CN109522860B - Internet of things application analysis system and method based on multiple tracks - Google Patents
Internet of things application analysis system and method based on multiple tracks Download PDFInfo
- Publication number
- CN109522860B CN109522860B CN201811422106.5A CN201811422106A CN109522860B CN 109522860 B CN109522860 B CN 109522860B CN 201811422106 A CN201811422106 A CN 201811422106A CN 109522860 B CN109522860 B CN 109522860B
- Authority
- CN
- China
- Prior art keywords
- data
- portrait
- module
- mac address
- identity
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Landscapes
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an Internet of things application analysis system and method based on multiple tracks, and relates to WIFI acquisition and portrait identity acquisition technologies. The system is as follows: the MAC address acquisition module (100), the MAC address filtering module (101) and the data preprocessing module (300) are sequentially interacted; the portrait identity acquisition module (200), the portrait comparison collision module (201) and the data preprocessing module (300) are sequentially interacted; a data pre-processing module (300); the data analysis center module (400) and the data association center module (500) interact in sequence. The invention has the following advantages and positive effects: the method has the advantages that the mutual correlation between the MAC address and the portrait data can be realized; the data has reliability, and the data is often precipitated for a long time and collided with a result set; the practicability is high; expandability, and can effectively protect the existing investment.
Description
Technical Field
The invention relates to a WIFI acquisition and portrait identity acquisition technology, in particular to a multi-track-based Internet of things application analysis system and a method thereof, namely a data mining system and a method thereof for confirming the corresponding relation between an MAC address and a portrait video identity by utilizing big data analysis to perform large-scale data operation.
Background
With the rapid development of communication technology and mobile internet technology, a network application mode is changed from a single internet access mode to rich and diverse business applications, and the life style of any person cannot be completely separated from the internet, so that the most basic clothes and residence, even work and study and the like are closely related to the internet. China, as a large number of net citizens, faces a complicated Internet world, and is not like being capable of clearly seeing submerged reef dangerous beaches and flying sand and walking stones in reality. With the rapid development of the wireless local area network technology, the coverage range of the WiFi is wide, and the access threshold is low, so that the WiFi becomes the preferred internet access mode. During the internet surfing process, a large amount of user information such as terminal information, location information, communication information, online shopping information, user internet surfing track information, user authentication information and the like can be generated. In the architecture of TCP/IP, MAC addresses play a very important role. In communication, the host network card identified by the MAC address serves as the hardware address of the host identity. After each network card is produced, a globally unique number is used for identifying the network card and cannot be repeated, and the number is an MAC address, namely a physical address of the network card.
However, the MAC address as the virtual identity information of the network cannot be correlated with the real data according to the MAC address, and the virtual data can be effectively acquired through a WIFI acquisition system or the like, but the problem that the virtual identity cannot be correlated with the real data is faced. Therefore, the traditional WIFI acquisition system has certain limitation and needs to be improved.
The portrait acquisition system can compare and collide real-time acquired data with real world identity information, convert real-time video data into real identity data, perform collision analysis with acquired virtual identity MAC, and correlate virtual identity with real identity. The portrait identity acquisition system has the defects of small acquisition radius, directional acquisition, small deployment range and the like, and has larger acquisition dead angles. The two are combined with each other, meanwhile, a big data mining technology is utilized, after multiple data comparison and precipitation, virtual MAC data are converted into real data, the advantages of the two can be simultaneously played, a plurality of identity information in a virtual network can be obtained, the characteristics of comprehensive WIFI control and deployment, wide coverage range, a plurality of collected virtual identity information and the like are played, real character information can be obtained by a portrait identity system, and the problem of data isolated island can be effectively solved by combining the two.
Disclosure of Invention
The invention aims to overcome the defects of the existing data WIFI acquisition system and provides a framework and an implementation method of an Internet of things application analysis system based on multiple tracks. The invention is used for realizing the association between the physical address of the mobile phone and the real identity of the figure acquired by the figure identity system, and the physical address of the mobile phone in the virtual network and the real identity information of the figure in the real world are mutually associated and analyzed, thereby avoiding information isolated island.
The technical scheme for realizing the aim of the invention is as follows:
the method mainly aims at the correlation analysis between the mobile phone MAC address in WIFI acquisition and the portrait identity video data in the real environment, and realizes data correlation by using a big data mining technology and depending on a unique design algorithm. By applying a big data analysis mining technology, portrait identity data collected around when the MAC address is collected is converted into real identity data in the real world through comparative analysis, the portrait identities around when the MAC address appears every time are recorded, systematic scoring is carried out by using the MAC address which appears repeatedly for many times and the portrait identity data records, the more the appearance times are, the higher the score is, and the score is stored as a highly suspicious data set after the threshold value is reached. The invention relates to an analysis and processing system for a data center of a cluster server based on WIFI mass front-end collected big data and wireless transmission of a security protocol. The development of the internet is great nowadays, and aiming at the problem of large data volume, it becomes an important subject to collect and uniformly analyze large data. The big data processing is based on the cluster server, the decoupling of the service and the data is realized in the aspect of service support, and the consistency and the agility of the service and the flexibility of a system architecture are ensured. Through the service encapsulation of resources such as data, computing power, analysis models and the like, the whole network interconnection is realized, and the sharing of services and data resources is also realized, thereby providing powerful guarantee for service linkage, service expansion and service innovation. The method is characterized in that data are designed by adopting a plurality of database mixed storage strategies on the resource center design, a distributed data storage scheme based on hbase is adopted for mass data, mongodb based on a memory database is adopted for extracted resource data to store TB-level data, data can be quickly retrieved, and an oracle-based relational database is adopted for system management data and temporary data, so that a system service flow can be better designed. The data center computing architecture adopts hadoop/hbase distributed mass data storage, has transverse expansibility and data reliability, can process PB-level data, simultaneously adopts spark technology with large data analysis real-time computing capacity and multi-iteration data operation, can off-line batch process computing tasks by applying the map/reduce technology of hadoop, processes data based on storm/spark streaming model in the data stream processing process, leads the processing modules to be more loosely coupled, can realize dynamic configuration and optimization of the workflow, realizes comprehensive processing of large-scale and complex data by the data resource center based on cloud platform design, and provides effective technical support for upper analysis mining and prediction application.
Internet of things application analysis system (system for short) based on multiple tracks
The system comprises an MAC address acquisition module, an MAC address filtering module, a portrait identity acquisition module, a portrait comparison collision module and a data preprocessing module; the data analysis center module and the data association center module;
the interaction relationship is as follows:
the MAC address acquisition module, the MAC address filtering module and the data preprocessing module are sequentially interacted to realize the acquisition of the MAC address and the filtering of the real MAC address;
the portrait identity acquisition module, the portrait comparison collision module and the data preprocessing module are sequentially interacted to realize the acquisition of the portrait identity data and the comparison of the portrait data;
the data preprocessing module, the data analysis center and the data association center are sequentially interacted to realize the mutual association of the MAC address data and the portrait identity data in the time region.
Second, an internet of things application analysis method (method for short) based on multiple tracks
Firstly, an MAC address acquisition module acquires a wireless WIFI physical address of a mobile phone, and realizes data capture and protocol analysis on air interface WIFI data according to a WIFI air interface protocol;
the MAC address filtering module performs virtual MAC address filtering and MAC address CRC (cyclic redundancy check) and filtering on the MAC address data acquired by the MAC address acquisition module to realize data cleaning, and the cleaned data is transmitted to the data preprocessing module by adopting a TCP (transmission control protocol);
the portrait identity acquisition module acquires portrait video data, completes data decomposition according to a set data format, and transmits the decomposed structured data to the portrait comparison collision module (201) for real identity collision;
the portrait comparison collision module collides the video portrait data acquired by the actual network with the real portrait database data, and sends the collision result to the data preprocessing module in a TCP protocol structured data format;
the data preprocessing module (300) receives the MAC address data transmitted by the MAC address filtering module and the portrait comparison collision module (201) and the structural data after the portrait comparison, realizes the cleaning and warehousing storage of data validity, and is used for a subsequent data analysis center to perform big data collision analysis and mining;
sixthly, the data analysis center searches for MAC address records and portrait identity records of X minutes before and after a certain time condition in each association area according to the matching of the MAC addresses and the portrait identity tracks which are simultaneously acquired in a certain range, excavates portrait identity information which possibly corresponds to a certain MAC address, counts the total times of appearance of the MAC addresses and the portrait identities in all the association areas, sorts the MAC addresses and the portrait identities in a descending order, the more the appearance times are, the higher the similarity is, excavates and analyzes data which are similar for many times through the system, and comprehensively examines, assesses and scores the similarity after a result set is accumulated to a threshold value;
and the data association center periodically stores the research and judgment results of the data analysis center, and stores the data records reaching the threshold value into a result set to be stored in the association database for subsequent system display and analysis.
The invention has the following advantages and positive effects:
the method has the advantages that the mutual correlation between the MAC address and the portrait data can be realized;
the data has reliability and collides with the result set after long-time data precipitation;
the practicability is high;
expandability, and can effectively protect the existing investment.
Drawings
FIG. 1 is a block diagram of the architecture of the present system;
wherein:
100-MAC address acquisition module;
101-MAC address filtering module;
200-portrait identity acquisition module;
201-portrait comparison collision module;
300-data preprocessing module;
400-data analysis center module;
500-data association center module;
the specific implementation mode is as follows:
a, system
1. General of
As shown in fig. 1, the system includes a MAC address acquisition module 100, a MAC address filtering module 101, a portrait identity acquisition module 200, a portrait comparison and collision module 201, and a data preprocessing module 300; a data analysis center module 400 and a data association center module 500;
the interaction relationship is as follows:
the MAC address acquisition module 100, the MAC address filtering module 101 and the data preprocessing module 300 interact in sequence to realize the acquisition of MAC addresses and the filtering of real MAC addresses;
the portrait identity acquisition module 200, the portrait comparison collision module 201 and the data preprocessing module 300 interact in sequence to realize the acquisition of portrait identity data and the comparison of portrait data;
a data preprocessing module 300; the data analysis center module 400 and the data association center module 500 interact with each other in sequence to realize the association between the MAC address data and the portrait identity data in the time domain.
2. Functional module
1) The MAC address acquisition module 100 is responsible for acquiring WIFI data in an air interface, that is, acquiring a physical MAC address of a mobile phone;
2) the MAC address filtering module 101 is responsible for cleaning the acquired MAC address and sending the data to the data preprocessing module 300 in a TCP manner;
3) the portrait identity acquisition module 200 is responsible for acquiring real-time portrait data;
4) the portrait comparing and colliding module 201 is responsible for completing the comparison and collision between the portrait and the data of the portrait database, converting the portrait data into a real identity, and sending the converted real portrait identity information to the data preprocessing module 300 in a structured format;
5) the data preprocessing module 300 is responsible for completing the storage of the MAC address data and the portrait structured data;
6) the data analysis center 400 searches for the MAC address records and the portrait identity records of X minutes before and after each relevant area under a certain time condition according to the matching of the MAC addresses and the portrait identity tracks which are simultaneously acquired in a certain range, and excavates portrait identity information possibly corresponding to a certain MAC address; and counting the total times of the occurrence of the MAC addresses and the portrait identities in all the associated areas, and sequencing the MAC addresses and the portrait identities in a descending order, wherein the more the pairs of the occurrence times are, the higher the similarity is. Through similar data mining and analysis for many times, the result set is accumulated to a threshold value and then similarity comprehensive research, judgment and scoring are carried out;
7) the data association center 500 stores the research and judgment results of the data analysis center 400 periodically, and stores the data records reaching the threshold value into a result set to be stored in the association database for the subsequent system to display and analyze.
Second, method
1. Step four
The data analysis center 400 searches for real portrait identity information according to a specific MAC address in a selected time period, including the following work flow:
A. searching the track of the MAC address by adopting a mode of adding the MAC address into a time period aiming at the MAC address, finding a corresponding association area/time, searching portrait data records of X minutes before and after each association area device, summarizing the number of times of portrait identities of all devices in the area, and sorting after accumulating according to a descending order;
B. after the following sorting results are obtained, the system carries out comprehensive evaluation on the similarity according to the occurrence times;
the figure appears for the 1 st time, and the similarity is 90 percent;
the figure appears for the 2 nd time, and the similarity is 85 percent;
the 3 rd appearance of the portrait, the similarity is 70%;
the figure appears for the 4 th time, and the similarity is 60 percent;
......
the human figure appears at the mth time, and the similarity is 0 percent;
m is a natural number, and m is a natural number,
the similarity is arranged in descending order, and the higher the value is, the more likely it is real portrait data.
Claims (3)
1. An application analysis system of the Internet of things based on multiple tracks,
the system comprises an MAC address acquisition module (100), an MAC address filtering module (101), a portrait identity acquisition module (200), a portrait comparison collision module (201) and a data preprocessing module (300); a data analysis center module (400) and a data association center module (500);
the interaction relationship is as follows:
the MAC address acquisition module (100), the MAC address filtering module (101) and the data preprocessing module (300) are sequentially interacted to realize the acquisition of MAC addresses and the filtering of real MAC addresses;
the portrait identity acquisition module (200), the portrait comparison collision module (201) and the data preprocessing module (300) are sequentially interacted to realize the acquisition of portrait identity data and the comparison of portrait data;
the data preprocessing module (300), the data analysis center (400) and the data association center (500) are sequentially interacted to realize the mutual association of the MAC address data and the portrait identity data in the time region;
the method is characterized in that:
the MAC address acquisition module (100) is responsible for acquiring WIFI data in an air interface, namely acquiring a physical MAC address of the mobile phone;
the MAC address filtering module (101) is responsible for cleaning the collected MAC addresses and sending the data to the data preprocessing module (300) in a TCP mode;
the portrait identity acquisition module (200) is responsible for acquiring real-time portrait data;
the portrait comparing and colliding module (201) is responsible for completing the comparison and collision of the portrait with the data of the portrait database, converting the portrait data into a real identity, and sending the converted real portrait identity information to the data preprocessing module (300) in a structured format;
the data preprocessing module (300) is responsible for finishing the storage of the MAC address data and the portrait structured data;
the data analysis center (400) searches MAC address records and portrait identity records of X minutes before and after a certain time condition in each associated area according to the matching of the MAC addresses and the portrait identity tracks which are simultaneously acquired in a certain range, and excavates portrait identity information possibly corresponding to a certain MAC address; counting the total occurrence times of the MAC addresses and the portrait identities in all the associated areas, sequencing the MAC addresses and the portrait identities in a descending order, wherein the more the MAC addresses and the portrait identities occur in pairs, the higher the similarity is, and accumulating a result set to a threshold value through multiple similar data mining and analysis of a system to perform comprehensive similarity research, judgment and scoring;
the data association center (500) stores the research and judgment results of the data analysis center (400) periodically, and stores the data records reaching the threshold value into a result set to be stored in the association database for subsequent system display and analysis.
2. The application analysis method based on the system of claim 1, characterized in that:
firstly, an MAC address acquisition module (100) acquires a wireless WIFI physical address of a mobile phone, and captures data and analyzes a protocol of air interface WIFI data according to a WIFI air interface protocol;
the MAC address filtering module (101) performs virtual MAC address filtering and MAC address CRC (cyclic redundancy check) and filtering on the MAC address data acquired by the MAC address acquisition module (100) to realize data cleaning, and transmits the cleaned data to the data preprocessing module (300) by adopting a TCP (transmission control protocol);
acquiring portrait video data by a portrait identity acquisition module (200), decomposing the data according to a set data format, and transmitting the decomposed structured data to a portrait comparison collision module (201) for real identity collision;
a portrait comparison collision module (201) collides the video portrait data acquired by the actual network with the real portrait database data, and sends the collision result to a data preprocessing module (300) in a TCP protocol structured data format;
the data preprocessing module (300) receives the MAC address data transmitted by the MAC address filtering module (101) and the portrait comparison collision module (201) and the structural data after the portrait comparison, realizes the cleaning and warehousing storage of data validity, and provides the follow-up data analysis center module (400) for big data collision analysis and mining;
sixthly, the data analysis center (400) searches MAC address records and portrait identity records of X minutes before and after a certain time condition in each association area according to the matching of the MAC addresses and the portrait identity tracks which are simultaneously acquired in a certain range, excavates portrait identity information which possibly corresponds to a certain MAC address, counts the total times of appearance of the MAC addresses and the portrait identities in all the association areas, sorts the MAC addresses and the portrait identities in a descending order, the more the times of appearance are, the higher the similarity is, excavates and analyzes data which are similar for many times through the system, and carries out comprehensive similarity study, judgment and scoring after a result set is accumulated to a threshold value;
and the data association center (500) stores the judgment results of the data analysis center (400) periodically, and stores the data records reaching the threshold value into a result set to be stored in an association database for subsequent system display and analysis.
3. The application analysis method of claim 2, characterized by the steps of (iv):
A. searching the track of the MAC address by adopting a mode of adding the MAC address into a time period aiming at the MAC address, finding a corresponding association area/time, searching portrait data records of X minutes before and after each association area device, summarizing the number of times of portrait identities of all devices in the area, and sorting after accumulating according to a descending order;
B. after the following sorting results are obtained, the system carries out comprehensive evaluation on the similarity according to the occurrence times;
the figure appears for the 1 st time, and the similarity is 90 percent;
the figure appears for the 2 nd time, and the similarity is 85 percent;
the 3 rd appearance of the portrait, the similarity is 70%;
the figure appears for the 4 th time, and the similarity is 60 percent;
......
the human figure appears at the mth time, and the similarity is 0 percent;
m is a natural number, and m is a natural number,
the similarity is arranged in descending order, and the higher the value is, the more likely it is real portrait data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811422106.5A CN109522860B (en) | 2018-11-27 | 2018-11-27 | Internet of things application analysis system and method based on multiple tracks |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811422106.5A CN109522860B (en) | 2018-11-27 | 2018-11-27 | Internet of things application analysis system and method based on multiple tracks |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109522860A CN109522860A (en) | 2019-03-26 |
CN109522860B true CN109522860B (en) | 2021-07-13 |
Family
ID=65794579
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811422106.5A Active CN109522860B (en) | 2018-11-27 | 2018-11-27 | Internet of things application analysis system and method based on multiple tracks |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109522860B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110727671A (en) * | 2019-10-11 | 2020-01-24 | 北京明略软件系统有限公司 | Case data processing method and device |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103886658A (en) * | 2014-01-28 | 2014-06-25 | 北京中科虹霸科技有限公司 | Multi-modal biometric recognition-based distributed internet-of-things lock equipment and unlocking method thereof |
CN105790955A (en) * | 2016-04-06 | 2016-07-20 | 深圳市博康智能信息技术有限公司 | Method and system for associating MAC addresses with face information |
CN106649298A (en) * | 2015-07-22 | 2017-05-10 | 中国科学院微电子研究所 | Cross-domain association establishment method and system based on Internet of things |
CN106874347A (en) * | 2016-12-26 | 2017-06-20 | 深圳市深网视界科技有限公司 | A kind of method and system for matching characteristics of human body and MAC Address |
CN107590439A (en) * | 2017-08-18 | 2018-01-16 | 湖南文理学院 | Target person identification method for tracing and device based on monitor video |
CN107623754A (en) * | 2017-09-28 | 2018-01-23 | 武汉虹旭信息技术有限责任公司 | WiFi acquisition systems and its method based on true and false MAC identifications |
CN108280339A (en) * | 2018-01-16 | 2018-07-13 | 合肥工业大学 | A kind of passenger's personal identification method based on Multi-source Information Fusion |
US10058290B1 (en) * | 2013-06-21 | 2018-08-28 | Fitbit, Inc. | Monitoring device with voice interaction |
CN108536749A (en) * | 2018-03-12 | 2018-09-14 | 南京甄视智能科技有限公司 | The method for building personnel's Track View based on collision detection method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8200775B2 (en) * | 2005-02-01 | 2012-06-12 | Newsilike Media Group, Inc | Enhanced syndication |
US20120094600A1 (en) * | 2010-10-19 | 2012-04-19 | Welch Allyn, Inc. | Platform for patient monitoring |
US9633326B2 (en) * | 2015-06-10 | 2017-04-25 | Smart Catch Inc. | Load distribution and consolidation tracking system |
-
2018
- 2018-11-27 CN CN201811422106.5A patent/CN109522860B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10058290B1 (en) * | 2013-06-21 | 2018-08-28 | Fitbit, Inc. | Monitoring device with voice interaction |
CN103886658A (en) * | 2014-01-28 | 2014-06-25 | 北京中科虹霸科技有限公司 | Multi-modal biometric recognition-based distributed internet-of-things lock equipment and unlocking method thereof |
CN106649298A (en) * | 2015-07-22 | 2017-05-10 | 中国科学院微电子研究所 | Cross-domain association establishment method and system based on Internet of things |
CN105790955A (en) * | 2016-04-06 | 2016-07-20 | 深圳市博康智能信息技术有限公司 | Method and system for associating MAC addresses with face information |
CN106874347A (en) * | 2016-12-26 | 2017-06-20 | 深圳市深网视界科技有限公司 | A kind of method and system for matching characteristics of human body and MAC Address |
CN107590439A (en) * | 2017-08-18 | 2018-01-16 | 湖南文理学院 | Target person identification method for tracing and device based on monitor video |
CN107623754A (en) * | 2017-09-28 | 2018-01-23 | 武汉虹旭信息技术有限责任公司 | WiFi acquisition systems and its method based on true and false MAC identifications |
CN108280339A (en) * | 2018-01-16 | 2018-07-13 | 合肥工业大学 | A kind of passenger's personal identification method based on Multi-source Information Fusion |
CN108536749A (en) * | 2018-03-12 | 2018-09-14 | 南京甄视智能科技有限公司 | The method for building personnel's Track View based on collision detection method |
Non-Patent Citations (2)
Title |
---|
Robust object tracking via online Principal Component–Canonical Correlation Analysis (P3CA);Yuxia Wang;《ORIGINAL PAPER》;20150605;第159-173页 * |
基于SPARK技术的网络虚拟身份数据挖掘;宋宇航;《中国优秀硕士学位论文全文数据库(信息科技辑)》;20180315;第I139-183页 * |
Also Published As
Publication number | Publication date |
---|---|
CN109522860A (en) | 2019-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109271554B (en) | Intelligent video identification system and application thereof | |
Ren et al. | Distributed and efficient object detection in edge computing: Challenges and solutions | |
CN106339428B (en) | Suspect's personal identification method and device based on video big data | |
CN101697545B (en) | Security incident correlation method and device as well as network server | |
CN109639481A (en) | A kind of net flow assorted method, system and electronic equipment based on deep learning | |
CN111209261B (en) | User travel track extraction method and system based on signaling big data | |
CN107623754B (en) | WiFi acquisition system and method based on authenticity MAC identification | |
CN105871832A (en) | Network application encrypted traffic recognition method and device based on protocol attributes | |
CN111930868A (en) | Big data behavior trajectory analysis method based on multi-dimensional data acquisition | |
CN106789242B (en) | Intelligent identification application analysis method based on mobile phone client software dynamic feature library | |
Gaikwad et al. | Smart surveillance system for real-time multi-person multi-camera tracking at the edge | |
CN105518644A (en) | Method for processing and displaying real-time social data on map | |
CN111177469A (en) | Face retrieval method and face retrieval device | |
CN109522860B (en) | Internet of things application analysis system and method based on multiple tracks | |
CN113239792A (en) | Big data analysis processing system and method | |
CN110035408A (en) | A kind of public safety wisdom detection system and method based on wisdom net connection automobile | |
CN113255477A (en) | Comprehensive management system and method for pedestrian video images | |
CN114241012B (en) | High-altitude parabolic determination method and device | |
CN114661928A (en) | Retrieval method, device and equipment of violation image and storage medium | |
Cao et al. | Edge-Cloud collaborated object detection via difficult-case discriminator | |
CN104484651A (en) | Dynamic portrait comparing method and system | |
CN110019070A (en) | A kind of security log clustering method based on Hadoop and system of calling to account | |
CN117151959B (en) | Real-time video analysis method, system and storage medium for city management | |
CN102930016A (en) | Method and equipment for providing search results on mobile terminals | |
WO2013189202A1 (en) | Intelligent video analysis system and method |
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 | ||
CB03 | Change of inventor or designer information |
Inventor after: Zhu Jiaojiao Inventor after: Shu Wenbing Inventor after: Dai Changjiang Inventor before: Shu Wenbing Inventor before: Dai Changjiang |
|
CB03 | Change of inventor or designer information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |