CN104935785A - Hadoop based distributed video big data prospect detection and motion tracking method - Google Patents
Hadoop based distributed video big data prospect detection and motion tracking method Download PDFInfo
- Publication number
- CN104935785A CN104935785A CN201510249132.2A CN201510249132A CN104935785A CN 104935785 A CN104935785 A CN 104935785A CN 201510249132 A CN201510249132 A CN 201510249132A CN 104935785 A CN104935785 A CN 104935785A
- Authority
- CN
- China
- Prior art keywords
- video
- distributed
- detection
- motion tracking
- decoding
- 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.)
- Pending
Links
Landscapes
- Closed-Circuit Television Systems (AREA)
Abstract
A Hadoop based distributed video big data prospect detection and motion tracking method relates to the distributed video technical field, and comprises the following steps: 1, setting up a Hadoop distributed detection platform; 2, video decoding: 2.1, setting up a video decoding database; 2.2, video corresponding decoding; 2.3, video data segment; 3, distributed prospect detection: 3.1, setting up computer calculation codes; 3.2, situation transition; 3.3, parameter mapping; 4, motion tracking calculation: 4.1, setting up a distributed calculating model; 4.2, comparison. The Hadoop based distributed video big data prospect detection and motion tracking method is convenient for fast analysis, calculation and tracking, thus shortening time, improving work efficiency, and saving energy resource.
Description
Technical field:
The present invention relates to distributed video technical field, be specifically related to a kind of based on the large data foreground detection of Hadoop distributed video and motion tracking method.
Background technology:
Distributed video coding (Distributed Video Coding) is theoretical and Wyner-Ziv theory based on Slepian-Wolf, absolute coding is carried out to two or more independent identically distributed information source, then utilizes the correlation between information source to carry out combined decoding to the information source of all codings by single decoder.The difference of it and traditional video coding technique is: traditional technical standard is usually all for fully excavating the redundant information of vision signal at coding side, therefore encoder complexity is generally 5 ~ 10 times of decoding complex degree, is suitable for vision signal first encoding, the occasion (as video broadcasting, video request program, video disc storage etc.) of repeatedly decoding; And distributed video coding has features such as encoder complexity is low, coding side power consumption is low, zmodem, be suitable for all limited wireless video terminal of some computing capabilitys, memory size, power consumption (as wireless video monitoring system, video sensor network etc.).
Hadoop is a distributed system architecture developed by Apache fund club.User can when not understanding distributed low-level details, exploitation distributed program.The power making full use of cluster carries out high-speed computation and storage.
Hadoop achieves a distributed file system (Hadoop Distributed FileSystem), is called for short HDFS.HDFS has the feature of high fault tolerance, and design is used for being deployed on cheap (low-cost) hardware; And it provides high-throughput (highthroughput) to visit the data of application program, be applicable to the application program that those have super large data set (large data set).The requirement of HDFS relaxes (relax) POSIX, can access the data in (streaming access) file system in the form of streaming.
The design that the framework of Hadoop is most crucial is exactly: HDFS and MapReduce.HDFS is that the data of magnanimity provide storage, then MapReduce is that the data of magnanimity provide calculating.
Along with promoting the use of of internal security supervisory control system, the data volume of monitoring video is increasing, these data making user therefrom obtain needs become abnormal difficult, such as, whether user needs to monitor certain region has object loss, and he needs to inquire concrete time period of object loss, place and situation at that time by monitoring video.If by manually completing such work, then need the monitoring video reaching tens hours in the face of several camera produces, this is all great waste to manpower and time undoubtedly, if run into the important case of seizing every minute and second, even may delay the opportunity of solving a case.
Summary of the invention:
The object of this invention is to provide one based on the large data foreground detection of Hadoop distributed video and motion tracking method, it is convenient to carry out rapid analysis, calculating, tracking, shortens the time, increases work efficiency, and saves the energy.
In order to solve the problem existing for background technology, the present invention adopts following technical scheme: its method is:
Step one: set up Hadoop Distributed Detection platform: adopt Hadoop distributed computing platform to detect, and data stored, adopts cipher mode to be encrypted while storage;
Step 2: video decode:
(2.1) video decode storehouse, is set up: by video decode library storage in memory;
(2.2), video correspondence decoding: set up a video decoding platform, carry out correspondence decoding by video decode storehouse, carry out H.264 decoding standard during decoding;
(2.3), partitioning video data: at Hadoop Distributed Detection platform, the storage information of pending data on HDFS is classified, then video is carried out segmentation;
Step 3: distributed foreground detection:
(3.1), computer calculate code is set up: by foreground detection module, frame of video is detected, after detection, export contextual model;
(3.2), change scene: contextual model is carried out code conversion,
(3.3), parameters map: adopt Parameter Mapping machine to video the contextual model of conversion, after reflection, file resolution is adjusted to standard value;
Step 4: the calculating of motion tracking:
(4.1), distributed computing platform is set up: calculate motion tracking figure according to computation model,
(4.2), contrast: figure is carried out operational efficiency contrast.
The present invention has following beneficial effect: be convenient to carry out rapid analysis, calculating, tracking, shortens the time, increases work efficiency, and saves the energy.
Embodiment:
This embodiment adopts following technical scheme: its method is:
Step one: set up Hadoop Distributed Detection platform: adopt Hadoop distributed computing platform to detect, and data stored, adopts cipher mode to be encrypted while storage;
Step 2: video decode:
(2.1) video decode storehouse, is set up: by video decode library storage in memory;
(2.2), video correspondence decoding: set up a video decoding platform, carry out correspondence decoding by video decode storehouse, carry out H.264 decoding standard during decoding;
(2.3), partitioning video data: at Hadoop Distributed Detection platform, the storage information of pending data on HDFS is classified, then video is carried out segmentation;
Step 3: distributed foreground detection:
(3.1), computer calculate code is set up: by foreground detection module, frame of video is detected, after detection, export contextual model;
(3.2), change scene: contextual model is carried out code conversion,
(3.3), parameters map: adopt Parameter Mapping machine to video the contextual model of conversion, after reflection, file resolution is adjusted to standard value;
Step 4: the calculating of motion tracking:
(4.1), distributed computing platform is set up: calculate motion tracking figure according to computation model,
(4.2), contrast: figure is carried out operational efficiency contrast.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (1)
1., based on the large data foreground detection of Hadoop distributed video and motion tracking method, it is characterized in that its method is:
Step one: set up Hadoop Distributed Detection platform: adopt Hadoop distributed computing platform to detect, and data stored, adopts cipher mode to be encrypted while storage;
Step 2: video decode:
(2.1) video decode storehouse, is set up: by video decode library storage in memory;
(2.2), video correspondence decoding: set up a video decoding platform, carry out correspondence decoding by video decode storehouse, carry out H.264 decoding standard during decoding;
(2.3), partitioning video data: at Hadoop Distributed Detection platform, the storage information of pending data on HDFS is classified, then video is carried out segmentation;
Step 3: distributed foreground detection:
(3.1), computer calculate code is set up: by foreground detection module, frame of video is detected, after detection, export contextual model;
(3.2), change scene: contextual model is carried out code conversion,
(3.3), parameters map: adopt Parameter Mapping machine to video the contextual model of conversion, after reflection, file resolution is adjusted to standard value;
Step 4: the calculating of motion tracking:
(4.1), distributed computing platform is set up: calculate motion tracking figure according to computation model,
(4.2), contrast: figure is carried out operational efficiency contrast.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510249132.2A CN104935785A (en) | 2015-05-15 | 2015-05-15 | Hadoop based distributed video big data prospect detection and motion tracking method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510249132.2A CN104935785A (en) | 2015-05-15 | 2015-05-15 | Hadoop based distributed video big data prospect detection and motion tracking method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104935785A true CN104935785A (en) | 2015-09-23 |
Family
ID=54122733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510249132.2A Pending CN104935785A (en) | 2015-05-15 | 2015-05-15 | Hadoop based distributed video big data prospect detection and motion tracking method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104935785A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106686108A (en) * | 2017-01-13 | 2017-05-17 | 中电科新型智慧城市研究院有限公司 | Video monitoring method based on distributed detection technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003079663A2 (en) * | 2002-03-14 | 2003-09-25 | General Electric Company | High-speed search of recorded video information to detect motion |
| CN103279521A (en) * | 2013-05-28 | 2013-09-04 | 重庆大学 | Video big data distributed decoding method based on Hadoop |
| CN104284057A (en) * | 2013-07-05 | 2015-01-14 | 浙江大华技术股份有限公司 | Video processing method and device |
| CN104394415A (en) * | 2014-12-09 | 2015-03-04 | 中国电子科技集团公司第二十八研究所 | Method for distributed decoding of video big data |
-
2015
- 2015-05-15 CN CN201510249132.2A patent/CN104935785A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003079663A2 (en) * | 2002-03-14 | 2003-09-25 | General Electric Company | High-speed search of recorded video information to detect motion |
| CN103279521A (en) * | 2013-05-28 | 2013-09-04 | 重庆大学 | Video big data distributed decoding method based on Hadoop |
| CN104284057A (en) * | 2013-07-05 | 2015-01-14 | 浙江大华技术股份有限公司 | Video processing method and device |
| CN104394415A (en) * | 2014-12-09 | 2015-03-04 | 中国电子科技集团公司第二十八研究所 | Method for distributed decoding of video big data |
Non-Patent Citations (1)
| Title |
|---|
| 杨飞: "基于Hadoop的分布式视频大数据前景检测与运动跟踪方法研究", 《重庆大学硕士学位论文》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106686108A (en) * | 2017-01-13 | 2017-05-17 | 中电科新型智慧城市研究院有限公司 | Video monitoring method based on distributed detection technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10511696B2 (en) | System and method for aggregation, archiving and compression of internet of things wireless sensor data | |
| US11166041B2 (en) | Hybrid pixel-domain and compressed-domain video analytics framework | |
| US20180332301A1 (en) | Method, apparatus, and system for deep feature coding and decoding | |
| WO2021027137A1 (en) | Time series data storage method and apparatus, computer device, and storage medium | |
| CN110430260A (en) | Robot cloud platform based on big data cloud computing support and working method | |
| CN105045856A (en) | Hadoop-based data processing system for big-data remote sensing satellite | |
| CN111092926B (en) | Digital retina multivariate data rapid association method | |
| CN103279521A (en) | Video big data distributed decoding method based on Hadoop | |
| CN104125458A (en) | Lossless stored data compression method and device | |
| CN110719438A (en) | Synchronous transmission control method for digital retina video stream and characteristic stream | |
| CN103714553A (en) | Multi-target tracking method and apparatus | |
| CN116702083B (en) | Satellite telemetry data anomaly detection method and system | |
| CN104346384A (en) | Method and device for processing small files | |
| CN105554502A (en) | Distributed compressed sensing video encoding and decoding method based on foreground-background separation | |
| CN102663375A (en) | Active target identification method based on digital watermark technology in H.264 | |
| CN104301671A (en) | Traffic monitoring video storing method in HDFS based on event intensity | |
| CN114640355A (en) | Lossy compression and decompression method, system, storage medium and equipment of time sequence database | |
| CN103577245A (en) | Lightweight class virtual machine migration method | |
| CN104394415B (en) | A kind of method of video big data distribution decoding | |
| KR20230040285A (en) | Method and system for detecting an object region based on bitstream information of image information | |
| CN104935785A (en) | Hadoop based distributed video big data prospect detection and motion tracking method | |
| CN109656712B (en) | Method and system for extracting GRIB code data | |
| CN116755403B (en) | Data acquisition method and system based on photovoltaic module production control system | |
| CN104853150A (en) | Multi-camera objective cooperatively tracking technology | |
| CN100574460C (en) | AVS inter-frame predicated reference sample extraction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150923 |