-k collective spatial keyword queries(TkCoSKQ), which aims at retrieving a set G including k sets of objects. Each group of object set can cover all the query keywords, and the objects in the set are close to the query position and have the minimum inter-object distance. We prove that the TkCoSKQ problem is NP-hard, and then propose two index-independent algorithms based on the spatial-textual similarity constraint, containing an exact algorithm and a heuristic algorithm. In addition, a variety of effective pruning strategies are presented to minimize the search scope. A large number of experiments on real datasets demonstrate the effectiveness and scalability of the proposed algorithms.

Similarity search in metric spaces finds similar objects to a given object, which has received much attention as it is able to support various data types and flexible similarity metrics. In real-life applications, metric spaces might be combined with graphs, resulting in geo-social network, citation graph, social image graph, to name but a few. In this paper, we introduce a new notion called quasi-metric graph that connects metric data using a graph, and formulate similarity search on quasi-metric graphs based on the combined similarity metric considering both the metric data similarity and graph similarity. We propose two simple efficient approaches, the best-first method and the breadth-first method, which traverse the quasi-metric graph following the best-first and the breadth-first paradigms, respectively, and utilize the triangle inequality to prune unnecessary evaluation. Extensive experiments with three real datasets demonstrate, compared with several baseline methods, the effectiveness and efficiency of our proposed methods.

In the study of SLAM problem using an RGB-D camera, depth information and visual information as two types of primary measurement data are rarely tightly coupled during refinement of camera pose estimation. In this paper, a new method of RGB-D camera SLAM is proposed based on extended bundle adjustment with integrated 2D and 3D information on the basis of a new projection model. First, the geometric relationship between the image plane coordinates and the depth values is constructed through RGB-D camera calibration. Then, 2D and 3D feature points are automatically extracted and matched between consecutive frames to build a continuous image network. Finally, extended bundle adjustment based on the new projection model, which takes both image and depth measurements into consideration, is applied to the image network for high-precision pose estimation. Field experiments show that the proposed method has a notably better performance than the traditional method, and the experimental results demonstrate the effectiveness of the proposed method in improving localization accuracy.