INTEGRATING COMPUTER VISION SENSOR INNOVATIONS INTO MOBILE DEVICES. Eli Savransky Principal Architect - CTO Office Mobile BU NVIDIA corp.

Similar documents
TEGRA K1 AND THE AUTOMOTIVE INDUSTRY. Gernot Ziegler, Timo Stich

IMAGE AND VISION PROCESSING ON TEGRA K1. Elif Albuz

THE LEADER IN VISUAL COMPUTING

TEGRA K1 による GPU コンピューティング

GTC 2013 March San Jose, CA The Smartest People. The Best Ideas. The Biggest Opportunities. Opportunities for Participation:

Advanced Imaging Applications on Smart-phones Convergence of General-purpose computing, Graphics acceleration, and Sensors

April 4-7, 2016 Silicon Valley VISIONWORKS A CUDA ACCELERATED COMPUTER VISION LIBRARY S6783. Elif Albuz, April 4, 2016

OpenCV on Zynq: Accelerating 4k60 Dense Optical Flow and Stereo Vision. Kamran Khan, Product Manager, Software Acceleration and Libraries July 2017

TR An Overview of NVIDIA Tegra K1 Architecture. Ang Li, Radu Serban, Dan Negrut

Vision Acceleration. Launch Briefing October Neil Trevett Vice President Mobile Ecosystem, NVIDIA President, Khronos Group

The Benefits of GPU Compute on ARM Mali GPUs

P I X E V I A : A I B A S E D, R E A L - T I M E C O M P U T E R V I S I O N S Y S T E M F O R D R O N E S

A176 Cyclone. GPGPU Fanless Small FF RediBuilt Supercomputer. IT and Instrumentation for industry. Aitech I/O

Adhocracy Innovation with Imaging technology. Socionext Inc. Hiroyuki Komori July 5th, 2017

Enabling a Richer Multimedia Experience with GPU Compute. Roberto Mijat Visual Computing Marketing Manager

Development of Low Power and High Performance Application Processor (T6G) for Multimedia Mobile Applications

SOM PRODUCTS BRIEF. S y s t e m o n M o d u l e. Engicam. SOMProducts ver

Embedded Computing without Compromise. Evolution of the Rugged GPGPU Computer Session: SIL7127 Dan Mor PLM -Aitech Systems GTC Israel 2017

HotChips An innovative HD video and digital image processor for low-cost digital entertainment products. Deepu Talla.

Compact form factor. High speed MXM edge connector. Processor. Max Cores 4. Max Thread 4. Memory. Graphics. Video Interfaces.

Efficient Video Processing on Embedded GPU

Multimedia in Mobile Phones. Architectures and Trends Lund

8/28/12. CSE 820 Graduate Computer Architecture. Richard Enbody. Dr. Enbody. 1 st Day 2

The Future of 3D Graphics NVIDIA

DevKit7000 Evaluation Kit

TIOVX TI s OpenVX Implementation

PV8900-CORE Full Function TCC8900/TCC8901/TCC8902 CPU Module Specification

. SMARC 2.0 Compliant

Multimedia SoC System Solutions

Hugo Cunha. Senior Firmware Developer Globaltronics

Hardware Acceleration of Feature Detection and Description Algorithms on Low Power Embedded Platforms

Embedded real-time stereo estimation via Semi-Global Matching on the GPU

Our Technology Expertise for Software Engineering Services. AceThought Services Your Partner in Innovation

arm MULTICORE PLATFORMS FOR ADVANCED APPLICATIONS Product Longevity

A new Computer Vision Processor Chip Design for automotive ADAS CNN applications in 22nm FDSOI based on Cadence VP6 Technology

Nvidia Jetson TX2 and its Software Toolset. João Fernandes 2017/2018

Tablet MODECOM FreeTAB1004 IPS X4

Module Introduction. Content 15 pages 2 questions. Learning Time 25 minutes

G3399 Single Board Computer Introduction

. Micro SD Card Socket. SMARC 2.0 Compliant

27 March 2018 Mikael Arguedas and Morgan Quigley

Spring 2009 Prof. Hyesoon Kim

1. Introduction 2. Methods for I/O Operations 3. Buses 4. Liquid Crystal Displays 5. Other Types of Displays 6. Graphics Adapters 7.

CS427 Multicore Architecture and Parallel Computing

Spring 2011 Prof. Hyesoon Kim

Open Standard APIs for Embedded Vision Processing

WebGL Meetup GDC Copyright Khronos Group, Page 1

Your Strategic Partner for Renesas RZ/G1x Products & Solutions

NVIDIA DESIGNWORKS Ankit Patel - Prerna Dogra -

Open API Standards for Mobile Graphics, Compute and Vision Processing GTC, March 2014

Hi3536 H.265 Decoder Processor. Brief Data Sheet. Issue 03. Date

SAM A5 ARM Cortex - A5 MPUs

COM EXPRESS STANDARD ADVANTAGES

Graphics Hardware. Instructor Stephen J. Guy

Prasanna Krishnaswamy Intel Platform Architect. Imaging Systems Design for Mixed Reality Scenarios

Qualcomm Snapdragon 450 Mobile Platform

Freescale i.mx6 Architecture

NXP-Freescale i.mx6 MicroSoM i4pro. Quad Core SoM (System-On-Module) Rev 1.3

Hi3520D V300 H.264 CODEC Processor. Brief Data Sheet. Issue 04. Date

4K DVB-T2 / DVB-S2 Android Streaming Box with Fly Mouse

8 TABLET MICROSCOPY SOLUTION

3D Graphics in Future Mobile Devices. Steve Steele, ARM

Comprehensive Arm Solutions for Innovative Machine Learning (ML) and Computer Vision (CV) Applications

Benchmarking Real-World In-Vehicle Applications

Antonio R. Miele Marco D. Santambrogio

Application questions. Theoretical questions

M2-SM6-xx - i.mx 6 based SMARC Modules

EyeCheck Smart Cameras

Effective System Design with ARM System IP

Deep Learning: Transforming Engineering and Science The MathWorks, Inc.

SOM IB8000 Quad Core SOM (System-On-Module) Rev 1.3

GTC Interaction Simplified. Gesture Recognition Everywhere: Gesture Solutions on Tegra

Software Driven Verification at SoC Level. Perspec System Verifier Overview

Emerging Vision Technologies: Enabling a New Era of Intelligent Devices

Mobile AR Hardware Futures

Introduction to the Tegra SoC Family and the ARM Architecture. Kristoffer Robin Stokke, PhD FLIR UAS

PHIL CARMACK SVP Mobile Business Unit Annual Investor Day 2013

NXP-Freescale i.mx6 MicroSoM i2. Dual Core SoM (System-On-Module) Rev 1.3

Basic: 125x95 mm Compact: 95x95 mm. Processor. Max Cores 4. Video Interfaces. Video Resolution. Mass Storage 2 x S-ATA Gen3 Channels.

Introduction to Sitara AM437x Processors

Picture-in-Picture. Video-in-Video

Elaborazione dati real-time su architetture embedded many-core e FPGA

The Challenges of System Design. Raising Performance and Reducing Power Consumption

Dimensions. System Information. Memory. Stand mm (19.4 inches) mm (26.1 inches) Depth mm (1.4 inches) 78.2 mm (3.

Introduction to ASIC Design

Silicon Motion s Graphics Display SoCs

AR Standards Update Austin, March 2012

Intelligent Video Analytics for Urban Management

Gecata by Movavi 5. Recording desktop. Recording with webcam Capture videos of the games you play. Record video of your full desktop.

Make technology more simple, Make life more intelligent. Embedded Computer EC-A3288C. Specifications V1.0

Completing the Multimedia Architecture

Outline Marquette University

NVIDIA AI BRAIN OF SELF DRIVING AND HD MAPPING. September 13, 2016

With voice navigation, fully compatible with Amazon AVS/Alexa voice services

4K Android Streaming Box with Fly Mouse

The Mobile Internet: The Potential of Handhelds to Bring Internet to the Masses. April 2008

Unleashing the benefits of GPU Computing with ARM Mali TM Practical applications and use-cases. Steve Steele, ARM

Visual Pose Estimation System for Autonomous Rendezvous of Spacecraft

2010 PROFIT. Research & Education. Tim Cheng ( 鄭光廷 )

A176 C clone. GPGPU Fanless Small FF RediBuilt Supercomputer. Aitech

Transcription:

INTEGRATING COMPUTER VISION SENSOR INNOVATIONS INTO MOBILE DEVICES Eli Savransky Principal Architect - CTO Office Mobile BU NVIDIA corp.

Computer Vision in Mobile Tegra K1 It s time!

AGENDA Use cases categories Underlying technologies examples Performance and power considerations Software considerations and dilemmas

VISION FUNCTIONALITY TAXONOMY 3D Reconstruction Markets UI / Smart TV / STB Gaming Automotive Social/Media E-commerce Modeling/Architecture/DIY/3D printing Tracking User Facing Scene Facing User Facing Scene Facing Small Scale Object Reconstruction Face, eye and hand gesture tracking Environmental Feature Tracking Facial Modeling Large Scale Body Modeling Scene Reconstruction Body Tracking Indoor/Outdoor Positional Tracking

UNDERLYING TECHNOLOGY: DEPTH EXTRACTION Obtain a depth map for many points on a 2D picture Not necessarily per every pixel From there, we can calculate: 3D geometry and model Body position and movement Face features and expression Aggregating models is easy From different shots From different sources

3D SCANNING: THE TECHNOLOGIES Different approaches: Structured light Project IR pattern Find the pattern symbols on the image Triangulate to find depth Stereo Capture two or more images Find corresponding points Triangulate to find depth Structure from Motion (SfM) Similar to Stereo but using same camera over time (instead of multiple cameras) Coded / multiple aperture Project different patterns and solve for depth Time of Flight Project pulse of light Capture returned phase A IR B

UNDERLYING TECHNOLOGY: VISUAL ODOMETRY The use of data from cameras to estimate device change in position over time 1. Uses either single, stereo, or omnidirectional cameras 2. Image correction for lens distortion 3. Feature detection 4. Construct optical flow field 5. Estimation of the camera motion from the optical flow 1. Kalman filter or cost function minimization 6. Check potential tracking errors and remove outliers 7. Periodic repopulation of points to maintain coverage across the image Images from Davide Scaramuzza

ARE WE THERE YET? Performance Do the algorithms fit in the HW? Is the HW fast enough? Do they leave enough headroom for the actual application? Do the algorithms and the applications work together efficiently? Power Cost Does it fit the constrains of thermal, max current and battery life? New sensors, light sources, etc. SW infrastructure Do the right APIs exist? Is the imaging pipeline flexible enough? Are there programming languages/environment to support this?

Audio Processor ARM7 TEGRA K1 28 nm HPM 23x23mm, 0.7mm pitch HS-FCBGA Quad Cortex-A15 4x Cores (1+ GHz) NEON SIMD 2 MB L2 (Shared) ARM Trust Zone Shadow LP C-A15 CPU HD Video Processor 1080p24/30 Video Decode 1080p24/30 Video Encode H.264 MPEG4 VC1 MPEG2 VP8 TEGRA K1: A MAJOR LEAP FORWARD FOR MOBILE & EMBEDDED APPLICATIONS SATA2 x1 USB 2.0 x3 PCIe* G2 x4 + x1 Image Processor 25MP Sensor Support ISP 1080p60 Enhanced JPEG Engine Kepler GeForce GPU w/cuda OpenGL-ES nextgen 192 Stream Processors 2D Graphics/Scaling KEPLER GPU, 192 CORES CUDA USB 3.0* x2 UART x4 I2C x5 SPI x4 SDIO/MMC x4 Display x2 HDMI edp/lvds 12GB/S BANDWIDTH VIDEO IMAGE COMPOSITOR (VIC) CSI x4 + x4 NOR Flash DDR3 Ctlr 64b 800+ MHz Security Engine DAP x5 (1 2 S/TDM) DESIGNED FOR MOBILE DEVICES

Audio Processor ARM7 GPU 28 nm HPM 23x23mm, 0.7mm pitch HS-FCBGA Quad Cortex-A15 4x Cores (1+ GHz) NEON SIMD 2 MB L2 (Shared) ARM Trust Zone Shadow LP C-A15 CPU HD Video Processor 1080p24/30 Video Decode 1080p24/30 Video Encode H.264 MPEG4 VC1 MPEG2 VP8 KEPLER Architecture 192 CUDA Cores, SM3.2 ISA Compatible to GeForce, Quadro, Tesla SATA2 x1 USB 2.0 x3 PCIe* G2 x4 + x1 Image Processor 25MP Sensor Support ISP 1080p60 Enhanced JPEG Engine Kepler GeForce GPU w/cuda OpenGL-ES nextgen 192 Stream Processors 2D Graphics/Scaling 64kb L1 Cache and Shared Memory 128kb L2 Cache 128 kb Register File USB 3.0* x2 UART x4 I2C x5 SPI x4 SDIO/MMC x4 Display x2 HDMI edp/lvds CSI x4 + x4 NOR Flash DDR3 Ctlr 64b 800+ MHz Security Engine DAP x5 (1 2 S/TDM)

SW CONSIDERATIONS Need APIs and frameworks to develop SW Flexible and complete enough for experimentation Fast and stable enough for productization Portable for installed base APIs and libraries Android Camera HAL v.3 OpenCV OpenVX StreamInput VisionWorks CUDA

ANDROID CAMERA HAL V3 Camera HAL v3 is a fundamentally new API Flexible primitives for building sophisticated use-cases Interface is clean and easily extensible Apps can have more control, and more responsibility Enables sophisticated camera applications Faster time to market and higher quality 1 Request 1 capture 1 result metadata + N image buffers

OPENCV LIBRARY Version 2.4.5 >900 functions (x the datatypes) OpenCV4Tegra acceleration: CUDA, NEON, GLSL, TBB multithreading OpenCV Image processing General Image Processing Segmentation Machine Learning, Detection Image Pyramids Transforms Fitting Video, Stereo, and 3D Camera Calibration Features Depth Maps Optical Flow Inpainting Tracking

VISIONWORKS Sobel Convolve Bilateral Filter Integral Image Integral Histogram Corner Harris Corner FAST Image Pyramid Optical Flow PyrLK Optical Flow Farneback Warp Perspective Hough Lines Fast NLM Denoising Stereo Block Matching IME (Iterative Motion Estimation) HOG (Histogram of Oriented Gradients) Soft Cascade Detector Object Tracker TLD Object Tracker SLAM Path Estimator MedianFlow Estimator

IT IS HAPPENING! Use cases emerging Tegra K1 mobile compute power in mobile devices Software Infrastructure

THANKS