Anda di halaman 1dari 84

Computer Vision

Penginderaan Visual untuk berbagai


keperluan
Dr. Mohammad Iqbal @ 2016
Disampaikan pada seminar nasional “Perkembangan Computer
Vision dan Multimedia" yang dilaksanakan oleh Himpunan
Mahasiswa Teknik Informatika Universitas Nasional pada hari
Rabu, 20 Januari 2016, di Aula Universitas Nasional Blok I lantai 4
Gunadarma University
 S3, S2, S1 and Proffessional Program
 Faculties
1. Computer Science and Information Technology
2. Industrial Technology
3. Economic
4. Civil Engineering and Plan
5. Psikology
6. Literature
 Research Organizations
 Research Organization University and for every
Faculty
 Special Science Group Discussion
 Lecturer Group Research: Foshema & Scimed
Penelitian Computer Vision di Gunadarma

Pusat Studi :
 Mikroelektronika dan Pengolahan citra –
imaging system dan smart sensor
 Robotika dan Multimedia Sistem
Multimedia dan Robotik – Implementasi
robotic vision dan data set collection
 Informatika Kedokteran – Implementasi
vision di bidang kedokteran dan kesehatan
 Interaksi Manusia dan Teknologi –
Evaluasi Interaksi mesin dengan manusia

3
Menu Seminar kita hari ini…
Apakah Computer Vision?

Penglihatan (Vision) itu Tidak Sederhana

Computer Vision Anatomy

Penggunaan Vision Hari Ini

Kesimpulan

Diskusi
Mengapa perlu belajar tentang Computer vision?
 Jutaan citra di capture setiap waktu

 Ada jutaan aplikasi yang bisa dibuat berdasarkan CV


Menu Seminar kita hari ini…
Apakah Computer Vision?

• Defenisi Komputer Grafik ? (transformasi 3D->2D)


• Defenisi Komputer grafik ? (Modeling vs. Rendering)
• Jadi Defenisi Komputer vision (2D->3D)
• Defenisi Computer Vision :
• Irisan antara Computer Vision dan Computer Graphics
• Menurut para ahli
• Permodelan berbasiskan Citra (Image-Based Modeling)
• Disiplin ilmu yang terkait
• Kecerdasan Buatan
• Dasar Matematika yang dibutuhkan
• Kaitan ilmu modern terkini untuk Computer Vision
• Lingkup Kurikulum Computer Vision di Universitas
Apakah Computer Vision?
• Kebalikan dari Komputer Grafik

Computer World
vision model

World Computer
model graphics

• Pemahaman komputer terhadap Citra (Image Understanding) secara AI, atau


menganalisis perilaku (behavior) / pola Citra
• Sensor untuk robotika
• Emulasi Komputer dari penglihatan manusia
Defenisi Komputer Grafik ? (transformasi 3D->2D)

3D geometri proyeksi

Simulasi
Sifat fisik
Grafik
Defenisi Komputer grafik ? (Modeling vs. Rendering)
 Modeling  Rendering
 Create model
 Apply material ke model Ambil “citra” dengan camera
 Tempatkan model di scene
 Tempatkan light di scene  Dua-duanya dapat selesai dengan commercial
 Tempatkan camera software: Autodesk MayaTM ,3D Studio MaxTM,
BlenderTM, etc.

Point Light

Spot
Light
Directional Light
Ambient
Light

Penggabungan pencahayaan oleh ILMU LANJUT : Grafik Komputer


Patrick Doran (2009) 9
Jadi Defenisi Komputer vision (2D->3D)

3D Geometri

Estimasi
Sifat fisik
Defenisi Computer Vision : Irisan antara Computer Vision
dan Computer Graphics

rendering shape estimation


modeling
surface design - shape motion estimation
- light
animation - motion recognition
- optics
- images 2D modeling
user-interfaces IP

Computer Graphics Computer Vision


Defenisi Computer Vision [Trucco&Verri’98]
 Trucco and Verri: computing
properties of the 3D world from
one or more digital images
 Sockman and Shapiro: To make
useful decisions about real
physical objects and scenes based
on sensed images
 Ballard and Brown: The
construction of explicit,
meaningful description of physical
objects from images
 Forsyth and Ponce: Extracting
descriptions of the world from
pictures or sequences of pictures
Defenisi Computer Vision : Permodelan berbasiskan
Citra (Image-Based Modeling)
image processing
graphics
Geometry (3D) + Photometry
Images (2D) shape appearance
vision

3 Image processing 2.1 Geometric image 2.2 Photometric


formation image formation
4 Feature extraction 5 Camera
calibration
7 Image 6 Structure
alignment from motion

8 Mosaics

9 Stereo
correspondence
11 Model-based 12 Photometric
reconstruction recovery
14 Image-based
rendering
Disiplin Ilmu yang Terkait : Kecerdasan Buatan
Kaitan ilmu modern terkini untuk Computer Vision
Lingkup Kurikulum Computer Vision

Image Computer
Processing Graphics Pattern Machine Intelligent
Recognition Learning Robotics
Computer
Vision Computational
Perception

Multi-Robot Autonomous
Systems Robotics
Multi-view
Geometry
Menu Seminar kita hari ini…
Penglihatan (Vision) itu Tidak Sederhana

• Karakteristik Human Vision


• Ilusi Adelson Checkerboard
• Warna yang konstan (Color Constancy)
• Ukuran yang Konstan (Size Constancy)
• Ilusi Thatcher

• Area Fokus Komputer Grafik dan Vision –


Hardware & Interaction

• Timeline Teknologi Computer Vision


Penglihatan (Vision) itu Tidak Sederhana
Mata Manusia Vs Kamera
Penglihatan itu Tidak Sederhana
 Penglihatan (vision) prestasi terbesar dari kecerdasan alami (natural
intelligence ) manusia
 Visual cortex menempati sekitar 50% dari bagian otak Macaque
 Seakan2 otak manusia dikhususkan utk menangani urusan vision

Itu raja atau


perdana
menteri ya ?
Karakteristik Human Vision

 Penglihatan adalah proses kontruktif


 Persepsi kesadaran dari yang kita lihat adalah ILUSI yang
dibuat oleh otak kita (dengan proses yang luar biasa
rumit).
 Contoh : kecerahan (brightness), warna (color), dan
ukuran yang konstan (size constancy)

22
Ilusi Adelson Checkerboard
Persepsi brightness adalah fungsi rumit dari nilai piksel

(Image courtesy of Ted Adelson)


Brightness constancy problem
23
Warna yang konstan (Color Constancy)
Warna Piksel sangat dipengaruhi oleh iluminasi
Persepsi dari konstannya suatu warna dikelola oleh otak kita

Sunlight Fluorescent light


(Images courtesy of David Heeger)
Ukuran yang Konstan (Size Constancy)
Ukuran obyek VS kedalaman obyek

(Images copyright John H. Kranz, 1999)


Karakteristik Human Vision

 Penglihatan akan menyelesaikan tugas tertentu


saja dalam konteks yang juga spesifik
 Umumnya kemampuan visual itu terikat langsung dengan
kebutuhan dan konteks seseorang (kebiasaan hidup,
emosional, dll).
 Contoh : Thatcher illusion
Ilusi Thatcher

(Due to P. Thompson)
Ilusi Thatcher

Face processing sensitif pada orientasi citranya


Area Fokus Komputer Grafik dan Vision – Hardware &
Interaction Screenless / Hologram technology
Wearable Teknologi
Teknologi Display
 HIGH RESOLUTION
 HIGH BRIGHTNESS
 LARGE VIEWING ANGLE
 HIGH WRITING SPEEDS
 LARGE COLOUR GAMUT
 HIGH CONTRAST
 LESS WEIGHT AND SIZE
 LOW POWER CONSUMPTION
 LOW COST Stereoscopic

Teknologi Surface /
Touch screen
Area Fokus Komputer Grafik dan Vision – Hardware &
Interaction
 Perangkat Input
 Mouse, tablet & stylus, multi-touch, force feedback, dan game controller lainnya
(seperti Wii), scanner, digital camera (images, computer vision), dsb.
 Semua bagian tubuh menjadi devais interaksi:
 http://www.xbox.com/kinect

30
Area Fokus Komputer Grafik dan Vision – Hardware &
Interaction
 Multi form Output
 Cell Phones/PDAs (smartphones), Apple iPhone™ Samsung Galaxy

laptop/desktops/tablets, SIII (Android)

Microsoft
 Microsoft PPI display Surface

 3D immersive virtual reality systems


such as Brown’s new Cave being built at
180 George Street
Microsoft PPI
display

Brown’s
old Cave
& new
Cave ILMU LANJUT : Interaksi Manusia
Komputer
Timeline Teknologi Computer Vision

# Computer Vision History graph from the


book of Richard Szeliski
Menu Seminar kita hari ini…

Computer Vision Anatomy

• Langkah2 dalam Pengolahan Citra Digital


• Sistem Pencahayaan (Lighting system)
• Staging
• Lensa dan Kamera
• Aplikasi Perangkat Lunak Vision
Computer Vision Anatomy

Pada dasarnya sistem Computer atau Machine Vision dibuat untuk


membantu menggantikan keahlian manusia pada bagian visual

34
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Level Pengolahan citra

 Level 0: Representasi citra (akuisisi, sampling, kuantisasi,


kompresi)
 Level 1: transformasi Image-to-image (enhancement,
restoration, segmentation)
 Level 2: Transformasi Image-to-parameter (feature
selection)
 Level 3: transformasi Parameter-to-decision (recognition
and interpretation)
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Kedudukan DIP, ComVis
 Image Processing: Levels 0 and 1

 Image Analysis: Levels 1 and 2

 Computer/Robot Vision: Levels 2 and 3

 Computer Graphics/Animation ?
 Pendekatan dalam “creating images” atau membuat “visual effects” dari
deksripsi yang diberikan pada level sebelumnya.
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Problem Domain
Image Morphologic
Restoration al Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description
Colour Image Image
Processing Compression
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Image Aquisition
Image Morphologic
Restoration al Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description
Colour Image Image
Processing Compression
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Image Enhancement
Image Morphologic
Restoration al Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description
Colour Image Image
Processing Compression
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Image Restoration
Image Morphologic
Restoration al Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description
Colour Image Image
Processing Compression
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Morphological Processing
Image Morphologic
Restoration al Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description
Colour Image Image
Processing Compression
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Segmentation
Image Morphologic
Restoration al Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description
Colour Image Image
Processing Compression
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Object Recognition
Image Morphologic
Restoration al Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description
Colour Image Image
Processing Compression
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Representation & Description
Image Morphologic
Restoration al Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description
Colour Image Image
Processing Compression
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Image Compression
Image Morphologic
Restoration al Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description
Colour Image Image
Processing Compression
Computer Vision Anatomy : Langkah2 dalam Pengolahan
Citra Digital - Colour Image Processing
Image Morphologic
Restoration al Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description
Colour Image Image
Processing Compression
Computer Vision Anatomy

1. Lighting
2. Staging
3. Lenses
4. Cameras
Computer Vision Anatomy : Lighting
Computer Vision Anatomy : Staging

 Parameter-parameter
penting dalam sistem
pencitraan (imaging
system).

49
Computer Vision Anatomy : Kamera dan Lensa
 Kamera dan Lensa :
 Jenis Sensor : CCD Vs CMOS (complimentary metal-oxide
semiconductor)
 Ukuran Sensor :

CCD/CMOS Size. (Image copyright of Edmund Optics).

 Cara Pembacaan : area scanning and line scanning.

50
Computer Vision Anatomy : Kamera dan Lensa
 Sistem Lensa :

Relationship between focal length, object and camera plane.


(Image copyright of Edmund Industrial Optics).

 Wide area lens (catadioptric, fisheye) Vs Basic Lens (zoom, macro,


telesentric)
 Sistem Filter Lensa : Polarization, IR, UV, …
Computer Vision Anatomy : Kamera dan Lensa
 Resolution :
Resolusi citra B lebih baik dari A.
(Image copyright of Edmund
Industrial Optic).

 Focus :

52
Computer Vision Anatomy : Kamera dan Lensa – Model
dan Geometri Kamera
Pinhole camera

or

Geometric transformations in 2D and 3D

53
Computer Vision Anatomy : Kamera dan Lensa – Camera
Calibration
 Know 2D/3D correspondences,
compute projection matrix

also radial distortion (non-linear)


Aplikasi Perangkat Lunak Vision

 HALCON dari MVTEC


http://www.mvtec.com/halcon/

HALCON is the comprehensive standard software with an integrated


development environment (IDE) for machine vision that is used worldwide. It
leads to cost savings and improved time to market: HALCON's flexible
architecture facilitates rapid development of machine vision, medical imaging,
and image analysis applications. HALCON provides outstanding performance
and a comprehensive support of multi-core platforms, MMX, and SSE2. It serves
all industries by a library of more than 1400 operators for blob analysis,
morphology, pattern matching, measuring, identification, and 3D vision, to
name just a few.
Aplikasi Perangkat Lunak Vision

COGNEX (http://www.cognex.com/Main.aspx)

 Vision Systems : All-in-one systems that combine camera, processor and vision software into a
single rugged package, with a simple and flexible user interface for configuring your
application.
 Vision Software : Vision software gives you the most flexibility for combining the full library of
powerful Cognex vision tools with the cameras, frame grabbers and peripherals of your choice,
and enables easy integration with PC-based data and control programs.
 Vision Sensors : Easy, affordable sensors that can be used in place of photoelectric sensors for
more reliable inspection, error-proofing and part detection.
 Industrial ID : Fast, reliable 1D and 2D code reading and verification for direct part mark or
high-contrast applications.
 Industry-Specific Products: A result of over 25 years of vision experience solving the most
difficult vision applications, these products include wafer identification, surface mount device
placement guidance, cylindrical product inspection and more.
 Web and Surface Inspection : Industry-leading technology for detecting and classifying
defects during the continuous production of metals, paper, nonwovens, plastics and glass.
Menu Seminar kita hari ini…

Penggunaan Vision Hari Ini


Penggunaan vision Hari Ini
Contoh state-of-the-art

Animal
Vehicle
head Four-legged

Mammal
wheel
leg

Can run, jump


Is herbivorous
Move on road Facing right
Facing right
Penggunaan vision Hari Ini
Industrial Vision

Damar Darbito, 2013 - Inspeksi Produksi Kartu Seluler


Penggunaan vision Hari Ini
Industrial Vision

Deteksi kecacatan pada mulut botol

Deteksi kecacatan dalam botol


Deteksi kecacatan pinggir botol

Benyamin, 2013 - Inspeksi Produksi Botol Susu plastik


Penggunaan vision Hari Ini
Recovery 3D layout dan context

BED

61
Penggunaan vision Hari Ini
Editing images as if they were 3D scenes
Penggunaan vision Hari Ini
Earth viewers (3D modeling)

Image from Microsoft’s Virtual Earth


(see also: Google Earth)
Penggunaan vision Hari Ini
3D from thousands of images

3D from one image

Building Rome in a Day: Agarwal et al. 2009


Hoiem Efros Hebert SIGGRAPH 2005

65
Penggunaan vision Hari Ini
Optical character recognition (OCR)

Technology to convert scanned docs to text


• If you have a scanner, it probably came with OCR software

Digit recognition, AT&T labs License plate readers


http://www.research.att.com/~yann/ http://en.wikipedia.org/wiki/Automatic_number_plate_recognition
66
Penggunaan vision Hari Ini
Face detection

 Many new digital cameras now detect faces


 Canon, Sony, Nikon …
Penggunaan vision Hari Ini
Smile detection?

Sony Cyber-shot® T70 Digital Still Camera


Penggunaan vision Hari Ini
 Object recognition (in supermarkets)

LaneHawk by EvolutionRobotics
“A smart camera is flush-mounted in the checkout
lane, continuously watching for items. When an
item is detected and recognized, the cashier
verifies the quantity of items that were found under
the basket, and continues to close the transaction.
The item can remain under the basket, and with
LaneHawk, you are assured to get paid for it… “

69
Penggunaan vision Hari Ini
Vision-based biometrics

“How the Afghan Girl was Identified by Her Iris Patterns” Read the story
wikipedia

70
Penggunaan vision Hari Ini
Login without a password…

Face recognition systems now


Fingerprint scanners on
beginning to appear more widely
many new laptops,
http://www.sensiblevision.com/
other devices
71
Penggunaan vision Hari Ini
Object recognition (in mobile phones)

Point & Find, Nokia


Google Goggles
Penggunaan vision Hari Ini
Special effects: shape capture

The Matrix movies, ESC Entertainment, XYZRGB, NRC


Penggunaan vision Hari Ini
Special effects: motion capture

Pirates of the Carribean, Industrial Light and Magic


Penggunaan vision Hari Ini
Special effects: motion capture

Based-on Ega Hegarini 2015 - Motion Analysis for sport science


Penggunaan vision Hari Ini
Sports

Sportvision first down line


Nice explanation on www.howstuffworks.com

http://www.sportvision.com/video.html

76
Penggunaan vision Hari Ini
Smart cars

 Mobileye
 Vision systems currently in high-end BMW, GM, Volvo models
 By 2010: 70% of car manufacturers.
Slide content courtesy of Amnon Shashua
Penggunaan vision Hari Ini
Smart Vision Drone
Penggunaan vision Hari Ini
Google cars

http://www.nytimes.com/2010/10/10/science/10google.html?ref=artificialintelligence
Penggunaan vision Hari Ini
Interactive Games: Kinect
 Object Recognition: http://www.youtube.com/watch?feature=iv&v=fQ59dXOo63o
 Mario: http://www.youtube.com/watch?v=8CTJL5lUjHg
 3D: http://www.youtube.com/watch?v=7QrnwoO1-8A
 Robot: http://www.youtube.com/watch?v=w8BmgtMKFbY
Penggunaan vision Hari Ini
Vision in space

NASA'S Mars Exploration Rover Spirit captured this westward view from atop
a low plateau where Spirit spent the closing months of 2007.
Vision systems (JPL) used for several tasks
• Panorama stitching
• 3D terrain modeling
• Obstacle detection, position tracking
• For more, read “Computer Vision on Mars” by Matthies et al.
Penggunaan vision Hari Ini
Industrial robots

Vision-guided robots position nut runners on wheels


Penggunaan vision Hari Ini
Mobile robots

http://www.robocup.org/

Saxena et al. 2008


NASA’s Mars Spirit Rover STAIR at Stanford
http://en.wikipedia.org/wiki/Spirit_rover
Penggunaan Vision Hari Ini
Medical imaging

3D imaging Image guided surgery


MRI, CT Grimson et al., MIT
Penggunaan vision Hari Ini
Entertainment : Video Mapping
1. Uses projection to place videographics on a
physical object.
2. Creates an optical illusion using light.
3. Transforms ordinary objects into magical living
entities.

86
www.artisuniversalis.com/educational
Kesimpulan
Hari ini sudah sama-sama kita bicarakan :
 Definisi
 Dasar Ilmu yang harus dikuasai
 Tantangannya
 Anatominya
 Implementasi Computer Vision dalam kehidupan

Selanjutnya ?
Terserah anda… (mau jadi player?
Atau mau jadi penonton saja?)
merci 
Thank You

Terima Kasih

Question?
δ Itot