Transcription

High Speed Video and ImageProcessing with Java and HadoopMelli AnnamalaiSenior Principal Product ManagerRob AbbottBig Data Technical LeadKrishna KuchimanchiHadoop DeveloperSeptember 20, 2016Copyright 2016, Oracle and/or its affiliates. All rights reserved.

Safe Harbor StatementThe following is intended to outline our general product direction. It is intended forinformation purposes only, and may not be incorporated into any contract. It is not acommitment to deliver any material, code, or functionality, and should not be relied uponin making purchasing decisions. The development, release, and timing of any features orfunctionality described for Oracle’s products remains at the sole discretion of Oracle.Copyright 2016, Oracle and/or its affiliates. All rights reserved. 4

Growing Volumes of Video and Image DataDronesSurveillance camerasCourtesy: c-span.orgCorporate archivesStock imagesLicense platesCopyright 2016, Oracle and/or its affiliates. All rights reserved. 5

Some Challenges Large volumes of data (addressing scale) Diversity in types of video/image processing Moving video data across the network(out of the scope of this presentation)Copyright 2016, Oracle and/or its affiliates. All rights reserved. 6

Addressing ScaleIdentified faces, license plate text,matching timestamps, etcInputInputVideo and Image Processing Face recognition License plate identification Fingerprint matching Optical character recognition Specialized processingIdentified faces, timestamps,individual frames6x compute powerCopyright 2016, Oracle and/or its affiliates. All rights reserved. 7

Scale-out Capability of Apache Hadoop18x compute poweron Oracle Big Data ApplianceCopyright 2016, Oracle and/or its affiliates. All rights reserved. 8

Multimedia Analytics Framework Enables processing of video and image data in Hadoop Leverages Hadoop parallelism for high speed processing– Ships with OpenCV (www.opencv.org)– Integrate third party software into framework Massive storage and InfiniBand network of Oracle Big Data Applianceenables processing and management of petabytes of multimedia dataPart of Oracle Big Data Spatial and GraphCopyright 2016, Oracle and/or its affiliates. All rights reserved. 9

Multimedia Analysis FrameworkHow it WorksOutputJSON or CSV or image with labels, timestamp in videoProcessSplitInputHDFSCopyright 2016, Oracle and/or its affiliates. All rights reserved. 10

Framework Runs a MapReduce Job Submitted as a Hadoop job hadoop jar ordhadoop-multimedia-analytics.jar –conf vprocess.xml vinput voutput Map tasks on each node decode segment of video/image and DE(JCODEC/FFMPEG)ANALYZE(OPENCV/PLUGIN CODE) (OPENCV/PLUGIN PEGANALYZE(OPENCV/PLUGIN CODE) (OPENCV/PLUGIN PEG)ANALYZE(OPENCV/PLUGIN CODE) (OPENCV/PLUGIN CODE)Copyright 2016, Oracle and/or its affiliates. All rights reserved. Confidential – Oracle Internal/Restricted/Highly Restricted11

Multimedia Analytics FrameworkBenefits Faster video processing– Processing massive video/image volumes ideal for Hadoop architecture Extensible framework– Use with a variety of third party video/image processing engines Use framework without specialized Hadoop skills– Gain Hadoop scalability without Hadoop-specific management and programming skills Integrate video/image processing with Big Data applicationsCopyright 2016, Oracle and/or its affiliates. All rights reserved. 12

Integrate with Video/Image Processing TechnologyOracle AnalyticsproductsDisplay/visualizeMAPMAPMAPHadoop APIsfor ultimedia AnalyticsPartner moduleMAPFramework OpenCVMAPMAPHadoop platformCopyright 2016, Oracle and/or its affiliates. All rights reserved. MAPMAPMAPOraclePartner13

ExtensibilityAddress diversity in video/image processing requirementsCopyright 2016, Oracle and/or its affiliates. All rights reserved. 14

Extensibility: Implement processFrame()Input:(key, value (frame from video or image))Output: (key, value)Defined by implementationImplement reduce task: For example, group by output [email protected] void processFrame(Text key, OrdImageWritable value)@Overridepublic Text getKey()@Overridepublic OrdImageWritable getValue()Copyright 2016, Oracle and/or its affiliates. All rights reserved. 15

Part of Oracle Big Data Cloud ServiceBig Data Cloud Service(Includes Big Data Spatial and Graph,Multimedia Analytics Framework)Copyright 2016, Oracle and/or its affiliates. All rights reserved. Confidential – Oracle Internal/Restricted/Highly Restricted16

Building ApplicationsCopyright 2016, Oracle and/or its affiliates. All rights reserved. 17

License Plate RecognitionCopyright 2016, Oracle and/or its affiliates. All rights reserved. 18

Integrate with Video/Image Processing TechnologyOracle AnalyticsproductsDisplay/visualizeHadoop APIsfor dataingestLicense plate recognitionOracleHadoop platformCopyright 2016, Oracle and/or its affiliates. All rights reserved. Partner19

Number Plate Demonstration OverviewExploration (Citizen Data Science) viaBig Data DiscoverySend Email to recipient if‘number plate matches fine’Captured ImagesNumber PlatesBig Data Lite VM withOracle Spatial & Graph & license platerecognitionOracleSQL DeveloperDB QueriesOracle DB11G11G DatabaseNumber plate fact & customer fact data to‘Detect & Act’ on finesCopyright 2016, Oracle and/or its affiliates. All rights reserved.

Copyright 2016, Oracle and/or its affiliates. All rights reserved. 21

Copyright 2016, Oracle and/or its affiliates. All rights reserved. 22

Copyright 2016, Oracle and/or its affiliates. All rights reserved. 23

Copyright 2016, Oracle and/or its affiliates. All rights reserved. 24

Optical Character RecognitionWith Apache TesseractCopyright 2016, Oracle and/or its affiliates. All rights reserved. 25

Implement OCR processing in processFrame()Input:(key, value (frame from video or image)Output: (key, value)Output value image overlaid with recognized [email protected] void processFrame(Text key, OrdImageWritable value) { call Tesseract APIs ocrString instance.doOCR()Details in /using oracle big data spatialCopyright 2016, Oracle and/or its affiliates. All rights reserved. 26

Copyright 2016, Oracle and/or its affiliates. All rights reserved. 27

Partnership with GriauleCopyright 2016, Oracle and/or its affiliates. All rights reserved. 28

Griaule Biom etrics S/A Specialized in software for large scale biometric identificationsystems (Big Data Biometrics) Provides technology for Systems Integrators who provide solutionsto the end customer 15 years researching biometrics, with over 20 certifications (FBI,NIST, FVC, etc.) Largest ABIS in the world using fingerprint as primary technologyfor deduplication Multimodal fingerprint, face and voice technologiesCopyright 2016, Oracle and/or its affiliates. All rights reserved. Confidential – Oracle Internal/Restricted/Highly Restricted29

Identification Uses Recognize people amid crowds Facial aging and weight changes Over 20 FBI certifications inbiometrics Most precise finger print algorithmin the world since the FVC2006Copyright 2016, Oracle and/or its affiliates. All rights reserved.

Architecture Easily integrated Plan to integrate with allGriaule’s identification systems(facial, voice, fingerprint andmore) Full access to Griaule’sintelligence systemsCopyright 2016, Oracle and/or its affiliates. All rights reserved.

Implement Griaule processing in processFrame()Input:(key, value (frame from video or image)Output: (key, value)Output value face with green or yellow bounding [email protected] void processFrame(Text key, OrdImageWritable value) {Copyright 2016, Oracle and/or its affiliates. All rights reserved. 32

DemoCopyright 2016, Oracle and/or its affiliates. All rights reserved. Image Courtesy Griaule33

Roadmap Real-time analysis of streaming video Spark streaming integrationCopyright 2016, Oracle and/or its affiliates. All rights reserved. 34

Summary Multimedia Analytics Frameworks enables fast video and image processingin Hadoop Extensibility API for third party software integration enables many differenttypes of processing Video and image data can be analyzed along side other Big Data typesCopyright 2016, Oracle and/or its affiliates. All rights reserved. 35

Copyright 2016, Oracle and/or its affiliates. All rights reserved. Confidential – Oracle Internal/Restricted/Highly Restricted36