Search

Objectives: Remote sensing image demand text is a user‑friendly approach for users to acquire images through natural language. Time is a key element when searching for remote sensing images, thus extracting and understanding time description in remote sensing image demand text is critical in‑demand semantic analysis. However, a few pieces of research focus on time extraction and semantic computing of remote sensing image demand text, and time extraction and semantic computing are not combined to get full consideration of time semantic analysis. Methods: we collect remote sensing image demand texts from domains of disaster mitigation, agriculture, forestry, surveying and mapping. Then we extract time descriptions from demand texts manually and analyze their composition. By dividing time description into different time elements, a formal representation model is provided and time semantic representation rules as while as time semantic computation rules are proposed. Finally, a time ontology that integrates the time formal representation and semantic computing together is developed, which including four parts: Time semantic elements, time description, time model, and time knowledge. A rule‑based time extracting method and a semantic computing method which both based on the time ontology are also given. Results: We carried out experiments on 2 000 remote sensing image demand texts, which were divided into five groups. The baseline was made manually and compared with the results of our methods. We got an average precision of 97.1%. Experiments show that our method has better efficiency for understanding time information in remote sensing data demand text. Conclusions: Integrating time extraction and semantic computing into one ontology providing a seamless comprehension of time description in remote sensing image demand text, which helps to improve the efficiency of obtaining remote sensing images through natural language. [ABSTRACT FROM AUTHOR]

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Road network kernel density estimation is a cluster analysis method for event points under road network constraints. It is often used to study spatial distribution patterns of traffic accidents, urban crimes, vehicle trajectories and other events. The traditional serial algorithm of road network kernel density estima- tion has higher efficiency under the condition of small data volume, but with the increase of data volume, the performance of the algorithm is significantly reduced, which can not meet the actual application require- ments. In this paper, an efficient parallel algorithm based on Spark computing framework is designed and implemented for road network segmentation and kernel density calculation in road network kernel density estimation method. Taking traffic accidents as an example, four groups of experiments are used for com - parative analysis. The results show that the parallel algorithm of road network kernel density estimation based on Spark computing framework has high computational efficiency and good extensibility. [ABSTRACT FROM AUTHOR]

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The "six-in-one" road code is the basic text data, which used to locate accidents and violations in the traffic management business, it lacks spatial information. However, The existing road network data in common use, such as Gacxle road network, is a kind of road network where one complete road is expressed by multiple road sections. Gaode road network' currency is relatively low compared to the OSM(OpenStreetMap) road network and it is hard to meet the demand for traffic management business. In order to solve the problems as above, this paper used Gaode road network as a basis and a high-currency OSM road network as a complement. It applied LCSS ( longest common subsequence) algorithm commonly used in trajectory clustering to road matching, then applied the Stroke method in the road network fusion after the road network matching. The experiment results show that LCSS algorithm has a good effect in road network's matching. Finally, based on this, it developed a road network's matching and fusion program, which applied in the Wuhan Traffic Management Bureau. [ABSTRACT FROM AUTHOR]

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The boundary-constrained max-p-regions problem is proposed to tackle the automatic regionalization problem in urban space with respect to constraining regions by boundaries. On the premise of maximized the number of regions p, a weighted objective function considering the subordinate uncertainty of spatial elements is designed to deal with the subordinat uncertainty caused by the intersec-tiou of elements and multiple boundaries. Besides a threshold constraint and other constraints in the max-^?-regions problem, several boundary constraints are incorporated as well. A region would normally be within a certain boundary. If a region crosses boundaries, these boundaries must be encompassed by the region. A Tabu-search based heuristic algorithm is designed and implemented to solve this NP-hard problem. The effectiveness are evaluated through a simulation dataset and a real-world dataset. The results show that the proposed model allows researchers and practitioners flexibly incorporate boundary constraints in real-world problems into the model specification, thus exerts more practical control over the regionalization results. [ABSTRACT FROM AUTHOR]

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Pedestrian detection is a hot topic and difficult problem in areas like computer vision and intelligent traffic. This paper researches on pedestrian detection in complex indoor space using depth sensors. In recent years, target detection methods based on RGB-Depth(RGBD) data mainly include background learning method and feature detecting operator method. However, the former method depends on the background knowledge of first tens of frames, and the number of frames decides the final detection accuracy. The latter takes plenty of time for computing, and being lacks of training samples may influence the detection result. Thus, this paper analyzes the complex scene features and integrates the color and depth information, and proposes a RGBD+ViBe (visual background extractor) background elimination method. The experiment results indicate that the detection accuracy of the proposed method is higher than the methods which only consider color or depth information and the RGBD+MoG method in foreground extraction. [ABSTRACT FROM AUTHOR]

This paper proposes a building polygon alignment approach for spatial data integration which can be used to improve the spatial data position accuracy. Firstly, this paper uses the minimum bounding rectangle combinatorial optimization algorithm to identify corresponding objects between the integrated data. Then, a pairwise constraint spectrum matching algorithm based on geometric simila-rity is proposed to detect conjugate-point pairs of 1:1, 1:N, and M:N correspondence. The conjugate-point pairs from 1:N, and M:N correspondence inevitably have weak or error corresponding point pair, thus this paper proposes a least-squares algorithm based on the IGG1 weight to align the corresponding objects. The proposed method is applied to align base map data with higher positional accuracy and Google map data with lower positional accuracy. The results show that the proposed method can not only detect conjugate-point pairs of 1:N, and M:N correspondence with complex contours, but also can achieve the accurate alignment between them, and minimize their difference of positional information. [ABSTRACT FROM AUTHOR]

City crimes tend to be clustered spatially and temporally. Knox test is an effective way to detect such interactions, however, this method has been criticized as being subjective because tbe determination of critical distances is arbitrary. This paper begins with an introduction of the Knox test and some common methods to select the spatial thresholds. Then a new approach is proposed to detect critical distances based on the average nearest neighborhood distance. Burglary, electric vehicle theft and pick pocketing events in Wuhan city are used as experimental data to validate the method. Results show that, compared with four common criteria, i.e., empirical distance, mean distance, Ripley’s K function threshold and natural breaks classification, the method we proposed is able to detect spatio-temporal interaction patterns of different events more effectively. The analysis results provide a reference for selecting critical distances for the Knox test. [ABSTRACT FROM AUTHOR]

Despite the large amount of floating car data,there are still some links lack of real-time data during some certain period of time. Therefore,it is difficult to estimate the travel time. Considering the problem of sparse data when using floating car data estimate the travel time,this paper put forward a kind of inferred method based on big data of floating car. It designed a three-layer artificial neural net-work model,whose input information and output information were the spatio-temporal correla- tion and the target link travel time respectively ,and obtained traffic spatio-temporal correlation relationship using historical big data of floating car and then inferred the travel time of target link. The experiment results indicate that the mean absolute percentage error of travel time can achieve to 30 percent. Compared with Naive model, the accuracy of ANN model performs better, and it is practical to solve the problem of data missing from the aspect of road net-work similarity. [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The existed address searching pre-prompt for standard address and POI information is relatively few. For the index of the address string, most will use Trie tree to index address. But Trie tree consumes huge memory in its establishment, especially when facing with massive data, the problem is particularly prominent. In view of these problems, this paper proposed a rapid address searching pre-prompt method based on key-value database. The method improved the structure of Trie tree, and reduced the complexity of address index. At the same time, the method avoided consuming huge memory in Trie tree establishment because of basing on key-value database to build the Trie tree. The experiment results show that the Trie tree index based on the key-value database has obvious advantages and efficiency in terms of transaction response performance and memory consumption compared with the Trie tree index based on memory construction. [ABSTRACT FROM AUTHOR]

Remote sensing (RS) images are an important source of geospatial data. However, current approaches in task-driven RS images discovery establish links between tasks and RS image parameters directly, without spatial-temporal constraints, leading to hard maintenance and low query precision Moreover, the complex relationship between tasks and RS images under spatial-temporal constraints is difficult to model and represent by rules. Thus, this research proposes an location and time method that not only filters but also acts as spatial-temporal constraint in the discovery process, and exploits the relationships between tasks and RS data sources under spatial-temporal constraints through Case-based Reasoning (CBR). The RS application case representation model and similarity assessment model is proposed to support analogical reasoning in CBR. A prototype system was developed to validate this method. The results show that the method is a feasible approach that improves the service efficacy of remote sensing data. [ABSTRACT FROM AUTHOR]

Although there exists quantities of GPS data of floating car, partial links lack real data during some certain period of time. Therefore, we can't estimate target link travel time. Considering the problem of sparse data when using floating car data estimating link travel time, we put forward a kind of inferred method based on big data of floating car. We designed a three-layer artificial neural network model, whose input information and output information are the feature relationship and the travel time ratio between target link and adjacent link respectively. We obtained traffic spatiotemporal association relationship using historical big data of floating car and then inferred link travel time. The model was verified by historical big data of Wuhan's floating car from March to July, 2014 and the MAPE of estimated value of link travel time is less than 25% which proved the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The movement trajectories of socioeconomic gravity centers can reflect the characteristics of micro and macro geographical structure evolution, while the correlation of gravity center trajectories indicates geographic relationships between different socioeconomic attributes. In this paper, we combine the analysis methods for entity object trajectories with geographic Center-of-Gravity models. We analyze movement patterns of trajectories generated from socioeconomic data as represented through directional rose-diagrams. A directional rose-diagram for trajectories allows analyzing movement patterns of socioeconomic gravity center trajectories from both individual and global scales. We also can extract the gravity center trajectories displaying significant patterns by tortuosity analysis. Besides, the half directional rose-diagram, an analysis tool especially for trajectory pairs, can intuitively express the relative relationship between two center trajectories. We take the trajectories of the center of gravity for 40 economic indicatorsin mainland China from 1985 to 2004 and mine their movement patterns as an example. This experiment provides a set of effective exploratory spatial-temporal data analysis tools for the study of socioeconomic data. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)