Defense Systems and AI-Enabled Visio ion Computing Kevin Moran - - PowerPoint PPT Presentation

▶
defense systems and ai enabled visio ion computing
SMART_READER_LITE
LIVE PREVIEW

Defense Systems and AI-Enabled Visio ion Computing Kevin Moran - - PowerPoint PPT Presentation

Feb 17, 2023 41 likes •431 views

WE INNOV OVAT ATE. E. WE DELIVER. ER. YOU SUCCEED. CCEED. Defense Systems and AI-Enabled Visio ion Computing Kevin Moran (kevin.moran@abaco.com) Abaco Systems advances the capabilities of the warfighter by providing game changing mission

slide-1
SLIDE 1

Defense Systems and AI-Enabled Visio ion Computing

Kevin Moran (kevin.moran@abaco.com)

WE INNOV OVAT ATE.

  • E. WE DELIVER.

ER.

YOU SUCCEED. CCEED.

slide-2
SLIDE 2

Abaco Systems advances the capabilities of the warfighter by providing game changing mission ready embedded systems, components and technologies to defense contractors. Our products reduce program risk, allow technology insertion with affordable readiness, and ultimately help platforms reach deployment sooner with lower cost

2

slide-3
SLIDE 3

3

Highly Experienced Team of 800+ Professionals with Global Reach

slide-4
SLIDE 4

4

Our Portfolio

slide-5
SLIDE 5

5

ABACO SYSTEMS SMALL FORM FACTOR RUGGED BOX

GVC1000

Rugged TX2 SoM Digital Protocols MilCAN / CAN High Speed 10 Gig Ethernet Integrated SATA Storage Expandable Future IO Military Connectors

Designed for Rugged applications for use in Harsh environments including Military Vehicles, UAVs, Robotics, Avionics and Industrial. Aligned to military environmental specifications

  • 40°C to +71°C
slide-6
SLIDE 6

6

ABACO SYSTEMS SMALL FORM FACTOR RUGGED BOX

GVC2000

Designed for Rugged applications for use in Harsh environments including Military Vehicles, UAVs, Robotics, Avionics and Industrial. Aligned to military environmental specifications

  • 40°C to +71°C

Rugged GM107 Maxwell ADC DAC ARINC429 (October) 1553 28V I/O Digital I/O Audio

slide-7
SLIDE 7

7

Vision functions supported by TX2-integrated GVC1000/2000

  • Deep Learning, inference at the edge.
  • Advanced image processing ISP and compression
  • Data parallelism using CUDA and OpenCL
slide-8
SLIDE 8

8

What is Autonomous?

From the Oxford Dictionary…

  • Freedom to govern itself or control its own affairs
  • Freedom to act independently
  • Device capable of operating without direct

human control It is not simply…

  • Automated,
  • Remotely operated (unmanned),
  • Guided.

For our purposes: Able to conduct complex, cooperative, extended missions within broad objectives, principles and guidelines.

slide-9
SLIDE 9

9

Modern Origin: ALVINN 1985-88

slide-10
SLIDE 10

ALVINN Road Test - 1988

10

slide-11
SLIDE 11

11

Vehicle AI: abridged chronology – personal / commercial

Chevy Tahoe: DARPA Urban Challenge 2007 Tesla S Autopilot 2014 ALVINN 1988

Robo-tram Robo-taxi Robo-pizza Robo-beer

slide-12
SLIDE 12

12

Vehicle AI: abridged chronology – military

ALVINN 1988 Oshkosh TerraMax: DARPA Urban Challenge 2007 Lockheed Martin F-35A 2014

Autonomous Platform Autonomous Underwater Vehicle Boeing QF-16 Robot Pack Mule

Tremendous variety of applications, missions, environments!

slide-13
SLIDE 13

13

AI will serve many purposes

Logistics AR displays, wearables ISR Cyber security, resiliency War gaming/planning Big data, cloud computing Collaborative missions Electronic warfare Missiles

slide-14
SLIDE 14

14

DoD invests in Autonomous and AI

Excerpted from roadmap:

  • Autonomous system is self-directed to reach a human-directed goal.
  • Machine learning…autonomous systems can develop modified strategies.
  • In unforeseen situations the autonomous system finds the optimal solution.
  • Smart teams of unmanned systems operating autonomously…conduct operations in

contested environments.

  • Industry and academic partnerships will be critical.

DoD Unmanned Systems Roadmap

slide-15
SLIDE 15

15

All Branches active with Autonomous R&D

Land Air Sea

Boeing QF-16 S-76 Helicopter - SARA Cessna 208 – DARPA ALIAS Sea Hunter Swarm Patrol UUV Robotic Sentries Cooperative Task Trucks Legged Squad Support

slide-16
SLIDE 16

16

Swarm capabilities across all branches

Air Force: Predator swarms Navy: Swarm Patrol Boats Army: Robotic Sentries

Common core:

  • Swarm is given broad cooperative mission.
  • Control is decentralized.
  • Vehicles extend communications beyond line of sight.
  • On-guard and patrolling 24x7.
  • Decision ability to move from defensive to offensive posture.

MDARS

SWARM

slide-17
SLIDE 17

17

Autonomous vehicles and AR require vision

Bot

  • th demand fid

fidelity, , ac accuracy an and low low la late tency!

…add registration and stabilization Target classification, tracking, fusion, perception

slide-18
SLIDE 18

18

Demanding visual environments and challenges

  • 2D localization
  • Lack of intentionally active threats
  • Stable terrain
  • Blue skies

On-road: planar field

  • 3D localization
  • Contested space: omni-directional threats
  • Explosions: altered terrain, EMPs
  • Degraded visual environments

“Off-road”: spherical field

slide-19
SLIDE 19

Software - AXIS Enabled Middleware for High Performance

Image processing, visualization & graphics

AXIS ImageFlex

19

slide-20
SLIDE 20

AXIS ImageFlex

Image processing and visualization toolkit

20

slide-21
SLIDE 21

Vision solutions: General

slide-22
SLIDE 22

22

Machine Vision examples

Neural Network Classification Neural Network Object Detection CUDA Interoperability Adaptive Image Fusion GPU Stabilization Image Morphing Situational Awareness

slide-23
SLIDE 23

23

Neural Network Classification

(CAFFE (Convolutional Architecture for Fast Feature Embedding) is a deep learning framework, originally developed at UC Berkeley.)

  • Demonstrates integration of AI classifier into an

ImageFlex application.

  • Uses a pre-trained CAFFE-based Googlenet neural network.
  • Converted to an optimized inference engine via ImageFlex conversion

utility, this, in turn, uses NVIDIA’s TensorRT.

  • ImageFlex also provides a AI annotator tool to assist labelling images to

prepare for neural net training for frameworks such as CAFFE using NVIDIA’s DIGITs.

slide-24
SLIDE 24

24

Neural Network Classification

0:17

slide-25
SLIDE 25

25

Neural Network Object Detection

  • Demonstrates integration of AI object detection

into an ImageFlex application

  • Uses NVIDIA’s DetectNet object detection neural network.
  • As per the simpler classifier, this is converted to an optimized inference

engine via ImageFlex conversion utility, that uses NVIDIA’s TensorRT.

  • ImageFlex is used to draw the bounding boxes based on the detections

and certainty threshold.

slide-26
SLIDE 26

26

Neural Network Object Detection

0:20

slide-27
SLIDE 27

27

CUDA Interoperability

  • Utilizes ImageFlex simple API to facilitate CUDA

and ImageFlex interoperability.

  • Allows user to integrate their CUDA processing into an ImageFlex application.
  • Eliminates need for complex and confusing OpenGL and CUDA interop code.
  • API also provides OpenCL interoperability support.
slide-28
SLIDE 28

28

CUDA Interoperability

0:20

slide-29
SLIDE 29

29

Adaptive Image Fusion

  • Two types of fusion mode available:
  • Alpha blend – simple weighted

combination of two input images.

  • Adaptive fusion – designed to maintain

high-resolution detail of both images.

  • Provides per-pixel frequency cut & other fusion weightings. Enables tailoring to best

meet fusion demands of application and sensor attributes.

  • Leverages GPU via OpenGL ‘shader’ language - OpenGLSL. GPU agnostic. High

performance, minimal CPU overhead.

slide-30
SLIDE 30

30

Adaptive Image Fusion

0:32

slide-31
SLIDE 31

Vision solutions: Augmented Reality / Displays

slide-32
SLIDE 32

32

GPU Stabilization

  • Use a CUDA-optimized algorithm to stabilize video,

correcting for shake in horizontal and vertical planes, plus rotations zoom.

  • Algorithm is based on the Lucas-Kanade Method.
slide-33
SLIDE 33

33

GPU Stabilization

0:20

slide-34
SLIDE 34

34

Distortion Correction and Image Morphing

Provides simple barrel / pin cushion distortion correction. Complex adaptive correction via “morphing” per grid. More complex dense grid can morph to arbitrary

  • shape. E.g. to compensate for HMD eye pieces or

complex optics. Each sub-rectangle in grid can morph in three different ways to suite requirements.

slide-35
SLIDE 35

35

Distortion Correction and Image Morphing

0:17

slide-36
SLIDE 36

36

Situational Awareness

  • ImageFlex provides API to create and draw cube maps.
  • Provides the capability to generate a full or partial ‘skybox’ from live

camera array or equirectangular videos files.

  • Facilities real-time 360 or full “spherical” situational awareness

applications via camera stitching.

  • Configuration utility enable set-up of stitched “skybox” panoramic from

camera array and capture configuration parameters for skybox application.

slide-37
SLIDE 37

37

Situational Awareness

0:27

slide-38
SLIDE 38

38

Conclusion and final messages

  • Vital Defense is key to security.
  • Autonomous will transform Defense -

Artificial Intelligence as a linchpin.

  • GPGPU-enabled deep-learning

graphics/vision/compute solutions are critical.

  • Opportunities for developers are

incredible and incredibly important!

slide-39
SLIDE 39

WE INNOVATE. WE DELIVER. YOU SUCCEED.

Thank you! Questions?

Kevin.Moran@abaco.com