KR101824194B1 - Apparatus and method of visualization for spatiotemporal data - Google Patents

Apparatus and method of visualization for spatiotemporal data Download PDF

Info

Publication number
KR101824194B1
KR101824194B1 KR1020160024137A KR20160024137A KR101824194B1 KR 101824194 B1 KR101824194 B1 KR 101824194B1 KR 1020160024137 A KR1020160024137 A KR 1020160024137A KR 20160024137 A KR20160024137 A KR 20160024137A KR 101824194 B1 KR101824194 B1 KR 101824194B1
Authority
KR
South Korea
Prior art keywords
space
time
flow
time data
point
Prior art date
Application number
KR1020160024137A
Other languages
Korean (ko)
Other versions
KR20170101521A (en
Inventor
장윤
김석연
정성민
Original Assignee
세종대학교산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 세종대학교산학협력단 filed Critical 세종대학교산학협력단
Priority to KR1020160024137A priority Critical patent/KR101824194B1/en
Publication of KR20170101521A publication Critical patent/KR20170101521A/en
Application granted granted Critical
Publication of KR101824194B1 publication Critical patent/KR101824194B1/en

Links

Images

Classifications

    • G06F17/30241—
    • G06F17/30699—
    • G06F17/3087—
    • G06F17/30991—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present invention includes a processor for executing a program stored in a memory and a memory in which a space-time data processing program is stored. At this time, the processor generates a probability density function for discrete space-time data based on the kernel density estimation technique, extracts a flow based on the generated probability density function, visualizes the extracted flow, , And the discrete space-time data includes location and time.

Description

TECHNICAL FIELD [0001] The present invention relates to a visualization apparatus for temporal / spatial data and a visualization method of time-space data of a visualization apparatus. [0002]

The present invention relates to a visualization apparatus for time-space data and a method for visualizing time-space data of a visualization apparatus.

Spatiotemporal data is a collection of specific information that occurs locally over time. In this case, the spatiotemporal data may include location information such as latitude and longitude and time information.

Recently, with the spread of smartphones equipped with GPS (Global Positioning System), the amount and precision of the collected space-time data is increasing. Accordingly, various techniques for visualizing the spatio-temporal data have been developed.

The conventional space time data analysis method expresses spatio - temporal data on a map over time and performs analysis through a process of searching correlation and pattern over time using the spatio - temporal data. However, the conventional spatial-temporal data analysis method analyzes the movement of data by analyzing the visualization results one by one on the basis of various time axes. Therefore, conventional time-span data analysis methods can require considerable time and effort for data analysis and data search.

In this connection, Korean Patent Laid-Open Publication No. 10-2015-0072470 (entitled " Time and space domain dependency analysis system of traffic flow in urban areas and highways ") is applied to a road network in a complicated urban center and a highway, Discloses a system for analyzing dependencies in time and space domains and representing them as quantified indices.

Disclosure of Invention Technical Problem [8] The present invention provides a space-time data visualization apparatus capable of expressing a flow of space-time data and a method of visualizing space-time data of a visualization apparatus.

It should be understood, however, that the technical scope of the present invention is not limited to the above-described technical problems, and other technical problems may exist.

According to a first aspect of the present invention, there is provided a visualization apparatus for space-time data, comprising a memory for storing a space-time data processing program and a processor for executing a program stored in the memory. At this time, the processor generates a probability density function for discrete space-time data based on the kernel density estimation technique, extracts a flow based on the generated probability density function, visualizes the extracted flow, , And the discrete space-time data includes location and time.

According to a second aspect of the present invention, there is provided a method for visualizing space-time data by a visualization apparatus, comprising: generating a probability density function for discrete space-time data based on a kernel density estimation technique; Extracting a flow based on the generated probability density function; And visualizing the extracted flow. At this time, the discrete space-time data includes the position and the time.

The present invention can provide a visualized result so that the analyst can easily recognize the pattern of the data in the spatio-temporal data analysis. Therefore, the present invention can perform comprehensive analysis of data at various points of view only by confirming visualized results. In addition, the present invention enables efficient data search using only a minimum visual result.

FIG. 1 is a diagram showing an example of a conventional space time data visualization method.
2 is a block diagram of a space-time data visualization apparatus according to an embodiment of the present invention.
3 is a diagram illustrating an example of a space-time data visualization process according to an embodiment of the present invention.
Figure 4 is an illustration of visualized space-time data in accordance with an embodiment of the present invention.
5 is an illustration of visualization through a two-dimensional gravity model and a three-dimensional gravity model.
Figure 6 is an illustration of visualization in accordance with an embodiment of the present invention.
7 is a flowchart of a method of visualizing space-time data of a visualization apparatus according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "electrically connected" with another part in between . Also, when a part is referred to as "including " an element, it does not exclude other elements unless specifically stated otherwise.

Next, with reference to FIG. 1, a conventional space time data visualization method will be described.

Generally, spatio - temporal data visualization visualizes data distributed over space on a map at a certain point in time. The visualization of general space-time data will be described with reference to Fig.

FIG. 1 is a diagram showing an example of a conventional space time data visualization method.

For example, data P101 located on the left side of the map P100 for the viewpoint 't' in FIG. 1 (a) can be moved from the viewpoint 't + 1' to the right side P102 on the map P110 . At this time, the conventional space time data visualization method can visualize such data in the form of an arrow P121 directed from left to right on the map P120.

Referring to FIG. 1B, the space-time data P131 and P141 expressed on the maps P130, P140 and P150 at the time point t-1, the time point t and the time point t + , P151) can be visualized in the form of an arrow P161 directed from the lower left end of the map P160 to the lower right end in the conventional space time data visualization method.

As shown in Figs. 1 (a) and 1 (b), when overlapping portions are small or simple, visualization is easy in the conventional space time data visualization method. However, as shown in FIG. 1 (c), the real data has a lot of overlapping portions and is complicated. Therefore, in the conventional space-time data visualization method, actual data can be visualized in a complicated form in which the flow can not be grasped at a glance.

Therefore, it is difficult to analyze the movement patterns or characteristics of time-space data over time with respect to time-space data visualized in a complicated form using the conventional time-space data visualization method. Therefore, rather than visualizing the spatiotemporal data as it is, it is necessary to extract the flow map according to the movement and trend of the spatiotemporal data, and visualize the spatiotemporal data based on the extracted flow map.

Next, with reference to FIGS. 2 to 6, a space-time data visualization apparatus 200 according to an embodiment of the present invention will be described.

2 is a block diagram of a space-time data visualization apparatus 200 according to an embodiment of the present invention.

The spatiotemporal data visualization apparatus 200 visualizes discrete space-time data over time. Then, the spatiotemporal data visualization apparatus 200 can display the visualized space time data on the map. At this time, the spatiotemporal data visualization apparatus 200 includes a display unit 210, a memory 220, and a processor 230.

The display unit 210 can display the visualized space-time data.

The memory 220 stores a space-time data processing program. At this time, the memory 220 collectively refers to a non-volatile storage device that keeps stored information even when power is not supplied, and a volatile storage device that requires power to maintain stored information.

Also, the memory 220 may store discrete space-time data. The discrete space-time data stored at this time may be collected through a position receiving unit (not shown) and a communication unit (not shown) such as a GPS module included in the spatiotemporal data visualization apparatus 200. In addition, the stored discrete space-time data may be collected via a smartphone or computing device and then communicated via a communication unit (not shown).

The discrete space-time data may include position information corresponding to time and time. At this time, the location information may be latitude and longitude. In addition, the position information may be predetermined coordinate information for analyzing the space time data.

For example, the discrete spatiotemporal data may be trajectory data collected from one or more users. Also, the discrete space-time data may be usage log data for a social network service (SNS) collected from one or more users, but is not limited thereto.

The processor 230 executes a space-time data processing program stored in the memory 220 to perform visualization of discrete space-time data. The process of time-space data processing and visualization by the processor 230 will be described in detail with reference to FIG.

3 is a diagram illustrating an example of a space-time data visualization process according to an embodiment of the present invention.

As shown in FIG. 3 (a), the processor 230 can represent the discrete space-time data on a map based on the position.

The processor 230 may extract a probability density function based on a kernel density estimation technique for discrete space-time data. The processor 230 may then perform a functional representation using the extracted probability density function. At this time, the functional expression may be visualized as a heat map in the map as shown in FIG. 3 (b).

3C, the processor 230 may represent the discrete space-time data expressed in one map in the form of a three-dimensional cube according to time, based on the probability density function.

The processor 230 may extract a flow from space-time data expressed in a three-dimensional cubic form according to the kernel density estimation, as shown in FIG. 3 (d).

3 (e), the processor 230 can generate a flow map for the extracted flow using an arrow-shaped graphic or the like, and visualize space-time data.

Figure 4 is an illustration of visualized space-time data in accordance with an embodiment of the present invention.

Through the process described above, the processor 230 can extract continuity from the discrete space-time data. The processor 230 can visualize on the map the flow map generated based on the data distributed on the space, according to the viewpoint, based on the extracted continuity, as shown in Fig. That is, the processor 230 can express the data flow or pattern through the visualized data on the map.

As shown in FIG. 4, the processor 230 may provide visualized space-time data to an analyst (hereinafter, an analyst) that analyzes space-time data through the display unit 210. The analyst can analyze the flow or pattern of spatio-temporal data through visualized space-time data.

For example, referring to the map P400 of FIG. 4, most of the arrows represented in the first region P410 are shown to be extracted from the first region P410. Thus, analysts can see that as the first region (P410) over time, the density within the unit area continues to decrease.

In the second area P420, a pattern in which arrows converge is expressed. Therefore, the analyst can analyze the pattern of increasing density over time through the second region (P420).

In addition, the analyst may analyze patterns in which the arrows extend in the same direction in the third region (P430). Therefore, the analyst can analyze the movement path of spatio-temporal data through a path with a long arrow like the third region (P430).

Meanwhile, the processor 230 may use a kernel density estimation technique to generate a probability density function for discrete data. The kernel density estimation technique can be computed by generating a kernel based on the location of space-time data, and dividing the cumulative sum of generated kernels by the number of kernels. Therefore, the processor 230 can perform kernel density estimation based on the two-dimensional position information included in the space-time data.

For example, the processor 230 may perform kernel density estimation through Equation (1).

Figure 112016019620111-pat00001

In Equation (1), N is the number of data used for kernel density estimation, and K s is a kernel function. H s, i represents the bandwidth of the kernel. Also, x and y may represent positions. That is, x and y may be GPS coordinates or predetermined relative coordinates.

In the case of the Epanechnikov kernel function, which is a commonly used kernel function, it is impossible to differentiate the spatio-temporal data. Therefore, when visualization of spatiotemporal data is performed through the Epanechnikov kernel function based kernel density estimation technique, the directionality may be lost or the trend of the data flow can not be accurately expressed.

Therefore, in order to solve a problem that may occur in the process of processing space-time data using the Epanechnikov kernel function, the processor 230 according to an embodiment of the present invention uses a kernel function as a tri- You can use kernel functions. At this time, the processor 230 may transform the following Equation 2 into two-dimensional coordinate data.

Figure 112016019620111-pat00002

The processor 230 may generate a probability density function from discrete space-time data through a kernel density estimation technique.

Processor 230 may visualize the extracted discrete probability density function. For example, the processor 230 may visualize in the form of a heat map based on the extracted discrete probability density function. The processor 230 may then render the visualized map to the display unit 210.

On the other hand, the processor 230 can extract the vector field from the space-time data based on the generated probability density. At this time, in order to extract the vector field, the processor 230 may use a three-dimensional gravity model.

The gravity model is a widely used model in the social sciences to explain phenomena similar to the gravitational interactions of Newton's law of gravitation. Generally, a gravity model can be used to compare two different views.

However, the discrete space-time data according to an embodiment of the present invention is three-dimensional data including a position corresponding to a viewpoint and a viewpoint. Therefore, when a general gravity model is applied to two points in a discrete space-time data, time is not taken into consideration. Therefore, the gravity model must be calculated and visualized every time the viewpoint is changed.

5 is an illustration of visualization through a two-dimensional gravity model and a three-dimensional gravity model.

FIG. 5A is an example of a case where visualization is performed using a general two-dimensional gravity model using the space-time data at the first and second time points. In this way, when the visualization is performed using a general two-dimensional gravity model, since the time is not considered, it is difficult to determine the moving direction and the path.

On the other hand, the three-dimensional gravity model can fuse different physical quantities in space and time. Therefore, the 3D gravity model can extract the vector field for the whole interval included in the space - time data through one operation.

Referring again to FIG. 5, (b) of FIG. 5 illustrates an example of visualization using a three-dimensional gravity model using time-space data at the first and second time points. As described above, in the case of the visualization using the three-dimensional gravity model according to an embodiment of the present invention, since the time is taken together with the position, it is easy to analyze the movement direction and the path.

Therefore, the processor 230 can calculate the vector field for each viewpoint included in the discrete space-time data, based on the three-dimensional gravity model. In addition, the processor 230 may extract the flow based on the calculated vector field of each viewpoint. At this time, the three-dimensional gravity model for the position ( x , y ) and time ( t ) is expressed by Equation (3).

Figure 112016019620111-pat00003

In Equation (3), W is the size of the window on the space, and T is the size of the time axis. That is, W can represent the range in which gravity is computed in space. And, depending on the setting of the W and T values, it is possible to determine how to consider the wide range in space and time.

Further, d ij is a distance to two points to be compared, and a0 , a1 and a2 are predetermined constant values, respectively. a0 and a1 are parameters to be given to the center value or the peripheral value in the gravity calculation, and a2 is a parameter for the influence of the space-time distance on the gravity. For example, a0 and a1 may be set to 1, and a2 may be set to 2, but this is not restrictive.

Meanwhile, the processor 230 may extract a vector field from the discrete space-time data, and then extract a flow corresponding to the discrete space-time data based on the extracted vector field. The processor 230 may then express the flow pattern based on the extracted flow. Processor 230 may visualize the represented flow pattern.

Figure 6 is an illustration of visualization in accordance with an embodiment of the present invention.

The processor 230 may perform visualization using the flow extracted from each point in time-space data.

Referring to FIG. 6, the processor 230 may represent the visualized flow on a map as shown in FIG. 6 (a). At this time, the processor 230 can visualize and express the spatiotemporal data collected every one hour as shown in (b) to (e) of FIG. That is, the processor 230 can visualize space time data collected from 19:30 to 20:30 as shown in FIG. 6 (b). 6 (c), the processor 230 can visualize space time data from 20:30 to 21:30, and as shown in (d) of FIG. 6, Minute space-time data can be visualized.

Therefore, the analyst can analyze the visualized space-time data every hour through the display unit 210. That is, the analyst analyzes spatial and temporal data every one hour through one of FIGS. 6 (b) through 6 (e), analyzes patterns of space-time data with respect to time through FIGS. 6 (b) can do.

In addition, the processor 230 may perform visualization of discrete space-time data through the extracted flow and various additional visualization methods.

For example, the processor 230 may generate a layer based on various additional visualization methods, such as a heat map, a Line Integral Convolution (LIC), a particle, and a point sprite, corresponding to discrete spatiotemporal data . The processor 230 may perform multi-rendering using one or more layers created based on the layer corresponding to the extracted flow and various additional visualization methods. The processor 230 may blend the layers to visualize the final flow map.

In addition, the processor 230 can filter and visualize the flow corresponding to the query requested by the user among the extracted flows.

Specifically, when the user enters a query through an input unit (not shown), the processor 230 may filter the flow corresponding to the user's query in the extracted flow. The processor 230 may then visualize the filtered flow. At this time, the query may include at least one of spatial information and time information to be analyzed by the user.

For example, if the user wishes to analyze the flow for a particular area, the user can create a query that includes spatial information of a particular area. And upon entering a query through an input unit (not shown), the processor 230 may filter the flow in response to the query. The processor can visualize the filtered flow. And the processor 230 may display the visualized flow on the display module.

Through this, the user can analyze the trend of the specific space according to the time, based on the visualization result with respect to the specific space provided by the processor 230 over time.

Likewise, when the user wants to analyze the flow between regions in a specific time zone, he can generate a query including time information of a specific time zone. Then, when the processor 230 visualizes the results corresponding to the query, the user can analyze trends across regions for a particular time period through the visualized results.

Next, a method of visualizing space-time data by the visualization apparatus 200 according to an embodiment of the present invention will be described with reference to FIG.

7 is a flowchart of a method of visualizing the space-time data of the visualization apparatus 220 according to an embodiment of the present invention.

The visualization apparatus 200 generates a probability density function for discrete space-time data based on the kernel density estimation technique (S700). At this time, the discrete space-time data includes the position and the time. And the kernel density estimation technique may be based on a triweight kernel function.

The visualization apparatus 200 extracts the flow based on the generated probability density function (S710).

At this time, the visualization apparatus 200 can calculate the vector field for each viewpoint included in the discrete space-time data, based on the three-dimensional gravity model. Then, the visualization apparatus 200 can extract the flow based on the calculated vector field of each viewpoint.

The visualization apparatus 200 can visualize the extracted flow (S720).

And the visualization apparatus 200 may display the visualized flow on the display unit 210. [

Meanwhile, if the query for at least one of time and space is input from the user after the flow of the space time data is extracted, the visualization apparatus 200 may filter the flow corresponding to the inputted query from the extracted flow.

The visualization device 200 may then visualize the filtered extracted flow in response to the query.

The method for visualizing space-time data of the visualization apparatus 200 and the visualization apparatus 200 according to an exemplary embodiment of the present invention is a method for visualizing space-time data by analyzing space- . Therefore, the visualization apparatus 200 and the visualization apparatus 200 for spatial data visualization can perform comprehensive analysis of data at various points of view only by confirming visualized results. In addition, the visualization apparatus 200 and the visualization apparatus 200 for temporal and spatial data visualization can efficiently perform data search using only a minimum visual result.

One embodiment of the present invention may also be embodied in the form of a recording medium including instructions executable by a computer, such as program modules, being executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. The computer-readable medium may also include computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

While the methods and systems of the present invention have been described in connection with specific embodiments, some or all of those elements or operations may be implemented using a computer system having a general purpose hardware architecture.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

200: Spatio-temporal data visualization device
210: display unit
220: Memory
230: Processor

Claims (11)

A visualization apparatus for space-time data,
The memory in which the space-time data processing program is stored
And a processor for executing a program stored in the memory,
Wherein the processor generates a probability density function for discrete space-time data based on a kernel density estimation technique, extracts a flow based on the generated probability density function, Visualize,
Wherein the discrete space-time data includes a position and a time,
Calculates a vector field for each viewpoint included in the discrete space-time data based on a three-dimensional gravity model of the following equation, and extracts the flow based on the vector field of each calculated viewpoint.
[Mathematical Expression]
Figure 112017081460326-pat00011

x, y: first point
x p , y q : second point
t: First point
t r : the second time point
Figure 112017081460326-pat00012
: Estimation of kernel density at point 1
Figure 112017081460326-pat00013
: Estimation of kernel density at the second location
w (x p , y q , t r ): direction value for the second point with respect to the first point
W: Size of window in space
T: Size of the time axis
d ij : distance between two points to be compared
a0, a1 and a2: fixed constants delete The method according to claim 1,
Wherein the kernel density estimation technique is based on a TriWeight kernel function. The method according to claim 1,
Wherein the processor filters a flow corresponding to the input query from the extracted flow when a query for at least one of time and space is input from a user,
And visualizes the filtered flow corresponding to the input query. The method according to claim 1,
Further comprising a display unit,
Wherein the processor displays the visualized flow on the display unit. A method for visualizing space-time data by a visualization apparatus,
Generating a probability density function for discrete space-time data based on a kernel density estimation technique;
Extracting a flow based on the generated probability density function; And
Visualizing the extracted flow,
Wherein the discrete space-time data includes a position and a time,
The step of extracting the flow
Calculating a vector field for each viewpoint included in the discrete space-time data based on a three-dimensional gravity model of the following equation; And
And extracting the flow based on the vector field at each of the calculated viewpoints.
[Mathematical Expression]
Figure 112017081460326-pat00014

x, y: first point
x p , y q : second point
t: First point
t r : the second time point
Figure 112017081460326-pat00015
: Estimation of kernel density at point 1
Figure 112017081460326-pat00016
: Estimation of kernel density at the second location
w (x p , y q , t r ): direction value for the second point with respect to the first point
W: Size of window in space
T: Size of the time axis
d ij : distance between two points to be compared
a0, a1 and a2: fixed constants delete The method according to claim 6,
Wherein the kernel density estimation technique is based on a TriWeight kernel function. The method according to claim 6,
After the step of visualizing the extracted flow,
And displaying the visualized flow on a display unit. The method according to claim 6,
After extracting the flow,
Filtering a flow corresponding to the input query from the extracted flow when a query for at least one of time and space is input from a user; And
Further comprising visualizing the filtered flow filtered corresponding to the query. A computer-readable recording medium recording a program for performing the method according to any one of claims 6 to 9 on a computer.
KR1020160024137A 2016-02-29 2016-02-29 Apparatus and method of visualization for spatiotemporal data KR101824194B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020160024137A KR101824194B1 (en) 2016-02-29 2016-02-29 Apparatus and method of visualization for spatiotemporal data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020160024137A KR101824194B1 (en) 2016-02-29 2016-02-29 Apparatus and method of visualization for spatiotemporal data

Publications (2)

Publication Number Publication Date
KR20170101521A KR20170101521A (en) 2017-09-06
KR101824194B1 true KR101824194B1 (en) 2018-01-31

Family

ID=59925421

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020160024137A KR101824194B1 (en) 2016-02-29 2016-02-29 Apparatus and method of visualization for spatiotemporal data

Country Status (1)

Country Link
KR (1) KR101824194B1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101957194B1 (en) * 2018-10-18 2019-03-13 한국과학기술정보연구원 Apparatus and method for generating field line of flow analysis data

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140188940A1 (en) 2012-12-30 2014-07-03 International Business Machines Corporation Spatiotemporal encounters detection in historical movement datasets
WO2016004762A1 (en) 2014-07-11 2016-01-14 华为技术有限公司 Data visualization method and device

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140188940A1 (en) 2012-12-30 2014-07-03 International Business Machines Corporation Spatiotemporal encounters detection in historical movement datasets
WO2016004762A1 (en) 2014-07-11 2016-01-14 华为技术有限公司 Data visualization method and device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
김석연 외 3명. 시공간 데이터의 시각화를 통한 국내 인구 이동 데이터 분석. 2014년 한국컴퓨터종합학수대회 논문집. 2014년, 1316-1318페이지.

Also Published As

Publication number Publication date
KR20170101521A (en) 2017-09-06

Similar Documents

Publication Publication Date Title
Yang et al. Drivingstereo: A large-scale dataset for stereo matching in autonomous driving scenarios
Sun et al. Leveraging crowdsourced GPS data for road extraction from aerial imagery
Bakar et al. spTimer: Spatio-temporal Bayesian modeling using R
Kim et al. Spatiotemporal saliency detection for video sequences based on random walk with restart
US20200265630A1 (en) Generative image synthesis for training deep learning machines
US8873842B2 (en) Using human intelligence tasks for precise image analysis
Guney et al. Tailoring a geomodel for analyzing an urban skyline
US9105128B2 (en) Adaptive image acquisition and processing with image analysis feedback
US9727976B1 (en) Geospatial-temporal semantic graph representations of trajectories from remote sensing and geolocation data
US20220156636A1 (en) Efficient flood waters analysis from spatio-temporal data fusion and statistics
Obermaier et al. Visual trends analysis in time-varying ensembles
CN105075264A (en) Enhancing motion pictures with accurate motion information
Workman et al. Dynamic traffic modeling from overhead imagery
Zhang et al. Topogroups: Context-preserving visual illustration of multi-scale spatial aggregates
KR101824194B1 (en) Apparatus and method of visualization for spatiotemporal data
Gomes et al. Real-time discovery of hot routes on trajectory data streams using interactive visualization based on gpu
CN103530612B (en) Fast target detection method based on a small amount of sample
Woodring et al. Semi‐automatic time‐series transfer functions via temporal clustering and sequencing
Veeravasarapu et al. Model-driven simulations for computer vision
Aldrich et al. Viscous fingers: A topological visual analytics approach
KR101744776B1 (en) Apparatus for estimating a floating population using records of search maps and method thereof
Deng et al. Efficient occlusion-free visualization for navigation in mountainous areas
Schennings Deep convolutional neural networks for real-time single frame monocular depth estimation
Janetzko et al. Visual abstraction of complex motion patterns
Hirve et al. Improving Big Data Analytics With Interactive Augmented Reality

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant