CN108052924B - Identification method of spatial motion behavior semantic mode - Google Patents
Identification method of spatial motion behavior semantic mode Download PDFInfo
- Publication number
- CN108052924B CN108052924B CN201711466898.1A CN201711466898A CN108052924B CN 108052924 B CN108052924 B CN 108052924B CN 201711466898 A CN201711466898 A CN 201711466898A CN 108052924 B CN108052924 B CN 108052924B
- Authority
- CN
- China
- Prior art keywords
- behavior
- time
- spatial
- frequency
- grid
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Abstract
The invention discloses a method for identifying a semantic mode of a spatial motion behavior, which comprises the following steps: sojourn behavior acquisition and judgment based on spatial positioning; establishing mathematical description and visual expression for the stay behavior, and establishing a spatial behavior semantic pattern map; and performing space-time frequent pattern mining according to the space behavior semantic pattern map. The spatial behavior pattern map expression mechanism and the measurement calculation method provided by the invention provide a basis for finding spatial semantic information. Because the regularity of the spatial behavior pattern statistical distribution conforms to the internal performance of the spatial behaviors of different professional groups, the method can indirectly understand the activity purpose and behavior motivation of a traveler, particularly distinctive abnormal dangerous behaviors, and reveal the hidden relation hidden in the behavior pattern and valuable for social security prevention and control, so that the social security precaution practical application based on the spatial movement big data abnormal behavior monitoring becomes possible.
Description
Technical Field
The invention belongs to the technical field of data analysis, relates to a spatial motion data analysis technology, and particularly relates to a method for identifying a spatial motion behavior semantic mode.
Background
Humans are performing various space activities every day, such as going to work in a unit and shopping in a store. As the human spatial behavior activities are purposeful or driven by tasks, the spatial behavior activities show group-related regularity, people with different professions and identities show different spatial behavior characteristics, most people returning early and late are office workers, and thieves can stroll around. In criminal activities endangering national and social security, criminals generally need to repeatedly step on points to the scene in order to find the best crime opportunity and plan escape routes, which is also a space behavior activity characteristic with strong motivation, most typically, the criminal frightening nationwide Zhoukua cases, in which dense stepping is performed before each robbery, and the longest stepping process lasts for 3 hours. Therefore, the spatial behavior activity rule of the object is an important identification information of identity and security behavior.
The path of the object activity and the regularity expressed by the stay time and frequency of the key position on the path form the space behavior mode of the object, the behavior mode reflects the semantic information of the space behavior, for example, the behavior with the stay time concentrated in two places of a residence and a unit corresponds to the work-on and work-off activity, and the behavior mode surrounding the frequent activity of the financial unit may be the stepping-on behavior before the plan. In addition, purposeful space behavior activities are influenced by geographic environment scenes, the space activity theme and the space scene theme are internally connected, and in criminal activities, different types of activities such as planning, jointing, escaping, material transferring and the like can occur in corresponding occasions, for example, in the occasion of a wharf, material transferring activities are likely to be implemented, and in the occasion of a railway station, escaping actions are likely to be implemented. Therefore, the semantic information of the spatial behavior pattern and the spatial scene can reveal the hidden relations such as the behavior motivation of the object, the real identity and the group relationship of the object and the like to a certain extent.
The current positioning systems such as a GPS, a mobile phone and the like can reliably measure the moving track and the stopping place of a moving target, but most of the space big data adopted by the current research is rich in moving track and insufficient in activity information, so that the rich semantic information behind the track is lost. The distribution rule of time, time period, duration and frequency of the object activities and the internal relation of behaviors and the geographical environment of the place of occurrence cannot be described by the spatial trajectory data. Furthermore, spatial patterns with similar spatial semantic information do not necessarily have similar spatial activity locations, e.g., office workers, but the work units and residences are not necessarily the same, thereby presenting difficulties in measuring spatial patterns with similar spatial semantic information.
Disclosure of Invention
With the development and popularization of various positioning technologies, the personal position information can be conveniently acquired and the movement and the stopping process can be observed. The objects and the geographic places have relations of stay, passing and the like, the stay is possibly difficult to measure the spatial position indoors, the rapid passing has limited effect on spatial behavior analysis, the outdoor stay is easy to be sensed by position service equipment, and the illustrated social security event often has a stay treading process. Therefore, the place, the duration and the frequency rule of the stay of the object are a meaningful spatial behavior description for safety precaution. By means of a knowledge expression mode of the knowledge graph, observation data of different places and time are gathered and structurally associated on a space-time dimension to form a space behavior mode graph of the object, and the space behavior mode rule of the object is visually and intuitively presented, so that the implicit space behavior motivation is conveniently observed.
Based on the above thought, the invention provides a method for identifying a spatial motion behavior semantic mode, which comprises the following steps:
step S1, collecting and judging the sojourn behavior based on space positioning;
step S2, establishing mathematical description and visual expression for the stay behavior, and establishing a spatial behavior semantic mode map;
and step S3, performing space behavior similarity measurement or time-space frequent pattern mining according to the space behavior semantic pattern map.
Preferably, the implementation process of step S1 includes the following sub-steps:
s1.1, collecting the stay behavior, adopting a track data collection method based on mobile phone base station positioning, applying track interpolation to complement the missing points in the track, adopting Kalman filtering to realize track noise reduction, and obtaining the track data of an observed object;
step S1.2: judging the stay behavior, acquiring the position of an observed object, taking the range of 400-500 m of a square circle as an observation radius, and staying for more than 5 minutes in the observation radius to be regarded as one stay; the number of lingers was added to 1 by the radius of observation at the entrance and exit.
Preferably, a two-dimensional matrix F [ K ] [ I ] is adopted for mathematical description of the single-point lingering behavior in the step S2, wherein K represents the time number, and I represents the time period number; the time-frequency graph expressed visually is a three-dimensional curved surface or a two-dimensional grid; the three-dimensional curved surface is a time-period-frequency three-dimensional curved surface, and different coordinate heights describe the frequency under the time resolution; the two-dimensional grid is a time-epoch two-dimensional grid, with different grid colors describing the frequency at that time resolution.
Preferably, the mathematical description of the single-object multi-point space lingering behavior in step S2 is represented by a three-dimensional tensor F [ N ] [ K ] [ I ], where N represents the number of spatial observation position points, K represents the number of time, and I represents the number of time segments; and performing visual expression by adopting a super grid, wherein one node in the super grid is a time-frequency graph two-dimensional grid of the sojourn behavior of the corresponding point, the two-dimensional grid is a time-period two-dimensional grid, and different grid colors describe the frequency under the time resolution.
Preferably, the mathematical description of the multi-object multi-point space lingering behavior in step S2 is expressed as a four-dimensional tensor F [ M ] [ N ] [ K ] [ I ], wherein M represents the number of observed objects, M ≧ 2, N represents the number of spatial observed position points, K represents the number of time periods, and I represents the number of time periods; and adopting a super-grid visual expression, wherein one node in the super-grid is a time-frequency graph two-dimensional grid of the sojourn behavior of the corresponding point, the two-dimensional grid is a time-period two-dimensional grid, and different grid colors describe the frequency under the time resolution.
Preferably, in step S3, a spatial behavior similarity measurement is performed to measure the similarity of the spatial behavior semantic patterns between two objects, so as to provide a basis for individual identification and team partnership discovery; including a location-independent similarity measure, a location-weakly-correlated similarity measure, and a location-strongly-correlated similarity measure:
the location-independent similarity measure is described as:
the similarity measure for a weak correlation of locations is described as:
the similarity measure for a strong correlation of locations is described as:
here, R (·) calculates matrix correlation coefficients, Fa, Fb are behavior pattern time-frequency graphs of objects a, b, respectively, La, Lb are observed location points of objects a, b, respectively, N is the number of location points involved in the calculation, the symbol "≈" represents a geospatial scene similarity operator, and the symbol "andgate" is a set intersection operator.
Preferably, in step S3, the frequent pattern mining is single-point time-domain correlation mining, the time-frequency graphs of all objects appearing at the observation position are overlapped, and then divided into several time intervals, the density distribution in each time period is obtained, if the maximum density distribution exceeds the investigation threshold, the frequent pattern mining is considered, and the process is formally described as:
here, Fi is a time-frequency diagram of the object i, N is the number of objects to be observed, Ct is a sampling operator for obtaining an accumulated frequency of a certain area in the time-frequency diagram, and Δ t is a time interval for investigation.
Preferably, the frequent pattern mining is multipoint frequent pattern mining in step S3, and if the stay behavior of the same object occurs in a plurality of occasions with the same functional attribute in a short period, the frequent pattern mining is determined as the frequent pattern, and the formalization of the process is described as follows:
here, Fi is a time-frequency diagram of a place where a certain object appears, and N is the number of sites.
Compared with the prior art, the invention has the beneficial effects that: the spatial behavior pattern map expression mechanism and the measurement calculation method provided by the invention provide a basis for finding spatial semantic information. Because the regularity of the spatial behavior pattern statistical distribution conforms to the internal performance of the spatial behaviors of different professional groups, the method can indirectly understand the activity purpose and behavior motivation of a traveler, particularly distinctive abnormal dangerous behaviors, and reveal the hidden relation hidden in the behavior pattern and valuable for social security prevention and control, so that the social security precaution practical application based on the spatial movement big data abnormal behavior monitoring becomes possible.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
Detailed Description
In order to facilitate the understanding and implementation of the present invention for those of ordinary skill in the art, the present invention is further described in detail with reference to the accompanying drawings and examples, it is to be understood that the embodiments described herein are merely illustrative and explanatory of the present invention and are not restrictive thereof.
Referring to fig. 1, the method for identifying a semantic pattern of a spatial motion behavior according to an embodiment of the present invention is characterized by including the following steps:
step S1, collecting and judging the sojourn behavior based on space positioning;
step S2, establishing mathematical description and visual expression for the stay behavior, and establishing a spatial behavior semantic mode map;
and step S3, performing space behavior similarity measurement or time-space frequent pattern mining according to the space behavior semantic pattern map.
Specifically, the implementation process of step S1 includes the following sub-steps:
s1.1, collecting the stay behavior, adopting a track data collection method based on mobile phone base station positioning, applying track interpolation to complement the missing points in the track, adopting Kalman filtering to realize track noise reduction, and obtaining the track data of an observed object;
step S1.2: judging the stay behavior, acquiring the position of an observed object, taking the range of 400-500 m of a square circle as an observation radius, and staying for more than 5 minutes in the observation radius to be regarded as one stay; the number of lingers was added to 1 by the radius of observation at the entrance and exit.
Specifically, a two-dimensional matrix F [ K ] [ I ] is adopted for mathematical description of the single-point stay behavior in the step S2, wherein K represents the time number, and I represents the time segment number; the time-frequency graph expressed visually is a three-dimensional curved surface or a two-dimensional grid; the three-dimensional curved surface is a time-period-frequency three-dimensional curved surface, and different coordinate heights describe the frequency under the time resolution; the two-dimensional grid is a time-epoch two-dimensional grid, with different grid colors describing the frequency at that time resolution.
Specifically, the mathematical description of the single-object multi-point space lingering behavior in the step S2 is represented by a three-dimensional tensor F [ N ] [ K ] [ I ], where N represents the number of spatial observation position points, K represents the number of time, and I represents the number of time segments; and performing visual expression by adopting a super grid, wherein one node in the super grid is a time-frequency graph two-dimensional grid of the sojourn behavior of the corresponding point, the two-dimensional grid is a time-period two-dimensional grid, and different grid colors describe the frequency under the time resolution.
Specifically, the mathematical description of the multi-object multi-point space lingering behavior in the step S2 is expressed as a four-dimensional tensor F [ M ] [ N ] [ K ] [ I ], where M represents the number of observed objects, M is greater than or equal to 2, N represents the number of spatial observed position points, K represents the number of time, and I represents the number of time segments; and adopting a super-grid visual expression, wherein one node in the super-grid is a time-frequency graph two-dimensional grid of the sojourn behavior of the corresponding point, the two-dimensional grid is a time-period two-dimensional grid, and different grid colors describe the frequency under the time resolution.
Specifically, in step S3, a spatial behavior similarity measure is performed to measure the similarity of the spatial behavior semantic patterns between two objects, so as to provide a basis for individual identification and team partnership discovery; including a location-independent similarity measure, a location-weakly-correlated similarity measure, and a location-strongly-correlated similarity measure:
the location-independent similarity measure is described as:
the similarity measure for a weak correlation of locations is described as:
the similarity measure for a strong correlation of locations is described as:
here, R (·) calculates matrix correlation coefficients, Fa, Fb are behavior pattern time-frequency graphs of objects a, b, respectively, La, Lb are observed location points of objects a, b, respectively, N is the number of location points involved in the calculation, the symbol "≈" represents a geospatial scene similarity operator, and the symbol "andgate" is a set intersection operator.
Specifically, in step S3, the frequent pattern mining is single-point time-domain correlation mining, the time-frequency graphs of all objects appearing at the observation position are superimposed, and then divided into a plurality of time intervals, and the density distribution in each time period is obtained, if the maximum density distribution exceeds the investigation threshold, the frequent pattern mining is regarded as the frequent pattern mining, and the formalized description of the process is as follows:
here, Fi is a time-frequency diagram of the object i, N is the number of objects to be observed, Ct is a sampling operator for obtaining an accumulated frequency of a certain area in the time-frequency diagram, and Δ t is a time interval for investigation.
Specifically, in step S3, the frequent pattern mining is multipoint frequent pattern mining, and if a stay behavior of the same object occurs in a plurality of occasions with the same functional attribute in a short period, it is determined as a frequent pattern, and the formalization of the process is described as follows:
here, Fi is a time-frequency diagram of a place where a certain object appears, and N is the number of sites.
It should be understood that parts of the specification not set forth in detail are well within the prior art.
It should be understood that the above description of the preferred embodiments is given for clarity and not for any purpose of limitation, and that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (4)
1. A method for identifying semantic patterns of spatial motion behaviors is characterized by comprising the following steps:
step S1, collecting and judging the stay behavior based on the space positioning data;
step S1.1: the method comprises the steps of carrying out stay behavior acquisition, namely, adopting a track data acquisition method based on mobile phone base station positioning, applying track interpolation to complement missing points in a track, adopting Kalman filtering to realize track noise reduction, and acquiring continuous moving track data of an observed object;
step S1.2: judging the stay behavior, acquiring the position of an observed object, taking the range of 400-500 m of a square circle as an observation radius, and staying for more than 5 minutes in the observation radius to be regarded as one stay; the radius of one observation is entered and exited, and the number of lingering times is added by 1, so as to accumulate;
step S2, establishing formal description and visual expression for the sojourn behavior to form a spatial behavior semantic mode map;
for ease of description, spatial linger behavior is divided into three case semantic considerations: the spatial behavior semantic pattern maps of the single-point lingering behavior, the single-object multi-point lingering behavior and the multi-object multi-point lingering behavior are respectively described in the following modes:
the mathematical description of the single-point stay behavior adopts a two-dimensional matrix F [ K ] [ I ], wherein K represents the time number, and I represents the time segment number; the time-frequency graph expressed visually is a three-dimensional curved surface or a two-dimensional grid; the three-dimensional curved surface is a time-period-frequency three-dimensional curved surface, and different coordinate heights describe the frequency under the time resolution; the two-dimensional grid is a time-period two-dimensional grid, and different grid colors describe the frequency under the time resolution;
the mathematical description of the sojourn behavior of the single-object multi-point space is expressed by a three-dimensional tensor F [ N ] [ K ] [ I ], wherein N represents the number of the observed position points of the space, K represents the number of time, and I represents the number of time segments; carrying out visual expression by adopting a super grid, wherein one node in the super grid is a time-frequency graph two-dimensional grid of the stay behavior of the corresponding point, the two-dimensional grid is a time-period two-dimensional grid, and different grid colors describe the frequency under the time resolution;
the mathematical description of the multi-object multi-point space lingering behavior is expressed by a four-dimensional tensor F [ M ] [ N ] [ K ] [ I ], wherein M represents the number of observed objects, M is larger than or equal to 2, N represents the number of space observation position points, K represents the number of time, and I represents the number of time segments; adopting a super-grid visual expression, wherein one node in the super-grid is a time-frequency graph two-dimensional grid of the sojourn behavior of the corresponding point, the two-dimensional grid is a time-period two-dimensional grid, and different grid colors describe the frequency under the time resolution;
and step S3, performing space behavior similarity measurement or time-space frequent pattern mining according to the space behavior semantic pattern map.
2. The method for identifying spatial movement behavior semantic patterns according to claim 1, wherein a spatial behavior similarity measurement is performed in step S3 to measure the similarity of spatial behavior semantic patterns between two objects, so as to provide a basis for individual identification and team partnership discovery; including a location-independent similarity measure, a location-weakly-correlated similarity measure, and a location-strongly-correlated similarity measure:
the location-independent similarity measure is described as:
the similarity measure for a weak correlation of locations is described as:
the similarity measure for a strong correlation of locations is described as:
here, R (·) calculates matrix correlation coefficients, Fa, Fb are behavior pattern time-frequency graphs of objects a, b, respectively, La, Lb are observed location points of objects a, b, respectively, N is the number of location points involved in the calculation, the symbol "≈" represents a geospatial scene similarity operator, and the symbol "andgate" is a set intersection operator.
3. The method for identifying semantic patterns of spatial motion behaviors as claimed in claim 1, wherein in step S3, frequent pattern mining is single-point time-domain correlation mining, time-frequency graphs of all objects appearing at an observation position are overlapped, and then divided into a plurality of time intervals, and a density distribution in each time period is obtained, and if a maximum density distribution exceeds a threshold of investigation, the mode is considered as a frequent pattern, and the process is formally described as:
here, Fi is a time-frequency diagram of the object i, N is the number of objects to be observed, Ct is a sampling operator for obtaining an accumulated frequency of a certain area in the time-frequency diagram, and Δ t is a time interval for investigation.
4. The method for identifying semantic patterns of spatial movement behaviors as claimed in claim 1, wherein the frequent pattern mining is multi-point frequent pattern mining in step S3, and if the stay behavior of the same object occurs in a plurality of occasions with the same functional attribute in a short period, the frequent pattern mining is determined as a frequent pattern, and the process is formally described as follows:
here, Fi is a time-frequency diagram of a place where a certain object appears, and N is the number of sites.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711466898.1A CN108052924B (en) | 2017-12-28 | 2017-12-28 | Identification method of spatial motion behavior semantic mode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711466898.1A CN108052924B (en) | 2017-12-28 | 2017-12-28 | Identification method of spatial motion behavior semantic mode |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108052924A CN108052924A (en) | 2018-05-18 |
| CN108052924B true CN108052924B (en) | 2020-10-27 |
Family
ID=62128946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711466898.1A Active CN108052924B (en) | 2017-12-28 | 2017-12-28 | Identification method of spatial motion behavior semantic mode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108052924B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109542951A (en) * | 2018-11-22 | 2019-03-29 | 中国科学院遥感与数字地球研究所 | A kind of the space-time representativeness assessment system and method for remote sensing big data |
| CN110837582B (en) * | 2019-11-28 | 2022-06-03 | 重庆紫光华山智安科技有限公司 | Data association method and device, electronic equipment and computer-readable storage medium |
| CN113051340B (en) * | 2021-03-30 | 2023-02-03 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | End-to-end sea-air activity target data rule real-time mining method |
| CN114492420B (en) * | 2022-04-02 | 2022-07-29 | 北京中科闻歌科技股份有限公司 | Text classification method, device and equipment and computer readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593361A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement space-time trajectory analysis method in sense network environment |
| CN104731795A (en) * | 2013-12-19 | 2015-06-24 | 日本电气株式会社 | Mining apparatus and method of activity patterns of individuals |
| CN105117424A (en) * | 2015-07-31 | 2015-12-02 | 中国科学院软件研究所 | Dwell-time-based moving object semantic behavior pattern mining method |
| CN105654508A (en) * | 2015-12-24 | 2016-06-08 | 武汉大学 | Monitoring video moving target tracking method based on self-adaptive background segmentation and system thereof |
| CN105678247A (en) * | 2015-12-30 | 2016-06-15 | 武汉大学 | Abnormal behavior early warning method and system for hovering event space-time big data analysis |
| CN106383868A (en) * | 2016-09-05 | 2017-02-08 | 电子科技大学 | Road network-based spatio-temporal trajectory clustering method |
| CN106778876A (en) * | 2016-12-21 | 2017-05-31 | 广州杰赛科技股份有限公司 | User classification method and system based on mobile subscriber track similitude |
| CN107045519A (en) * | 2016-10-31 | 2017-08-15 | 浙江大学 | A kind of visualization system of analysis crowd movement law |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4607797B2 (en) * | 2006-03-06 | 2011-01-05 | 株式会社東芝 | Behavior discrimination device, method and program |
| US20110205359A1 (en) * | 2010-02-19 | 2011-08-25 | Panasonic Corporation | Video surveillance system |
-
2017
- 2017-12-28 CN CN201711466898.1A patent/CN108052924B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593361A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement space-time trajectory analysis method in sense network environment |
| CN104731795A (en) * | 2013-12-19 | 2015-06-24 | 日本电气株式会社 | Mining apparatus and method of activity patterns of individuals |
| CN105117424A (en) * | 2015-07-31 | 2015-12-02 | 中国科学院软件研究所 | Dwell-time-based moving object semantic behavior pattern mining method |
| CN105654508A (en) * | 2015-12-24 | 2016-06-08 | 武汉大学 | Monitoring video moving target tracking method based on self-adaptive background segmentation and system thereof |
| CN105678247A (en) * | 2015-12-30 | 2016-06-15 | 武汉大学 | Abnormal behavior early warning method and system for hovering event space-time big data analysis |
| CN106383868A (en) * | 2016-09-05 | 2017-02-08 | 电子科技大学 | Road network-based spatio-temporal trajectory clustering method |
| CN107045519A (en) * | 2016-10-31 | 2017-08-15 | 浙江大学 | A kind of visualization system of analysis crowd movement law |
| CN106778876A (en) * | 2016-12-21 | 2017-05-31 | 广州杰赛科技股份有限公司 | User classification method and system based on mobile subscriber track similitude |
Non-Patent Citations (5)
| Title |
|---|
| A Segment-Based Trajectory Similarity Measure in the Urban Transportation Systems;Yingchi Mao 等;《www.preprints.org》;20170306;1-16 * |
| DoSTra: Discovering Common Behaviors of Objects Using the Duration of Staying on Each Location of Trajectories;Limin Guo 等;《Trajectory-Based Behavior Analytics: Papers from the 2015 AAAI Workshop》;20151231;9-17 * |
| 城市海量手机用户停留时空分异分析;徐金垒 等;《地球信息科学》;20141224;第17卷(第2期);197-205 * |
| 基于用户移动数据的可视化用户行为分析;陈鹏;《中国优秀硕士学位论文全文数据库 信息科技辑》;20170215;正文第2.1.3节，第3.2.1节，第5.6节，图5-17 * |
| 面向智能监控摄像头的监控视频大数据分析处理;邵振峰 等;《电子与信息学报》;20170208;第39卷(第5期);1116-1122 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108052924A (en) | 2018-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108052924B (en) | Identification method of spatial motion behavior semantic mode | |
| Kjærgaard et al. | Mobile sensing of pedestrian flocks in indoor environments using wifi signals | |
| Sharma et al. | A review on technological advancements in crowd management | |
| EP2219379B1 (en) | Social network construction based on data association | |
| Wirz et al. | Inferring crowd conditions from pedestrians' location traces for real-time crowd monitoring during city-scale mass gatherings | |
| Lin et al. | Real-time monitoring system for workers' behaviour analysis on a large-dam construction site | |
| Yu et al. | Trajectory outlier detection approach based on common slices sub-sequence | |
| Cao et al. | Automatic user identification method across heterogeneous mobility data sources | |
| CN109543312B (en) | Space-time investigation analysis method and system | |
| CN108170793A (en) | Dwell point analysis method and its system based on vehicle semanteme track data | |
| CN106792523B (en) | A kind of anomaly detection method based on extensive WiFi activity trajectory | |
| Griffiths et al. | UK-based terrorists' antecedent behavior: A spatial and temporal analysis | |
| WO2020114138A1 (en) | Information associated analysis method and apparatus, and storage medium and electronic device | |
| CN102224526A (en) | A system and a method for identifying human behavioural intention based on an effective motion analysis | |
| CN111935450A (en) | Intelligent suspect tracking method and system and computer readable storage medium | |
| CN112002431A (en) | Method and system for discovering close contacts of specific user by utilizing electromagnetic signals | |
| CN110716925B (en) | Cross-border behavior recognition method based on track analysis | |
| CN114706988A (en) | Monitoring and early warning method and device based on knowledge graph | |
| Shad et al. | Cell oscillation resolution in mobility profile building | |
| Andrienko et al. | Towards privacy-preserving semantic mobility analysis | |
| Ellersiek et al. | Using Bluetooth to track mobility patterns: depicting its potential based on various case studies | |
| Su et al. | A new approach for social group detection based on spatio-temporal interpersonal distance measurement | |
| Chamikara et al. | SL-SecureNet: intelligent policing using data mining techniques | |
| Chen et al. | Trajectory clustering for people's movement pattern based on Crowd souring data | |
| Zhao et al. | Discovering individual life style from anonymized wifi scan lists on smartphones |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |